ALBERT

Description: The use of synthetic sequences is one of the most promising tools for advanced in silico evaluation of the quantification of cardiac deformation and strain through 3-D ultrasound (US) and magnetic resonance (MR) imaging. In this paper, we propose the first simulation framework which allows the generation of realistic 3-D synthetic cardiac US and MR (both cine and tagging) image sequences from the same virtual patient. A state-of-the-art electromechanical (E/M) model was exploited for simulating groundtruth cardiac motion fields ranging from healthy to various pathological cases, including both ventricular dyssynchrony and myocardial ischemia. The E/M groundtruth along with template MR/US images and physical simulators were combined in a unified framework for generating synthetic data. We efficiently merged several warping strategies to keep the full control of myocardial deformations while preserving realistic image texture. In total, we generated 18 virtual patients, each with synthetic 3-D US, cine MR, and tagged MR sequences. The simulated images were evaluated both qualitatively by showing realistic textures and quantitatively by observing myocardial intensity distributions similar to real data. In particular, the US simulation showed a smoother myocardium/background interface than the state-of-the-art. We also assessed the mechanical properties. The pathological subjects were discriminated from the healthy ones by both global indexes (ejection fraction and the global circumferential strain) and regional strain curves. The synthetic database is comprehensive in terms of both pathology and modality, and has a level of realism sufficient for validation purposes. All the 90 sequences are made publicly available to the research community via an open-access database.

Description: Collecting large databases of annotated medical images is crucial for the validation and testing of feature extraction, statistical analysis, and machine learning algorithms. Recent advances in cardiac electromechanical modeling and image synthesis provided a framework to generate synthetic images based on realistic mesh simulations. Nonetheless, their potential to augment an existing database with large amounts of synthetic cases requires further investigation. We build upon these works and propose a revised scheme for synthesizing pathological cardiac sequences from real healthy sequences. Our new pipeline notably involves a much easier registration problem to reduce potential artifacts, and takes advantage of mesh correspondences to generate new data from a given case without additional registration. The output sequences are thoroughly examined in terms of quality and usability on a given application: the assessment of myocardial viability, via the generation of 465 synthetic cine MR sequences (15 healthy and 450 with pathological tissue viability [random location, extent, and grade, up to myocardial infarct]). We demonstrate that: 1) our methodology improves the state-of-the-art algorithms in terms of realism and accuracy of the simulated images and 2) our methodology is well-suited for the generation of large databases at small computational cost.

Description: It is generally recognized that color information is central to the automatic and visual analysis of histopathology tissue slides. In practice, pathologists rely on color, which reflects the presence of specific tissue components, to establish a diagnosis. Similarly, automatic histopathology image analysis algorithms rely on color or intensity measures to extract tissue features. With the increasing access to digitized histopathology images, color variation and its implications have become a critical issue. These variations are the result of not only a variety of factors involved in the preparation of tissue slides but also in the digitization process itself. Consequently, different strategies have been proposed to alleviate stain-related tissue inconsistencies in automatic image analysis systems. Such techniques generally rely on collecting color statistics to perform color matching across images. In this work, we propose a different approach for stain normalization that we refer to as stain transfer. We design a discriminative image analysis model equipped with a stain normalization component that transfers stains across datasets. Our model comprises a generative network that learns data set-specific staining properties and image-specific color transformations as well as a task-specific network (e.g., classifier or segmentation network). The model is trained end-to-end using a multi-objective cost function. We evaluate the proposed approach in the context of automatic histopathology image analysis on three data sets and two different analysis tasks: tissue segmentation and classification. The proposed method achieves superior results in terms of accuracy and quality of normalized images compared to various baselines.

Description: In medical image analysis applications, the availability of the large amounts of annotated data is becoming increasingly critical. However, annotated medical data is often scarce and costly to obtain. In this paper, we address the problem of synthesizing retinal color images by applying recent techniques based on adversarial learning. In this setting, a generative model is trained to maximize a loss function provided by a second model attempting to classify its output into real or synthetic. In particular, we propose to implement an adversarial autoencoder for the task of retinal vessel network synthesis. We use the generated vessel trees as an intermediate stage for the generation of color retinal images, which is accomplished with a generative adversarial network. Both models require the optimization of almost everywhere differentiable loss functions, which allows us to train them jointly. The resulting model offers an end-to-end retinal image synthesis system capable of generating as many retinal images as the user requires, with their corresponding vessel networks, by sampling from a simple probability distribution that we impose to the associated latent space. We show that the learned latent space contains a well-defined semantic structure, implying that we can perform calculations in the space of retinal images, e.g., smoothly interpolating new data points between two retinal images. Visual and quantitative results demonstrate that the synthesized images are substantially different from those in the training set, while being also anatomically consistent and displaying a reasonable visual quality.

Description: Multi-modality medical imaging is increasingly used for comprehensive assessment of complex diseases in either diagnostic examinations or as part of medical research trials. Different imaging modalities provide complementary information about living tissues. However, multi-modal examinations are not always possible due to adversary factors, such as patient discomfort, increased cost, prolonged scanning time, and scanner unavailability. In additionally, in large imaging studies, incomplete records are not uncommon owing to image artifacts, data corruption or data loss, which compromise the potential of multi-modal acquisitions. In this paper, we propose a weakly coupled and geometry co-regularized joint dictionary learning method to address the problem of cross-modality synthesis while considering the fact that collecting the large amounts of training data is often impractical. Our learning stage requires only a few registered multi-modality image pairs as training data. To employ both paired images and a large set of unpaired data, a cross-modality image matching criterion is proposed. Then, we propose a unified model by integrating such a criterion into the joint dictionary learning and the observed common feature space for associating cross-modality data for the purpose of synthesis. Furthermore, two regularization terms are added to construct robust sparse representations. Our experimental results demonstrate superior performance of the proposed model over state-of-the-art methods.

Description: The simultaneous removal of noise and preservation of the integrity of 3-D magnetic resonance (MR) images is a difficult and important task. In this paper, we consider characterizing MR images with 3-D operators, and present a novel 4-D transform-domain method termed ‘modified nonlocal tensor-SVD (MNL-tSVD)’ for MR image denoising. The proposed method is based on the grouping, hard-thresholding and aggregation paradigms, and can be viewed as a generalized nonlocal extension of tensor-SVD (t-SVD). By keeping MR images in its natural three-dimensional form, and collaboratively filtering similar patches, MNL-tSVD utilizes both the self-similarity property and 3-D structure of MR images to preserve more actual details and minimize the introduction of new artifacts. We show the adaptability of MNL-tSVD by incorporating it into a two-stage denoising strategy with a few adjustments. In addition, analysis of the relationship between MNL-tSVD and current the state-of-the-art 4-D transforms is given. Experimental comparisons over simulated and real brain data sets at different Rician noise levels show that MNL-tSVD can produce competitive performance compared with related approaches.

Description: Recent advances in imaging genetics produce large amounts of data including functional MRI images, single nucleotide polymorphisms (SNPs), and cognitive assessments. Understanding the complex interactions among these heterogeneous and complementary data has the potential to help with diagnosis and prevention of mental disorders. However, limited efforts have been made due to the high dimensionality, group structure, and mixed type of these data. In this paper, we present a novel method to detect conditional associations between imaging genetics data. We use projected distance correlation to build a conditional dependency graph among high-dimensional mixed data, and then use multiple testing to detect significant group level associations (e.g., regions of interest-gene). In addition, we introduce a scalable algorithm based on orthogonal greedy algorithm, yielding the greedy projected distance correlation (G-PDC). This can reduce the computational cost, which is critical for analyzing large volume of imaging genomics data. The results from our simulations demonstrate a higher degree of accuracy with G-PDC than distance correlation, Pearson’s correlation, and partial correlation, especially when the correlation is nonlinear. Finally, we apply our method to the Philadelphia Neurodevelopmental data cohort with 866 samples including fMRI images and SNP profiles. The results uncover several statistically significant and biologically interesting interactions, which are further validated with many existing studies. The MATLAB code is available at https://sites.google.com/site/jianfang86/gPDC .

Description: We present a multi-scale approach of tumor modeling in order to predict its evolution during radiotherapy. Within this context we focus on three different scales of tumor modeling: microscopic (individual cells in a voxel), mesoscopic (population of cells in a voxel) and macroscopic (whole tumor), with transition interfaces between these three scales. At the cellular level, the description is based on phase transfer probabilities in the cellular cycle. At the mesoscopic scale we represent populations of cells according to different stages in a cell cycle. Finally, at the macroscopic scale, the tumor description is based on the use of FDG PET image voxels. These three scales exist naturally: biological data are collected at the macroscopic scale, but the pathological behavior of the tumor is based on an abnormal cell-cycle at the microscopic scale. On the other hand, the introduction of a mesoscopic scale is essential in order to reduce the gap between the two extreme, in terms of resolution, description levels. It also reduces the computational burden of simulating a large number of individual cells. As an application of the proposed multi-scale model, we simulate the effect of oxygen on tumor evolution during radiotherapy. Two consecutive FDG PET images of 17 rectal cancer patients undergoing radiotherapy are used to simulate the tumor evolution during treatment. The simulated results are compared with those obtained on a third FDG PET image acquired two weeks after the beginning of the treatment.

Description: In this paper, we investigate the estimation of the maximum target registration error (TRE) magnitude of the target location while using point-based rigid registration in the image guided system. Under the uniform restriction of fiducial localization error (FLE) magnitude, we explicitly formulate the estimation as an optimization problem. Through analyzing the approximated problem which assumes the rigidity of the fiducial set holds with the perturbation of FLE, we present a strict lower bound for the maximum TRE magnitude. The simulations show that the lower bound is close to the actual maximum TRE magnitude for the target locations lying far away from the fiducial points. Unlike the expected TRE magnitude in which all fiducial points contribute, the lower bound is only related to the fiducial points serving as the vertices of the convex hull of the fiducial set. Our analysis provides a new perspective of investigating the problem of TRE estimation and is helpful for the surgeons to learn about the worst situation during using the image guided system.

Description: Brain tumors are the most common malignant neurologic tumors with the highest mortality and disability rate. Because of the delicate structure of the brain, the clinical use of several commonly used biopsy diagnosis is limited for brain tumors. Radiomics is an emerging technique for noninvasive diagnosis based on quantitative medical image analyses. However, current radiomics techniques are not standardized regarding feature extraction, feature selection, and decision making. In this paper, we propose a sparse representation-based radiomics (SRR) system for the diagnosis of brain tumors. First, we developed a dictionary learning- and sparse representation-based feature extraction method that exploits the statistical characteristics of the lesion area, leading to fine and more effective feature extraction compared with the traditional explicitly calculation-based methods. Then, we set up an iterative sparse representation method to solve the redundancy problem of the extracted features. Finally, we proposed a novel multi-feature collaborative sparse representation classification framework that introduces a new coefficient of regularization term to combine features from multi-modal images at the sparse representation coefficient level. Two clinical problems were used to validate the performance and usefulness of the proposed SRR system. One was the differential diagnosis between primary central nervous system lymphoma (PCNSL) and glioblastoma (GBM), and the other was isocitrate dehydrogenase 1 estimation for gliomas. The SRR system had superior PCNSL and GBM differentiation performance compared with some advanced imaging techniques and yielded 11% better performance for estimating IDH1 compared with the traditional radiomics methods.

Description: We present the first in vivo images of anisotropic conductivity distribution in the human head, measured at a frequency of approximately 10 Hz. We used magnetic resonance electrical impedance tomography techniques to encode phase changes caused by current flow within the head via two independent electrode pairs. These results were then combined with diffusion tensor imaging data to reconstruct full anisotropic conductivity distributions in 5-mm-thick slices of the brains of two participants. Conductivity values recovered in this paper were broadly consistent with literature values. We anticipate that this technique will be of use in many areas of neuroscience, most importantly in functional imaging via inverse electroencephalogram. Future studies will involve pulse sequence acceleration to maximize brain coverage and resolution.

Description: The most commonly used evaluation metrics for quality assessment of retinal vessel segmentation are sensitivity, specificity, and accuracy, which are based on pixel-to-pixel matching. However, due to the inter-observer problem that vessels annotated by different observers vary in both thickness and location, pixel-to-pixel matching is too restrictive to fairly evaluate the results of vessel segmentation. In this paper, the proposed skeletal similarity metric is constructed by comparing the skeleton maps generated from the reference and the source vessel segmentation maps. To address the inter-observer problem, instead of using a pixel-to-pixel matching strategy, each skeleton segment in the reference skeleton map is adaptively assigned with a searching range whose radius is determined based on its vessel thickness. Pixels in the source skeleton map located within the searching range are then selected for similarity calculation. The skeletal similarity consists of a curve similarity, which measures the structural similarity between the reference and the source skeleton maps and a thickness similarity, which measures the thickness consistency between the reference and the source vessel segmentation maps. In contrast to other metrics that provide a global score for the overall performance, we modify the definitions of true positive, false negative, true negative, and false positive based on the skeletal similarity, based on which sensitivity, specificity, accuracy, and other objective measurements can be constructed. More importantly, the skeletal similarity metric has better potential to be used as a pixelwise loss function for training deep learning models for retinal vessel segmentation. Through comparison of a set of examples, we demonstrate that the redefined metrics based on the skeletal similarity are more effective for quality evaluation, especially with greater tolerance to the inter-observer problem.

Description: We are developing a 1-mm 3 resolution, high-sensitivity positron emission tomography (PET) system for loco-regional cancer imaging. The completed system will comprise two $16.5times 10$ cm detector panels and contain 4 608 position sensitive avalanche photodiodes (PSAPDs) coupled to arrays of $0.9times 0.9times 1$ mm 3 LYSO crystal elements for a total of 294 912 crystal elements. For the first time, this paper summarizes the design and reports the performance of a significant portion of the final clinical PET system, comprising 1 536 PSAPDs, 98 304 crystal elements, and an active field-of-view (FOV) of $16.5times3.3$ cm. The sub-system performance parameters, such as energy, time, and spatial resolutions are predictive of the performance of the final system due to the modular design. Analysis of the multiplexed crystal flood histograms shows 84% of the crystal elements have〉99% crystal identification accuracy. The 511 keV photopeak energy resolution was 11.34±0.06% full-width half maximum (FWHM), and coincidence timing resolution was 13.92 ± 0.01 ns FWHM at 511 keV. The spatial resolution was measured using maximum likelihood expectation maximization reconstruction of a grid of point sources suspended in warm background. The averaged resolution over the central 6 cm of the FOV is 1.01 ± 0.13 mm in the X-direction, 1.84 ± 0.20 mm in the Y-direction, and 0.84 ± 0.11 mm in the Z-direction. Quantitative analysis of acquired micro-Derenzo phantom images shows better than 1.2 mm resolution at the center of the FOV, with subsequent resolution degradation in the y-direction toward the edge of the FOV caused by limited angle tomography effec- s.

Description: We consider the challenges in estimating the state-related changes in brain connectivity networks with a large number of nodes. Existing studies use the sliding-window analysis or time-varying coefficient models, which are unable to capture both smooth and abrupt changes simultaneously, and rely on ad-hoc approaches to the high-dimensional estimation. To overcome these limitations, we propose a Markov-switching dynamic factor model, which allows the dynamic connectivity states in functional magnetic resonance imaging (fMRI) data to be driven by lower-dimensional latent factors. We specify a regime-switching vector autoregressive (SVAR) factor process to quantity the time-varying directed connectivity. The model enables a reliable, data-adaptive estimation of change-points of connectivity regimes and the massive dependencies associated with each regime. We develop a three-step estimation procedure: 1) extracting the factors using principal component analysis, 2) identifying connectivity regimes in a low-dimensional subspace based on the factor-based SVAR model, and 3) constructing high-dimensional state connectivity metrics based on the subspace estimates. Simulation results show that our estimator outperforms $K$ -means clustering of time-windowed coefficients, providing more accurate estimate of time-evolving connectivity. It achieves percentage of reduction in mean squared error by 60% when the network dimension is comparable to the sample size. When applied to the resting-state fMRI data, our method successfully identifies modular organization in the resting-statenetworksin consistencywith other studies. It further reveals changes in brain states with variations across subjects and distinct large-scale directed connectivity patterns across states.

Description: This paper reports on the feasibility of using a quasi-Newton optimization algorithm, limited-memory Broyden-Fletcher-Goldfarb-Shanno with boundary constraints (L-BFGS-B), for penalized image reconstruction problems in emission tomography (ET). For further acceleration, an additional preconditioning technique based on a diagonal approximation of the Hessian was introduced. The convergence rate of L-BFGS-B and the proposed preconditioned algorithm (L-BFGS-B-PC) was evaluated with simulated data with various factors, such as the noise level, penalty type, penalty strength and background level. Data of three 18 F-FDG patient acquisitions were also reconstructed. Results showed that the proposed L-BFGS-B-PC outperforms L-BFGS-B in convergence rate for all simulated conditions and the patient data. Based on these results, L-BFGS-B-PC shows promise for clinical application.

Description: Attenuation correction for positron-emission tomography (PET)/magnetic resonance (MR) hybrid imaging systems and dose planning for MR-based radiation therapy remain challenging due to insufficient high-energy photon attenuation information. We present a novel approach that uses the learned nonlinear local descriptors and feature matching to predict pseudo computed tomography (pCT) images from T1-weighted and T2-weighted magnetic resonance imaging (MRI) data. The nonlinear local descriptors are obtained by projecting the linear descriptors into the nonlinear high-dimensional space using an explicit feature map and low-rank approximation with supervised manifold regularization. The nearest neighbors of each local descriptor in the input MR images are searched in a constrained spatial range of the MR images among the training dataset. Then the pCT patches are estimated through k-nearest neighbor regression. The proposed method for pCT prediction is quantitatively analyzed on a dataset consisting of paired brain MRI and CT images from 13 subjects. Our method generates pCT images with a mean absolute error (MAE) of 75.25 ± 18.05 Hounsfield units, a peak signal-to-noise ratio of 30.87 ± 1.15 dB, a relative MAE of 1.56 ± 0.5% in PET attenuation correction, and a dose relative structure volume difference of 0.055 ± 0.107% in ${D}_{98%}$ , as compared with true CT. The experimental results also show that our method outperforms four state-of-the-art methods.

Description: Robust and effective shape prior modeling from a set of training data remains a challenging task, since the shape variation is complicated, and shape models should preserve local details as well as handle shape noises. To address these challenges, a novel robust projective dictionary learning (RPDL) scheme is proposed in this paper. Specifically, the RPDL method integrates the dimension reduction and dictionary learning into a unified framework for shape prior modeling, which can not only learn a robust and representative dictionary with the energy preservation of the training data, but also reduce the dimensionality and computational cost via the subspace learning. In addition, the proposed RPDL algorithm is regularized by using the $ell _{1}$ norm to handle the outliers and noises, and is embedded in an online framework so that of memory and time efficiency. The proposed method is employed to model prostate shape prior for the application of magnetic resonance transrectal ultrasound registration. The experimental results demonstrate that our method provides more accurate and robust shape modeling than the state-of-the-art methods do. The proposed RPDL method is applicable for modeling other organs, and hence, a general solution for the problem of shape prior modeling.

Description: Hyperpolarized MRI with 13 C-labelled compounds is an emerging clinical technique allowing in vivo metabolic processes to be characterized non-invasively. Accurate quantification of 13 C data, both for clinical and research purposes, typically relies on the use of region-of-interest analysis to detect and compare regions of altered metabolism. However, it is not clear how this should be determined from the five-dimensional data produced and most standard methodologies are unable to exploit the multidimensional nature of the data. Here we propose a solution to the novel problem of 13 C image segmentation using a hybrid Markov random field model with continuous fuzzy logic. The algorithm fully utilizes the multi-dimensional data format in order to classify each voxel into one of six distinct classes based on its metabolic characteristics. Bayesian priors fully incorporate spatial, temporal and ratiometric contextual information whilst image contrast from multiple spectral dimensions are considered concurrently by using an analogy from color image segmentation. Performance of the algorithm is demonstrated on in silico data, where the superiority of the approach over a reference thresholding method is consistently observed. Application to in vivo animal data from a pre-clinical subcutaneous tumor model illustrates the ability of the MRF algorithm to successfully detect tumor location whilst avoiding image artifacts. This work has the potential to assist the analysis of human hyperpolarized 13 C data in the future.

Description: Recently, the growing emphasis on medical ultrasound (US) has led to a rapid development of US extended field-of-view (EFOV) techniques. US EFOV techniques can be classified into three categories: 2-D US EFOV, 3-D US, and 3-D US EFOV. In this paper, we propose a novel EFOV method called 2.5-D US EFOV that combines both the advantages of the 2-D US EFOV and the 3-D US by generating a panorama on a curved image plane guided by a curved scanning trajectory of the US probe. In 2.5-D US EFOV, the real-time position and orientation of the US image plane can be recorded via an electromagnetic spatial sensor attached to the probe. The scanning direction is not necessarily straight and can be curved according to the regions of interest (ROI). To form the curved panorama, an image cutting method is proposed. Finally, the curved panorama is rendered in a 3-D space using a surface rendering based on a texture mapping technique. This allows 3-D measurements of lines and angles. Phantom experiments demonstrated that 2.5-D US EFOV images could show anatomical structures of ROI accurately and rapidly. The overall average errors for the distance and angle measurements are −0.097 ± 0.128 cm (−1% ± 1.2%) and 1.50° ± 1.60° (1.9% ± 2%), respectively. A typical extended US image can be reconstructed from 321 B-scans images within 3 s. The satisfying quantitative result on the spinal tissues of a scoliosis subject demonstrates that our system has potential applications in the assessment of musculoskeletal issues.

Description: Ultrafast ultrasound imaging using plane or diverging waves, instead of focused beams, has advanced greatly the development of novel ultrasound imaging methods for evaluating tissue functions beyond anatomical information. However, the sonographic signal-to-noise ratio (SNR) of ultrafast imaging remains limited due to the lack of transmission focusing, and thus insufficient acoustic energy delivery. We hereby propose a new ultrafast ultrasound imaging methodology with cascaded dual-polarity waves (CDWs), which consists of a pulse train with positive and negative polarities. A new coding scheme and a corresponding linear decoding process were thereby designed to obtain the recovered signals with increased amplitude, thus increasing the SNR without sacrificing the frame rate. The newly designed CDW ultrafast ultrasound imaging technique achieved higher quality B-mode images than coherent plane-wave compounding (CPWC) and multiplane wave (MW) imaging in a calibration phantom, ex vivo pork belly, and in vivo human back muscle. CDW imaging shows a significant improvement in the SNR (10.71 dB versus CPWC and 7.62 dB versus MW), penetration depth (36.94% versus CPWC and 35.14% versus MW), and contrast ratio in deep regions (5.97 dB versus CPWC and 5.05 dB versus MW) without compromising other image quality metrics, such as spatial resolution and frame rate. The enhanced image qualities and ultrafast frame rates offered by CDW imaging beget great potential for various novel imaging applications.

Description: Automated 3-D breast ultrasound has been proposed as a complementary modality to mammography for early detection of breast cancers. To facilitate the interpretation of these images, computer aided detection systems are being developed in which mass segmentation is an essential component for feature extraction and temporal comparisons. However, automated segmentation of masses is challenging because of the large variety in shape, size, and texture of these 3-D objects. In this paper, the authors aim to develop a computerized segmentation system, which uses a seed position as the only priori of the problem. A two-stage segmentation approach has been proposed incorporating shape information of training masses. At the first stage, a new adaptive region growing algorithm is used to give a rough estimation of the mass boundary. The similarity threshold of the proposed algorithm is determined using a Gaussian mixture model based on the volume and circularity of the training masses. In the second stage, a novel geometric edge-based deformable model is introduced using the result of the first stage as the initial contour. In a data set of 50 masses, including 38 malignant and 12 benign lesions, the proposed segmentation method achieved a mean Dice of 0.74 ± 0.19 which outperformed the adaptive region growing with a mean Dice of 0.65 ± 0.2 (p-value < 0.02). Moreover, the resulting mean Dice was significantly (p-value < 0.001) better than that of the distance regularized level set evolution method (0.52 ± 0.27). The supervised method presented in this paper achieved accurate mass segmentation results in terms of Dice measure. The suggested segmentation method can be utilized in two aspects: 1) to automatically measure the change in volume of breast lesions over time and 2) to extract features for a computer aided detection or diagnosis system.

Description: Automated cell segmentation and tracking is essential for dynamic studies of cellular morphology, movement, and interactions as well as other cellular behaviors. However, accurate, automated, and easy-to-use cell segmentation remains a challenge, especially in cases of high cell densities, where discrete boundaries are not easily discernable. Here, we present a fully automated segmentation algorithm that iteratively segments cells based on the observed distribution of optical cell volumes measured by quantitative phase microscopy. By fitting these distributions to known probability density functions, we are able to converge on volumetric thresholds that enable valid segmentation cuts. Since each threshold is determined from the observed data itself, virtually no input is needed from the user. We demonstrate the effectiveness of this approach over time using six cell types that display a range of morphologies, and evaluate these cultures over a range of confluencies. Facile dynamic measures of cell mobility and function revealed unique cellular behaviors that relate to tissue origins, state of differentiation, and real-time signaling. These will improve our understanding of multicellular communication and organization.

Description: We present a novel approach to the problem of neuron segmentation in image volumes acquired by an electron microscopy. Existing methods, such as agglomerative or correlation clustering, rely solely on boundary evidence and have problems where such an evidence is lacking (e.g., incomplete staining) or ambiguous (e.g., co-located cell and mitochondria membranes). We investigate if these difficulties can be overcome by means of sparse region appearance cues that differentiate between pre- and postsynaptic neuron segments in mammalian neural tissue. We combine these cues with the traditional boundary evidence in the asymmetric multiway cut (AMWC) model, which simultaneously solves the partitioning and the semantic region labeling problems. We show that AMWC problems over superpixel graphs can be solved to global optimality with a cutting plane approach, and that the introduction of semantic class priors leads to significantly better segmentations.

Description: Positron emission tomography (PET) is a functional imaging modality widely used in oncology, cardiology, and neuroscience. It is highly sensitive, but suffers from relatively poor spatial resolution, as compared with anatomical imaging modalities, such as magnetic resonance imaging (MRI). With the recent development of combined PET/MR systems, we can improve the PET image quality by incorporating MR information into image reconstruction. Previously, kernel learning has been successfully embedded into static and dynamic PET image reconstruction using either PET temporal or MRI information. Here, we combine both PET temporal and MRI information adaptively to improve the quality of direct Patlak reconstruction. We examined different approaches to combine the PET and MRI information in kernel learning to address the issue of potential mismatches between MRI and PET signals. Computer simulations and hybrid real-patient data acquired on a simultaneous PET/MR scanner were used to evaluate the proposed methods. Results show that the method that combines PET temporal information and MRI spatial information adaptively based on the structure similarity index has the best performance in terms of noise reduction and resolution improvement.

Description: We present a novel reconstruction algorithm based on a general cone-beam CT forward model, which is capable of incorporating the blur and noise correlations that are exhibited in flat-panel CBCT measurement data. Specifically, the proposed model may include scintillator blur, focal-spot blur, and noise correlations due to light spread in the scintillator. The proposed algorithm (GPL-BC) uses a Gaussian Penalized-Likelihood objective function, which incorporates models of blur and correlated noise. In a simulation study, GPL-BC was able to achieve lower bias as compared with deblurring followed by FDK as well as a model-based reconstruction method without integration of measurement blur. In the same study, GPL-BC was able to achieve better line-pair reconstructions (in terms of segmented-image accuracy) as compared with deblurring followed by FDK, a model-based method without blur, and a model-based method with blur but not noise correlations. A prototype extremities quantitative cone-beam CT test-bench was used to image a physical sample of human trabecular bone. These data were used to compare reconstructions using the proposed method and model-based methods without blur and/or correlation to a registered $mu $ CT image of the same bone sample. The GPL-BC reconstructions resulted in more accurate trabecular bone segmentation. Multiple trabecular bone metrics, including trabecular thickness (Tb.Th.) were computed for each reconstruction approach as well as the $mu $ CT volume. The GPL-BC reconstruction provided the most accurate Tb.Th. measurement, 0.255 mm, as compared with the $mu $ CT derived value of 0.193 mm, followed by the GPL-B reconstruction, the GPL-I reconstruction, and then the FDK reconstruction (0.271 mm, 0.309 mm, and 0.335 mm, respect- vely).

Description: Computer-aided diagnosis (CAD) of retinal pathologies is a current active area in medical image analysis. Due to the increasing use of retinal optical coherence tomography (OCT) imaging technique, a CAD system in retinal OCT is essential to assist ophthalmologist in the early detection of ocular diseases and treatment monitoring. This paper presents a novel CAD system based on a multi-scale convolutional mixture of expert (MCME) ensemble model to identify normal retina, and two common types of macular pathologies, namely, dry age-related macular degeneration, and diabetic macular edema. The proposed MCME modular model is a data-driven neural structure, which employs a new cost function for discriminative and fast learning of image features by applying convolutional neural networks on multiple-scale sub-images. MCME maximizes the likelihood function of the training data set and ground truth by considering a mixture model, which tries also to model the joint interaction between individual experts by using a correlated multivariate component for each expert module instead of only modeling the marginal distributions by independent Gaussian components. Two different macular OCT data sets from Heidelberg devices were considered for the evaluation of the method, i.e., a local data set of OCT images of 148 subjects and a public data set of 45 OCT acquisitions. For comparison purpose, we performed a wide range of classification measures to compare the results with the best configurations of the MCME method. With the MCME model of four scale-dependent experts, the precision rate of 98.86%, and the area under the receiver operating characteristic curve (AUC) of 0.9985 were obtained on average.

Description: Inhomogeneities in the transmit radio frequency magnetic field ( ${text{B}}_{1}^{+}$ ) reduce the quality of magnetic resonance (MR) images. This quality can be improved by using high-permittivity pads that tailor the ${text{B}}_{1}^{+}$ fields. The design of an optimal pad is application-specific and not straightforward and would therefore benefit from a systematic optimization approach. In this paper, we propose such a method to efficiently design dielectric pads. To this end, a projection-based model order reduction technique is used that significantly decreases the dimension of the design problem. Subsequently, the resulting reduced-order model is incorporated in an optimization method in which a desired field in a region of interest can be set. The method is validated by designing a pad for imaging the cerebellum at 7 T. The optimal pad that is found is used in an MR measurement to demonstrate its effectiveness in improving the image quality.

Description: In this article, we evaluate Parallel Level Sets (PLS) and Bowsher’s method as segmentation-free anatomical priors for regularized brain positron emission tomography (PET) reconstruction. We derive the proximity operators for two PLS priors and use the EM-TV algorithm in combination with the first order primal-dual algorithm by Chambolle and Pock to solve the non-smooth optimization problem for PET reconstruction with PLS regularization. In addition, we compare the performance of two PLS versions against the symmetric and asymmetric Bowsher priors with quadratic and relative difference penalty function. For this aim, we first evaluate reconstructions of 30 noise realizations of simulated PET data derived from a real hybrid positron emission tomography/magnetic resonance imaging (PET/MR) acquisition in terms of regional bias and noise. Second, we evaluate reconstructions of a real brain PET/MR data set acquired on a GE Signa time-of-flight PET/MR in a similar way. The reconstructions of simulated and real 3D PET/MR data show that all priors were superior to post-smoothed maximum likelihood expectation maximization with ordered subsets (OSEM) in terms of bias-noise characteristics in different regions of interest where the PET uptake follows anatomical boundaries. Our implementation of the asymmetric Bowsher prior showed slightly superior performance compared with the two versions of PLS and the symmetric Bowsher prior. At very high regularization weights, all investigated anatomical priors suffer from the transfer of non-shared gradients.

Description: Presents the table of contents for this issue of this publication.

Description: In X-ray fluoroscopy, static overlays are used to visualize soft tissue. We propose a system for cardiac and respiratory motion compensation of these overlays. It consists of a 3-D motion model created from real-time magnetic resonance (MR) imaging. Multiple sagittal slices are acquired and retrospectively stacked to consistent 3-D volumes. Slice stacking considers cardiac information derived from the ECG and respiratory information extracted from the images. Additionally, temporal smoothness of the stacking is enhanced. Motion is estimated from the MR volumes using deformable 3-D/3-D registration. The motion model itself is a linear direct correspondence model using the same surrogate signals as slice stacking. In X-ray fluoroscopy, only the surrogate signals need to be extracted to apply the motion model and animate the overlay in real time. For evaluation, points are manually annotated in oblique MR slices and in contrast-enhanced X-ray images. The 2-D Euclidean distance of these points is reduced from 3.85 to 2.75 mm in MR and from 3.0 to 1.8 mm in X-ray compared with the static baseline. Furthermore, the motion-compensated overlays are shown qualitatively as images and videos.

Description: We present a novel approach for improving the shape statistics of medical image objects by generating correspondence of skeletal points. Each object’s interior is modeled by an s-rep, i.e., by a sampled, folded, two-sided skeletal sheet with spoke vectors proceeding from the skeletal sheet to the boundary. The skeleton is divided into three parts: the up side, the down side, and the fold curve. The spokes on each part are treated separately and, using spoke interpolation, are shifted along that skeleton in each training sample so as to tighten the probability distribution on those spokes’ geometric properties while sampling the object interior regularly. As with the surface/boundary-based correspondence method of Cates et al. , entropy is used to measure both the probability distribution tightness and the sampling regularity, here of the spokes’ geometric properties. Evaluation on synthetic and real world lateral ventricle and hippocampus data sets demonstrate improvement in the performance of statistics using the resulting probability distributions. This improvement is greater than that achieved by an entropy-based correspondence method on the boundary points.

Description: Histotripsy utilizes focused ultrasound to generate bubble clouds for transcutaneous tissue liquefaction. Bubble activity maps are under development to provide image guidance and monitor treatment progress. The aim of this paper was to investigate the feasibility of using plane wave B-mode and passive cavitation images to be used as binary classifiers of histotripsy-induced liquefaction. Prostate tissue phantoms were exposed to histotripsy pulses over a range of pulse durations (5– $20~mu text{s}$ ) and peak negative pressures (12–23 MPa). Acoustic emissions were recorded during the insonation and beamformed to form passive cavitation images. Plane wave B-mode images were acquired following the insonation to detect the hyperechoic bubble cloud. Phantom samples were sectioned and stained to delineate the liquefaction zone. Correlation between passive cavitation and plane wave B-mode images and the liquefaction zone was assessed using receiver operating characteristic (ROC) curve analysis. Liquefaction of the phantom was observed for all the insonation conditions. The area under the ROC (0.94 versus 0.82), accuracy (0.90 versus 0.83), and sensitivity (0.81 versus 0.49) was greater for passive cavitation images relative to B-mode images ( ${p} 〈 0.05$ ) along the azimuth of the liquefaction zone. The specificity was greater than 0.9 for both imaging modalities. These results demonstrate a stronger correlation between histotripsy-induced liquefaction and passive cavitation imaging compared with the plane wave B-mode imaging, albeit with limited passive cavitation image range resolution.

Description: We present a direct (noniterative) algorithm for 1-D quadratic data fitting with neighboring intensity differences penalized by the Huber function. Applications of such an algorithm include 1-D processing of medical signals, such as smoothing of tissue time concentration curves in kinetic data analysis or sinogram preprocessing, and using it as a subproblem solver for 2-D or 3-D image restoration and reconstruction. dynamic programming was used to develop the direct algorithm. The problem was reformulated as a sequence of univariate optimization problems, for ${k} =textsf {1}, ldots , {N}$ , where ${N}$ is the number of data points. The solution to the univariate problem at index ${k}$ is parameterized by the solution at ${k}+textsf {1}$ , except at ${k}={N}$ . Solving the univariate optimization problem at ${k}={N}$ yields the solution to each problem in the sequence using back-tracking. Computational issues and memory cost are discussed in detail. Two numerical studies, tissue concentration curve smoothing and sinogram preprocessing for image reconstruction, are used to validate the direct algorithm and illustrate its practical applications. In the example of 1-D curve smoothing, the efficiency of the direct algorithm is compared with four iterative methods: the iterative coordinate descent, Nesterov’s accelerated gradient descent algorithm, FISTA, and an off-the-shelf second order method. The first two methods were applied to the primal problem, the others to the dual problem. The comparisons show that the direct - lgorithm outperforms all other methods by a significant factor, which rapidly grows with the curvature of the Huber function. The second example, sinogram preprocessing, showed that robustness and speed of the direct algorithm are maintained over a wide range of signal variations, and that noise and streaking artifacts could be reduced with almost no increase in computation time. We also outline how the proposed 1-D solver can be used for imaging applications.

Description: We present a comparative study for discriminative anatomy detection in high dimensional neuroimaging data. While most studies solve this problem using mass univariate approaches, recent works show better accuracy and variable selection using a sparse classification model. Two types of image-based regularization methods have been proposed in the literature based on either a Graph Net (GN) model or a total variation (TV) model. These studies showed increased classification accuracy and interpretability of results when using image-based regularization, but did not look at the accuracy and quality of the recovered significant regions. In this paper, we theoretically prove bounds on the recovered sparse coefficients and the corresponding selected image regions in four models (two based on GN penalty and two based on TV penalty). Practically, we confirm the theoretical findings by measuring the accuracy of selected regions compared with ground truth on simulated data. We also evaluate the stability of recovered regions over cross-validation folds using real MRI data. Our findings show that the TV penalty is superior to the GN model. In addition, we showed that adding an l 2 penalty improves the accuracy of estimated coefficients and selected significant regions for the both types of models.

Description: Similarity measure is a main core of image registration algorithms. Spatially varying intensity distortion is an important challenge, which affects the performance of similarity measures. Correlation among the pixels is the main characteristic of this distortion. Similarity measures such as sum-of-squared-differences (SSD) and mutual information ignore this correlation; hence, perfect registration cannot be achieved in the presence of this distortion. In this paper, we model this correlation with the aid of the low rank matrix theory. Based on this model, we compensate this distortion analytically and introduce rank-regularized SSD (RRSSD). This new similarity measure is a modified SSD based on singular values of difference image in mono-modal imaging. In fact, image registration and distortion correction are performed simultaneously in the proposed model. Based on our experiments, the RRSSD similarity measure achieves clinically acceptable registration results, and outperforms other state-of-the-art similarity measures, such as the well-known method of residual complexity.

Description: We present a novel method to segment instances of glandular structures from colon histopathology images. We use a structure learning approach which represents local spatial configurations of class labels, capturing structural information normally ignored by sliding-window methods. This allows us to reveal different spatial structures of pixel labels (e.g., locations between adjacent glands, or far from glands), and to identify correctly neighboring glandular structures as separate instances. Exemplars of label structures are obtained via clustering and used to train support vector machine classifiers. The label structures predicted are then combined and post-processed to obtain segmentation maps. We combine hand-crafted, multi-scale image features with features computed by a deep convolutional network trained to map images to segmentation maps. We evaluate the proposed method on the public domain GlaS data set, which allows extensive comparisons with recent, alternative methods. Using the GlaS contest protocol, our method achieves the overall best performance.

Description: Accurate identification of the needle target is crucial for effective epidural anesthesia. Currently, epidural needle placement is administered by a manual technique, relying on the sense of feel, which has a significant failure rate. Moreover, misleading the needle may lead to inadequate anesthesia, post dural puncture headaches, and other potential complications. Ultrasound offers guidance to the physician for identification of the needle target, but accurate interpretation and localization remain challenges. A hybrid machine learning system is proposed to automatically localize the needle target for epidural needle placement in ultrasound images of the spine. In particular, a deep network architecture along with a feature augmentation technique is proposed for automatic identification of the anatomical landmarks of the epidural space in ultrasound images. Experimental results of the target localization on planes of 3-D as well as 2-D images have been compared against an expert sonographer. When compared with the expert annotations, the average lateral and vertical errors on the planes of 3-D test data were 1 and 0.4 mm, respectively. On 2-D test data set, an average lateral error of 1.7 mm and vertical error of 0.8 mm were acquired.

Description: The use of appearance and shape priors in image segmentation is known to improve accuracy; however, existing techniques have several drawbacks. For instance, most active shape and appearance models require landmark points and assume unimodal shape and appearance distributions, and the level set representation does not support construction of local priors. In this paper, we present novel appearance and shape models for image segmentation based on a differentiable implicit parametric shape representation called a disjunctive normal shape model (DNSM). The DNSM is formed by the disjunction of polytopes, which themselves are formed by the conjunctions of half-spaces. The DNSM’s parametric nature allows the use of powerful local prior statistics, and its implicit nature removes the need to use landmarks and easily handles topological changes. In a Bayesian inference framework, we model arbitrary shape and appearance distributions using nonparametric density estimations, at any local scale. The proposed local shape prior results in accurate segmentation even when very few training shapes are available, because the method generates a rich set of shape variations by locally combining training samples. We demonstrate the performance of the framework by applying it to both 2-D and 3-D data sets with emphasis on biomedical image segmentation applications.

Description: This paper describes an automated method for registering 3-D models of metallic knee implants to single-plane radiographic images. We develop a multistage approach that identifies the correct pose by matching altered dilations of an edge-detected image with the silhouette of an implant model. The location of the similarity function’s minimum is found using a novel optimization routine that combines the Dividing Rectangles algorithm with properties of the registration metric. Depending on the implant type (tibial or femoral), this technique reliably converges under maximum displacements of approximately 25 to 55 millimeters for translation components and 25° to 55° for Euler angles. The method proves to be robust to noise from bones and soft tissue. After an initial guess for the first image in the sequence, subsequent frames can be automatically registered from the optimum pose in the previous image.

Description: Recently, matrix gradient coils (also termed multi-coils or multi-coil arrays) were introduced for imaging and B 0 shimming with 24, 48, and even 84 coil elements. However, in imaging applications, providing one amplifier per coil element is not always feasible due to high cost and technical complexity. In this simulation study, we show that an 84-channel matrix gradient coil (head insert for brain imaging) is able to create a wide variety of field shapes even if the number of amplifiers is reduced. An optimization algorithm was implemented that obtains groups of coil elements, such that a desired target field can be created by driving each group with an amplifier. This limits the number of amplifiers to the number of coil element groups. Simulated annealing is used due to the NP-hard combinatorial nature of the given problem. A spherical harmonic basis set up to the full third order within a sphere of 20-cm diameter in the center of the coil was investigated as target fields. We show that the median normalized least squares error for all target fields is below approximately 5% for 12 or more amplifiers. At the same time, the dissipated power stays within reasonable limits. With a relatively small set of amplifiers, switches can be used to sequentially generate spherical harmonics up to third order. The costs associated with a matrix gradient coil can be lowered, which increases the practical utility of matrix gradient coils.

Description: Ultrasound molecular imaging (USMI) is accomplished by detecting microbubble (MB) contrast agents that have bound to specific biomarkers, and can be used for a variety of imaging applications, such as the early detection of cancer. USMI has been widely utilized in preclinical imaging in mice; however, USMI in humans can be challenging because of the low concentration of bound MBs and the signal degradation caused by the presence of heterogenous soft tissue between the transducer and the lesion. Short-lag spatial coherence (SLSC) beamforming has been proposed as a robust technique that is less affected by poor signal quality than standard delay-and-sum (DAS) beamforming. In this paper, USMI performance was assessed using contrast-enhanced ultrasound imaging combined with DAS (conventional CEUS) and with SLSC (SLSC-CEUS). Each method was characterized by flow channel phantom experiments. In a USMI-mimicking phantom, SLSC-CEUS was found to be more robust to high levels of additive thermal noise than DAS, with a 6dB SNR improvement when the thermal noise level was +6dB or higher. However, SLSC-CEUS was also found to be insensitive to increases in MB concentration, making it a poor choice for perfusion imaging. USMI performance was also measured in vivo using VEGFR2-targeted MBs in mice with subcutaneous human hepatocellular carcinoma tumors, with clinical imaging conditions mimicked using a porcine tissue layer between the tumor and the transducer. SLSC-CEUS improved the SNR in each of ten tumors by an average of 41%, corresponding to 3.0dB SNR. These results indicate that the SLSC beamformer is well-suited for USMI applications because of its high sensitivity and robust properties under challenging imaging conditions.

Description: The motion of the common carotid artery (CCA) wall has been established to be useful in early diagnosis of atherosclerotic disease. However, tracking the CCA wall motion from ultrasound images remains a challenging task. In this paper, a nonlinear state-space approach has been developed to track CCA wall motion from ultrasound sequences. In this approach, a nonlinear state-space equation with a time-variant control signal was constructed from a mathematical model of the dynamics of the CCA wall. Then, the unscented Kalman filter (UKF) was adopted to solve the nonlinear state transfer function in order to evolve the state of the target tissue, which involves estimation of the motion trajectory of the CCA wall from noisy ultrasound images. The performance of this approach has been validated on 30 simulated ultrasound sequences and a real ultrasound dataset of 103 subjects by comparing the motion tracking results obtained in this study to those of three state-of-the-art methods and of the manual tracing method performed by two experienced ultrasound physicians. The experimental results demonstrated that the proposed approach is highly correlated with (intra-class correlation coefficient ≥ 0.9948 for the longitudinal motion and ≥ 0.9966 for the radial motion) and well agrees (the 95% confidence interval width is 0.8871 mm for the longitudinal motion and 0.4159 mm for the radial motion) with the manual tracing method on real data and also exhibits high accuracy on simulated data (0.1161 ~ 0.1260 mm). These results appear to demonstrate the effectiveness of the proposed approach for motion tracking of the CCA wall.

Description: Plane-wave-based ultrafast imaging has become the prevalent technique for non-conventional ultrasound imaging. The image quality, especially in terms of the suppression of artifacts, is generally compromised by reducing the number of transmissions for a higher frame rate. We hereby propose a new ultrafast imaging framework that reduces not only the side lobe artifacts but also the axial lobe artifacts using combined transmissions with a new coherence-based factor. The results from simulations, in vitro wire phantoms, the ex vivo porcine artery, and the in vivo porcine heart show that our proposed methodology greatly reduced the axial lobe artifact by 25±5 dB compared with coherent plane-wave compounding (CPWC), which was considered as the ultrafast imaging standard, and suppressed side lobe artifacts by 15 ± 5 dB compared with CPWC and coherent spherical-wave compounding. The reduction of artifacts in our proposed ultrafast imaging framework led to a better boundary delineation of soft tissues than CPWC.

Description: Iterative algorithms have become increasingly popular in computed tomography (CT) image reconstruction, since they better deal with the adverse image artifacts arising from low radiation dose image acquisition. But iterative methods remain computationally expensive. The main cost emerges in the projection and back projection operations, where accurate CT system modeling can greatly improve the quality of the reconstructed image. We present a framework that improves upon one particular aspect—the accurate projection of the image basis functions. It differs from current methods in that it substitutes the high computational complexity associated with accurate voxel projection by a small number of memory operations. Coefficients are computed in advance and stored in look-up tables parameterized by the CT system’s projection geometry. The look-up tables only require a few kilobytes of storage and can be efficiently accelerated on the GPU. We demonstrate our framework with both numerical and clinical experiments and compare its performance with the current state-of-the-art scheme—the separable footprint method.

Description: Contrast-enhanced ultrasound (CEUS) is a non-invasive imaging technique extensively used for blood perfusion imaging of various organs. This modality is based on the acoustic detection of gas-filled microbubble contrast agents used as intravascular flow tracers. Recent efforts aim at quantifying parameters related to the enhancement in the vascular compartment using time-intensity curve (TIC), and at using these latter as indicators for several pathological conditions. However, this quantification is mainly hampered by two reasons: first, the quantification intrinsically solely relies on temporal intensity variation, the explicit spatial transport of the contrast agent being left out. Second, the exact relationship between the acquired US-signal and the local microbubble concentration is hardly accessible. This paper introduces the use of a fluid dynamic model for the analysis of dynamic CEUS (DCEUS), in order to circumvent the two above-mentioned limitations. A new kinetic analysis is proposed in order to quantify the velocity amplitude of the bolus arrival. The efficiency of proposed methodology is evaluated both in-vitro , for the quantitative estimation of microbubble flow rates, and in-vivo , for the classification of placental insufficiency (control versus ligature) of pregnant rats from DCEUS. Besides, for the in-vivo experimental setup, we demonstrated that the proposed approach outperforms the performance of existing TIC-based methods.

Description: Incorporation of prior knowledge about organ shape and location is key to improve performance of image analysis approaches. In particular, priors can be useful in cases where images are corrupted and contain artefacts due to limitations in image acquisition. The highly constrained nature of anatomical objects can be well captured with learning-based techniques. However, in most recent and promising techniques such as CNN-based segmentation it is not obvious how to incorporate such prior knowledge. State-of-the-art methods operate as pixel-wise classifiers where the training objectives do not incorporate the structure and inter-dependencies of the output. To overcome this limitation, we propose a generic training strategy that incorporates anatomical prior knowledge into CNNs through a new regularisation model, which is trained end-to-end. The new framework encourages models to follow the global anatomical properties of the underlying anatomy ( e.g. shape, label structure) via learnt non-linear representations of the shape. We show that the proposed approach can be easily adapted to different analysis tasks ( e.g. image enhancement, segmentation) and improve the prediction accuracy of the state-of-the-art models. The applicability of our approach is shown on multi-modal cardiac data sets and public benchmarks. In addition, we demonstrate how the learnt deep models of 3-D shapes can be interpreted and used as biomarkers for classification of cardiac pathologies.

Description: Multi-source interior computed tomography (CT) has a great potential to provide ultra-fast and organ-oriented imaging at low radiation dose. However, X-ray cross scattering from multiple simultaneously activated X-ray imaging chains compromises imaging quality. Previously, we published two hardware-based scatter correction methods for multi-source interior CT. Here, we propose a software-based scatter correction method, with the benefit of no need for hardware modifications. The new method is based on a physics model and an iterative framework. The physics model was derived analytically, and was used to calculate X-ray scattering signals in both forward direction and cross directions in multi-source interior CT. The physics model was integrated to an iterative scatter correction framework to reduce scatter artifacts. The method was applied to phantom data from both Monte Carlo simulations and physical experimentation that were designed to emulate the image acquisition in a multi-source interior CT architecture recently proposed by our team. The proposed scatter correction method reduced scatter artifacts significantly, even with only one iteration. Within a few iterations, the reconstructed images fast converged toward the “scatter-free” reference images. After applying the scatter correction method, the maximum CT number error at the region-of-interests (ROIs) was reduced to 46 HU in numerical phantom dataset and 48 HU in physical phantom dataset respectively, and the contrast-noise-ratio at those ROIs increased by up to 44.3% and up to 19.7%, respectively. The proposed physics model-based iterative scatter correction method could be useful for scatter correction in dual-source or multi-source CT.

Description: Principal component analysis (PCA) is an exploratory tool widely used in data analysis to uncover the dominant patterns of variability within a population. Despite its ability to represent a data set in a low-dimensional space, PCA’s interpretability remains limited. Indeed, the components produced by PCA are often noisy or exhibit no visually meaningful patterns. Furthermore, the fact that the components are usually non-sparse may also impede interpretation, unless arbitrary thresholding is applied. However, in neuroimaging, it is essential to uncover clinically interpretable phenotypic markers that would account for the main variability in the brain images of a population. Recently, some alternatives to the standard PCA approach, such as sparse PCA (SPCA), have been proposed, their aim being to limit the density of the components. Nonetheless, sparsity alone does not entirely solve the interpretability problem in neuroimaging, since it may yield scattered and unstable components. We hypothesized that the incorporation of prior information regarding the structure of the data may lead to improved relevance and interpretability of brain patterns. We therefore present a simple extension of the popular PCA framework that adds structured sparsity penalties on the loading vectors in order to identify the few stable regions in the brain images that capture most of the variability. Such structured sparsity can be obtained by combining, e.g., $ell _{1}$ and total variation (TV) penalties, where the TV regularization encodes information on the underlying structure of the data. This paper presents the structured SPCA (denoted SPCA-TV) optimization framework and its resolution. We demonstrate SPCA-TV’s effectiveness and versatility on three different data sets. It can be applied to any kind of structured data, such as, e.g., ${N}$ -dimensional array images or meshes of cortical surfaces. The gains of SPCA-TV over unstructured approaches (such as SPCA and ElasticNet PCA) or structured approach (such as GraphNet PCA) are significant, since SPCA-TV reveals the variability within a data set in the form of intelligible brain patterns that are easier to interpret and more stable across different samples.

Description: For magnetic resonance imaging of tissues with very short transverse relaxation times, radio-frequency excitation must be immediately followed by data acquisition with fast spatial encoding. In zero-echo-time (ZTE) imaging, excitation is performed while the readout gradient is already on, causing data loss due to an initial dead time. One major dead time contribution is the settling time of the filters involved in signal down-conversion. In this paper, a multi-rate acquisition scheme is proposed to minimize dead time due to filtering. Short filters and high output bandwidth are used initially to minimize settling time. With increasing time since the signal onset, longer filters with better frequency selectivity enable stronger signal decimation. In this way, significant dead time reduction is accomplished at only a slight increase in the overall amount of output data. Multi-rate acquisition was implemented with a two-stage filter cascade in a digital receiver based on a field-programmable gate array. In ZTE imaging in a phantom and in vivo , dead time reduction by multi-rate acquisition is shown to improve image quality and expand the feasible bandwidth while increasing the amount of data collected by only a few percent.

Description: This paper presents an image reconstruction method based on parametric level set (PLS) method using electrical impedance tomography. The conductivity to be reconstructed was assumed to be piecewise constant and the geometry of the anomaly was represented by a shape-based PLS function, which we represent using Gaussian radial basis functions (GRBF). The representation of the PLS function significantly reduces the number of unknowns, and circumvents many difficulties that are associated with traditional level set (TLS) methods, such as regularization, re-initialization and use of signed distance function. PLS reconstruction results shown in this article are some of the first ones using experimental EIT data. The performance of the PLS method was tested with water tank data for two-phase visualization and with simulations which demonstrate the most popular biomedical application of EIT: lung imaging. In addition, robustness studies of the PLS method w.r.t width of the Gaussian function and GRBF centers were performed on simulated lung imaging data. The experimental and simulation results show that PLS method has significant improvement in image quality compared with the TLS reconstruction.

Description: Automated detection of vascular structures is of great importance in understanding the mechanism, diagnosis, and treatment of many vascular pathologies. However, automatic vascular detection continues to be an open issue because of difficulties posed by multiple factors, such as poor contrast, inhomogeneous backgrounds, anatomical variations, and the presence of noise during image acquisition. In this paper, we propose a novel 2-D/3-D symmetry filter to tackle these challenging issues for enhancing vessels from different imaging modalities. The proposed filter not only considers local phase features by using a quadrature filter to distinguish between lines and edges, but also uses the weighted geometric mean of the blurred and shifted responses of the quadrature filter, which allows more tolerance of vessels with irregular appearance. As a result, this filter shows a strong response to the vascular features under typical imaging conditions. Results based on eight publicly available datasets (six 2-D data sets, one 3-D data set, and one 3-D synthetic data set) demonstrate its superior performance to other state-of-the-art methods.

Description: Magnetic resonance imaging of short relaxation time spin systems has been a widely discussed topic with serious clinical applications and led to the emergence of fast imaging ultra-short echo-time sequences. Nevertheless, these sequences suffer from image blurring, due to the related sampling point spread function and are highly prone to imaging artefacts arising from, e.g., chemical shifts or magnetic susceptibilities. In this paper, we present a concept of spherical quasi-random single-point imaging. The approach is highly accelerateable, due to intrinsic undersampling properties and capable of strong metal artefact suppression. Imaging acceleration is achieved by sampling of quasi-random points in $k$ -space, based on a low-discrepancy sequence, and a combination with non-linear optimization reconstruction techniques [compressed sensing (CS)]. The presented low-discrepancy trajectory shows ideal noise like undersampling properties for the combination with CS, leading to denoised images with excellent metal artefact reduction. Using eightfold undersampling, acquisition time of a few minutes can be achieved for volume acquisitions.

Description: Image guidance has become the standard of care for patient positioning in radiotherapy, where image registration is often a critical step to help manage patient motion. However, in practice, verification of registration quality is often adversely affected by difficulty in manual inspection of 3-D images and time constraint, thus affecting the therapeutic outcome. Therefore, we proposed to employ both bootstrapping and the supervised learning methods of linear discriminant analysis and random forest to help robustly assess registration quality in ultrasound-guided radiotherapy. We validated both approaches using phantom and real clinical ultrasound images, and showed that both performed well for the task. While learning-based techniques offer better accuracy and shorter evaluation time, bootstrapping requires no prior training and has a higher sensitivity.

Description: Characterization of the noise distribution in magnetic resonance images has multiple applications, including quality assurance and protocol optimization. Noise characterization is particularly important in the presence of parallel imaging acceleration with multi-coil acquisitions, where the noise distribution can contain severe spatial heterogeneities. If the parallel imaging reconstruction is a linear process, an accurate noise analysis can be carried out by taking into account the correlations between all the samples involved. However, for ${k}$ -space-based techniques such as generalized autocalibrating partially parallel acquisition (GRAPPA), the exact analysis has been considered computationally prohibitive due to the very large size of the noise covariance matrices required to characterize the noise propagation from ${k}$ -space to image space. Previously proposed methods avoid this computational burden by formulating the GRAPPA reconstruction as a pixel-wise linear operation performed in the image space. However, these methods are not exact in the presence of non-uniform sampling of ${k}$ -space (e.g., containing a calibration region). For this reason, in this paper, we develop an accurate characterization of the noise distribution for self-calibrated parallel imaging in the presence of arbitrary Cartesian sampling patterns. By exploiting the symmetries and separability in the noise propagation process, the proposed method is computationally efficient and does not require large matrices. Under the assumption of a fixed reconstruction kernel, this method provides the precise distribution of the noise variance for each coil’s image. These coil-by-coil noise maps are subsequently combined according to the coil combination approach- used in image reconstruction, and therefore can be applied with both complex coil combination and root-sum-of-squares approaches. In this paper, we present the proposed noise characterization method and compare it to previous techniques using Monte Carlo simulations as well as phantom acquisitions.

Description: To introduce magnetic resonance mediated radiofrequency ablation (MR-RFA), in which the MRI scanner uniquely serves both diagnostic and therapeutic roles. In MR-RFA scanner-induced RF heating is channeled to the ablation site via a Larmor frequency RF pickup device and needle system, and controlled via the pulse sequence. MR-RFA was evaluated with simulation of electric and magnetic fields to predict the increase in local specific-absorption-rate (SAR). Temperature-time profiles were measured for different configurations of the device in agar phantoms and ex vivo bovine liver in a 1.5 T scanner. Temperature rise in MR-RFA was imaged using the proton resonance frequency method validated with fiber-optic thermometry. MR-RFA was performed on the livers of two healthy live pigs. Simulations indicated a near tenfold increase in SAR at the RFA needle tip. Temperature-time profiles depended significantly on the physical parameters of the device although both configurations tested yielded temperature increases sufficient for ablation. Resected livers from live ablations exhibited clear thermal lesions. MR-RFA holds potential for integrating RF ablation tumor therapy with MRI scanning. MR-RFA may add value to MRI with the addition of a potentially disposable ablation device, while retaining MRI’s ability to provide real time procedure guidance and measurement of tissue temperature, perfusion, and coagulation.

Description: Respiratory motion during positron emission tomography (PET)/computed tomography (CT) imaging can cause significant image blurring and underestimation of tracer concentration for both static and dynamic studies. In this paper, with the aim to eliminate both intra-cycle and inter-cycle motions, and apply to dynamic imaging, we developed a non-rigid event-by-event (NR-EBE) respiratory motion-compensated list-mode reconstruction algorithm. The proposed method consists of two components: the first component estimates a continuous non-rigid motion field of the internal organs using the internal–external motion correlation. This continuous motion field is then incorporated into the second component, non-rigid MOLAR (NR-MOLAR) reconstruction algorithm to deform the system matrix to the reference location where the attenuation CT is acquired. The point spread function (PSF) and time-of-flight (TOF) kernels in NR-MOLAR are incorporated in the system matrix calculation, and therefore are also deformed according to motion. We first validated NR-MOLAR using a XCAT phantom with a simulated respiratory motion. NR-EBE motion-compensated image reconstruction using both the components was then validated on three human studies injected with 18 F-FPDTBZ and one with 18 F-fluorodeoxyglucose (FDG) tracers. The human results were compared with conventional non-rigid motion correction using discrete motion field (NR-discrete, one motion field per gate) and a previously proposed rigid EBE motion-compensated image reconstruction (R-EBE) that was designed to correct for rigid motion on a target lesion/organ. The XCAT results demonstrated that NR-MOLAR incorporating both PSF and TOF kernels effectively corrected for non-rigid motion. The 18 F-FPDTBZ studies showed that NR-EBE out-performed NR-Discrete, and yielded comparable results with R-EBE on target organs while yielding superior image quality in other regions. The FDG study showed that NR- EBE clearly improved the visibility of multiple moving lesions in the liver where some of them could not be discerned in other reconstructions, in addition to improving quantification. These results show that NR-EBE motion-compensated image reconstruction appears to be a promising tool for lesion detection and quantification when imaging thoracic and abdominal regions using PET.

Description: Developing custom-built MR coils is a cumbersome task, in which an a priori prediction of the coils’ SNR performance, their sensitivity pattern, and their depth of penetration helps to greatly speed up the design process by reducing the required hardware manufacturing iterations. The simulation-based design flow presented in this paper takes the entire MR imaging process into account. That is, it includes all geometric and material properties of the coil and the phantom, the thermal noise as well as the target MR sequences. The proposed simulation-driven design flow is validated using a manufactured prototype coil, whose performance was optimized regarding its SNR performance, based on the presented design flow, by comparing the coil’s measured performance against the simulated results. In these experiments, the mean and the standard deviation of the relative error between the simulated and measured coil sensitivity pattern were found to be $mu ={1.79}%$ and $sigma ={3.15}%$ . Moreover, the peak deviation between the simulated and measured voxel SNR was found to be less than 4%, indicating that simulations are in good accordance with the measured results, validating the proposed software-based design approach.

Description: Optimal control approaches have proved useful in designing RF pulses for large tip-angle applications. A typical challenge for optimal control design is the inclusion of constraints resulting from physiological or technical limitations that assure the realizability of the optimized pulses. In this paper, we show how to treat such inequality constraints, in particular, amplitude constraints on the B1 field, the slice-selective gradient, and its slew rate, as well as constraints on the slice profile accuracy. For the latter, a pointwise profile error and additional phase constraints are prescribed. Here, a penalization method is introduced that corresponds to a higher order tracking instead of the common quadratic tracking. The order is driven to infinity in the course of the optimization. We jointly optimize for the RF and slice-selective gradient waveform. The amplitude constraints on these control variables are treated efficiently by semismooth Newton or quasi-Newton methods. The method is flexible, adapting to many optimization goals. As an application, we reduce the power of refocusing pulses, which is important for spin echo-based applications with a short echo spacing. Here, the optimization method is tested in numerical experiments for reducing the pulse power of simultaneous multislice refocusing pulses. The results are validated by phantom and in-vivo experiments.

Description: Patients who have implanted medical devices with long conductive leads are often restricted from receiving MRI scans due to the danger of RF-induced heating near the lead tips. Phantom studies have shown that this heating varies significantly on a case-by-case basis, indicating that many patients with implanted devices can receive clinically useful MRI scans without harm. However, the difficulty of predicting RF-induced lead tip heating prior to scanning prevents numerous implant recipients from being scanned. Here, we demonstrate that thermo-acoustic ultrasound (TAUS) has the potential to be utilized for a pre-scan procedure assessing the risk of RF-induced lead tip heating in MRI. A system was developed to detect TAUS signals by four different TAUS acquisition methods. We then integrated this system with an MRI scanner and detected a peak in RF power absorption near the tip of a model lead when transmitting from the scanner’s body coil. We also developed and experimentally validated simulations to characterize the thermo-acoustic signal generated near lead tips. These results indicate that TAUS is a promising method for assessing RF implant safety, and with further development, a TAUS pre-scan could allow many more patients to have access to MRI scans of significant clinical value.

Description: Sensitivity to phase deviations in MRI forms the basis of a variety of techniques, including magnetic susceptibility weighted imaging and chemical shift imaging. Current phase processing techniques fall into two families: those which process the complex image data with magnitude and phase coupled, and phase unwrapping-based techniques that first linearize the phase topology across the image. However, issues, such as low signal and the existence of phase poles, can lead both methods to experience error. Cyclic continuous max-flow (CCMF) phase processing uses primal-dual-variational optimization over a cylindrical manifold, which represent the inherent topology of phase images, increasing its robustness to these issues. CCMF represents a third distinct paradigm in phase processing, being the only technique equipped with the inherent topology of phase. CCMF is robust and efficient with at least comparable accuracy as the prior paradigms.

Description: Inspired by recent advances in deep learning, we propose a framework for reconstructing dynamic sequences of 2-D cardiac magnetic resonance (MR) images from undersampled data using a deep cascade of convolutional neural networks (CNNs) to accelerate the data acquisition process. In particular, we address the case where data are acquired using aggressive Cartesian undersampling. First, we show that when each 2-D image frame is reconstructed independently, the proposed method outperforms state-of-the-art 2-D compressed sensing approaches, such as dictionary learning-based MR image reconstruction, in terms of reconstruction error and reconstruction speed. Second, when reconstructing the frames of the sequences jointly, we demonstrate that CNNs can learn spatio-temporal correlations efficiently by combining convolution and data sharing approaches. We show that the proposed method consistently outperforms state-of-the-art methods and is capable of preserving anatomical structure more faithfully up to 11-fold undersampling. Moreover, reconstruction is very fast: each complete dynamic sequence can be reconstructed in less than 10 s and, for the 2-D case, each image frame can be reconstructed in 23 ms, enabling real-time applications.

Description: Macular holes are blinding conditions, where a hole develops in the central part of retina, resulting in reduced central vision. The prognosis and treatment options are related to a number of variables, including the macular hole size and shape. High-resolution spectral domain optical coherence tomography allows precise imaging of the macular hole geometry in three dimensions, but the measurement of these by human observers is time-consuming and prone to high inter- and intra-observer variability, being characteristically measured in 2-D rather than 3-D. We introduce several novel techniques to automatically retrieve accurate 3-D measurements of the macular hole, including: surface area, base area, base diameter, top area, top diameter, height, and minimum diameter. Specifically, we introduce a multi-scale 3-D level set segmentation approach based on a state-of-the-art level set method, and we introduce novel curvature-based cutting and 3-D measurement procedures. The algorithm is fully automatic, and we validate our extracted measurements both qualitatively and quantitatively, where our results show the method to be robust across a variety of scenarios. Our automated processes are considered a significant contribution for clinical applications.

Description: Penalized least-squares iterative image reconstruction algorithms used for spatial resolution-limited imaging, such as functional magnetic resonance imaging (fMRI), commonly use a quadratic roughness penalty to regularize the reconstructed images. When used for complex-valued images, the conventional roughness penalty regularizes the real and imaginary parts equally. However, these imaging methods sometimes benefit from separate penalties for each part. The spatial smoothness from the roughness penalty on the reconstructed image is dictated by the regularization parameter(s). One method to set the parameter to a desired smoothness level is to evaluate the full width at half maximum of the reconstruction method’s local impulse response. Previous work has shown that when using the conventional quadratic roughness penalty, one can approximate the local impulse response using an FFT-based calculation. However, that acceleration method cannot be applied directly for separate real and imaginary regularization. This paper proposes a fast and stable calculation for this case that also uses FFT-based calculations to approximate the local impulse responses of the real and imaginary parts. This approach is demonstrated with a quadratic image reconstruction of fMRI data that uses separate roughness penalties for the real and imaginary parts.

Description: A new reconstruction method, coined MIRAGE, is presented for accurate, fast, and robust parameter mapping of multiple-echo gradient-echo (MEGE) imaging, the basis sequence of novel quantitative magnetic resonance imaging techniques such as water content and susceptibility mapping. Assuming that the temporal signal can be modeled as a sum of damped complex exponentials, MIRAGE performs model-based reconstruction of undersampled data by minimizing the rank of local Hankel matrices. It further incorporates multi-channel information and spatial prior knowledge. Finally, the parameter maps are estimated using nonlinear regression. Simulations and retrospective undersampling of phantom and in vivo data affirm robustness, e.g., to strong inhomogeneity of the static magnetic field and partial volume effects. MIRAGE is compared with a state-of-the-art compressed sensing method, ${{text {L}}_{1}}$ -ESPIRiT. Parameter maps estimated from reconstructed data using MIRAGE are shown to be accurate, with the mean absolute error reduced by up to 50% for in vivo results. The proposed method has the potential to improve the diagnostic utility of quantitative imaging techniques that rely on MEGE data.

Description: The classification of blood vessels into arterioles and venules is a fundamental step in the automatic investigation of retinal biomarkers for systemic diseases. In this paper, we present a novel technique for vessel classification on ultra-wide-field-of-view images of the retinal fundus acquired with a scanning laser ophthalmoscope. To the best of our knowledge, this is the first time that a fully automated artery/vein classification technique for this type of retinal imaging with no manual intervention has been presented. The proposed method exploits hand-crafted features based on local vessel intensity and vascular morphology to formulate a graph representation from which a globally optimal separation between the arterial and venular networks is computed by graph cut approach. The technique was tested on three different data sets (one publicly available and two local) and achieved an average classification accuracy of 0.883 in the largest data set.

Description: Tumor growth is associated with cell invasion and mass-effect, which are traditionally formulated by mathematical models, namely reaction-diffusion equations and biomechanics. Such models can be personalized based on clinical measurements to build the predictive models for tumor growth. In this paper, we investigate the possibility of using deep convolutional neural networks to directly represent and learn the cell invasion and mass-effect, and to predict the subsequent involvement regions of a tumor. The invasion network learns the cell invasion from information related to metabolic rate, cell density, and tumor boundary derived from multimodal imaging data. The expansion network models the mass-effect from the growing motion of tumor mass. We also study different architectures that fuse the invasion and expansion networks, in order to exploit the inherent correlations among them. Our network can easily be trained on population data and personalized to a target patient, unlike most previous mathematical modeling methods that fail to incorporate population data. Quantitative experiments on a pancreatic tumor data set show that the proposed method substantially outperforms a state-of-the-art mathematical model-based approach in both accuracy and efficiency, and that the information captured by each of the two subnetworks is complementary.

Description: In high-dimensional magnetic resonance imaging applications, time-consuming, sequential acquisition of data samples in the spatial frequency domain ( ${k}$ -space) can often be accelerated by accounting for dependencies in linear reconstruction, at the cost of noise amplification that depends on the sampling pattern. Common examples are support-constrained, parallel, and dynamic MRI, and ${k}$ -space sampling strategies are primarily driven by image-domain metrics that are expensive to compute for arbitrary sampling patterns. It remains challenging to provide systematic and computationally efficient automatic designs of arbitrary multidimensional Cartesian sampling patterns that mitigate noise amplification, given the subspace to which the object is confined. To address this problem, this paper introduces a theoretical framework that describes local geometric properties of the sampling pattern and relates them to the spread in the eigenvalues of the information matrix described by its first two spectral moments. This new criterion is then used for very efficient optimization of complex multidimensional sampling patterns that does not require reconstructing images or explicitly mapping noise amplification. Experiments with in vivo data show strong agreement between this criterion and traditional, comprehensive image-domain- and ${k}$ -space-based metrics, indicating the potential of the approach for computationally efficient (on-the-fly), automatic, and adaptive design of sampling patterns.

Description: There is intense interest in fMRI research on whole-brain functional connectivity, and however, two fundamental issues are still unresolved: the impact of spatiotemporal data resolution (spatial parcellation and temporal sampling) and the impact of the network construction method on the reliability of functional brain networks. In particular, the impact of spatiotemporal data resolution on the resulting connectivity findings has not been sufficiently investigated. In fact, a number of studies have already observed that functional networks often give different conclusions across different parcellation scales. If the interpretations from functional networks are inconsistent across spatiotemporal scales, then the whole validity of the functional network paradigm is called into question. This paper investigates the consistency of resting state network structure when using different temporal sampling or spatial parcellation, or different methods for constructing the networks. To pursue this, we develop a novel network comparison framework based on persistent homology from a topological data analysis. We use the new network comparison tools to characterize the spatial and temporal scales under which consistent functional networks can be constructed. The methods are illustrated on Human Connectome Project data, showing that the DISCOH 2 network construction method outperforms other approaches at most data spatiotemporal resolutions.

Description: Diffusion MRI data are generally acquired using hyperpolarized gases during patient breath-hold, which yields a compromise between achievable image resolution, lung coverage, and number of $b$ -values. In this paper, we propose a novel method that accelerates the acquisition of diffusion MRI data by undersampling in both the spatial and $b$ -value dimensions and incorporating knowledge about signal decay into the reconstruction (SIDER). SIDER is compared with total variation (TV) reconstruction by assessing its effect on both the recovery of ventilation images and the estimated mean alveolar dimensions (MADs). Both methods are assessed by retrospectively undersampling diffusion data sets ( $n $ =8) of healthy volunteers and patients with Chronic Obstructive Pulmonary Disease (COPD) for acceleration factors between x2 and x10. TV led to large errors and artifacts for acceleration factors equal to or larger than x5. SIDER improved TV, with a lower solution error and MAD histograms closer to those obtained from fully sampled data for acceleration factors up to x10. SIDER preserved image quality at all acceleration factors, although images were slightly smoothed and some details were lost at x10. In conclusion, we developed and validated a novel compressed sensing method for lung MRI imaging and achieved high acceleration factors, which can be used to increase the amount of data acquired during breath-hold. This methodology is expected to improve the accuracy of estimated lung microstructure dimensions and provide more options in the study of lung diseases with MRI.

Description: Heavy smokers undergoing screening with low-dose chest CT are affected by cardiovascular disease as much as by lung cancer. Low-dose chest CT scans acquired in screening enable quantification of atherosclerotic calcifications and thus enable identification of subjects at increased cardiovascular risk. This paper presents a method for automatic detection of coronary artery, thoracic aorta, and cardiac valve calcifications in low-dose chest CT using two consecutive convolutional neural networks. The first network identifies and labels potential calcifications according to their anatomical location and the second network identifies true calcifications among the detected candidates. This method was trained and evaluated on a set of 1744 CT scans from the National Lung Screening Trial. To determine whether any reconstruction or only images reconstructed with soft tissue filters can be used for calcification detection, we evaluated the method on soft and medium/sharp filter reconstructions separately. On soft filter reconstructions, the method achieved F 1 scores of 0.89, 0.89, 0.67, and 0.55 for coronary artery, thoracic aorta, aortic valve, and mitral valve calcifications, respectively. On sharp filter reconstructions, the F 1 scores were 0.84, 0.81, 0.64, and 0.66, respectively. Linearly weighted kappa coefficients for risk category assignment based on per subject coronary artery calcium were 0.91 and 0.90 for soft and sharp filter reconstructions, respectively. These results demonstrate that the presented method enables reliable automatic cardiovascular risk assessment in all low-dose chest CT scans acquired for lung cancer screening.

Description: Imaging corneal biomechanical changes or abnormalities is important for better clinical diagnosis and treatment of corneal diseases. We propose a novel ultrasound-based method, called ocular pulse elastography (OPE), to image corneal deformation during the naturally occurring ocular pulse. Experiments on animal and human donor eyes, as well as synthetic radiofrequency (RF) data, were used to evaluate the efficacy of the OPE method. Using very high-frequency ultrasound (center frequency = 55 MHz), correlation-based speckle tracking yielded an accuracy of less than 10% error for axial tissue displacements of $0.5~mu text{m}$ or above. Satisfactory speckle tracking was achieved for out-of-plane displacements up to $32~mu text{m}$ . Using synthetic RF data with or without a pre-defined uniform strain, the OPE method detected strains down to 0.0001 axially and 0.00025 laterally with an error less than 10%. Experiments in human donor eyes showed excellent repeatability with an intraclass correlation of 0.98. The measurement outcome from OPE was also shown to be highly correlated with that of standard inflation. These results suggest the feasibility of OPE as a potential clinical tool for evaluating corneal biomechanics in vivo .

Description: This editorial introduces the Special Issue on Simulation and Synthesis in Medical Imaging. In this editorial, we define so-far ambiguous terms of simulation and synthesis in medical imaging. We also briefly discuss the synergistic importance of mechanistic (hypothesis-driven) and phenomenological (data-driven) models of medical image generation. Finally, we introduce the twelve papers published in this issue covering both mechanistic (5) and phenomenological (7) medical image generation. This rich selection of papers covers applications in cardiology, retinopathy, histopathology, neurosciences, and oncology. It also covers all mainstream diagnostic medical imaging modalities. We conclude the editorial with a personal view on the field and highlight some existing challenges and future research opportunities.

Description: In this paper, we aim to produce a realistic 2-D projection of the breast parenchymal distribution from a 3-D breast magnetic resonance image (MRI). To evaluate the accuracy of our simulation, we compare our results with the local breast density (i.e., density map) obtained from the complementary full-field digital mammogram. To achieve this goal, we have developed a fully automatic framework, which registers MRI volumes to X-ray mammograms using a subject-specific biomechanical model of the breast. The optimization step modifies the position, orientation, and elastic parameters of the breast model to perform the alignment between the images. When the model reaches an optimal solution, the MRI glandular tissue is projected and compared with the one obtained from the corresponding mammograms. To reduce the loss of information during the ray-casting, we introduce a new approach that avoids resampling the MRI volume. In the results, we focus our efforts on evaluating the agreement of the distributions of glandular tissue, the degree of structural similarity, and the correlation between the real and synthetic density maps. Our approach obtained a high-structural agreement regardless the glandularity of the breast, whilst the similarity of the glandular tissue distributions and correlation between both images increase in denser breasts. Furthermore, the synthetic images show continuity with respect to large structures in the density maps.

Description: Electrocardiographic Imaging has become an increasingly used technique for non-invasive diagnosis of cardiac arrhythmias, although the need for medical imaging technology to determine the anatomy hinders its introduction in the clinical practice. This paper explores the ability of a new metric based on the inverse reconstruction quality for the location and orientation of the atrial surface inside the torso. Body surface electrical signals from 31 realistic mathematical models and four AF patients were used to estimate the optimal position of the atria inside the torso. The curvature of the L-curve from the Tikhonov method, which was found to be related to the inverse reconstruction quality, was measured after application of deviations in atrial position and orientation. Independent deviations in the atrial position were solved by finding the maximal L-curve curvature with an error of 1.7 ± 2.4 mm in mathematical models and 9.1 ± 11.5 mm in patients. For the case of independent angular deviations, the error in location by using the L-curve was 5.8±7.1° in mathematical models and 12.4° ± 13.2° in patients. The ability of the L-curve curvature was tested also under superimposed uncertainties in the three axis of translation and in the three axis of rotation, and the error in location was of 2.3 ± 3.2 mm and 6.4° ± 7.1° in mathematical models, and 7.9±10.7 mm and 12.1°±15.5° in patients. The curvature of L-curve is a useful marker for the atrial position and would allow emending the inaccuracies in its location.

Description: These instructions give guidelines for preparing papers for this publication. Presents information for authors publishing in this journal.

Description: Describes the above-named upcoming conference event. May include topics to be covered or calls for papers.

Description: Presents the table of contents for this issue of the publication.

Description: The four-dimensional (4-D) eXtended CArdiac-Torso (XCAT) series of phantoms was developed to provide accurate computerized models of the human anatomy and physiology. The XCAT series encompasses a vast population of phantoms of varying ages from newborn to adult, each including parameterized models for the cardiac and respiratory motions. With great flexibility in the XCAT’s design, any number of body sizes, different anatomies, cardiac or respiratory motions or patterns, patient positions and orientations, and spatial resolutions can be simulated. As such, the XCAT phantoms are gaining a wide use in biomedical imaging research. There they can provide a virtual patient base from which to quantitatively evaluate and improve imaging instrumentation, data acquisition, techniques, and image reconstruction and processing methods which can lead to improved image quality and more accurate clinical diagnoses. The phantoms have also found great use in radiation dosimetry, radiation therapy, medical device design, and even the security and defense industry. This review paper highlights some specific areas in which the XCAT phantoms have found use within biomedical imaging and other fields. From these examples, we illustrate the increasingly important role that computerized phantoms and computer simulation are playing in the research community.

Description: The investigation of the performance of different positron emission tomography (PET) reconstruction and motion compensation methods requires accurate and realistic representation of the anatomy and motion trajectories as observed in real subjects during acquisitions. The generation of well-controlled clinical datasets is difficult due to the many different clinical protocols, scanner specifications, patient sizes, and physiological variations. Alternatively, computational phantoms can be used to generate large data sets for different disease states, providing a ground truth. Several studies use registration of dynamic images to derive voxel deformations to create moving computational phantoms. These phantoms together with simulation software generate raw data. This paper proposes a method for the synthesis of dynamic PET data using a fast analytic method. This is achieved by incorporating realistic models of respiratory motion into a numerical phantom to generate datasets with continuous and variable motion with magnetic resonance imaging (MRI)-derived motion modeling and high resolution MRI images. In this paper, data sets for two different clinical traces are presented, 18 F-FDG and 68 Ga-PSMA. This approach incorporates realistic models of respiratory motion to generate temporally and spatially correlated MRI and PET data sets, as those expected to be obtained from simultaneous PET–MRI acquisitions.

Description: The purpose of this paper was to extend the extended cardiac-torso (XCAT) series of computational phantoms to include a detailed lung architecture including airways and pulmonary vasculature. Eleven XCAT phantoms of varying anatomy were used in this paper. The lung lobes and initial branches of the airways, pulmonary arteries, and veins were previously defined in each XCAT model. These models were extended from the initial branches of the airways and vessels to the level of terminal branches using an anatomically-based volume-filling branching algorithm. This algorithm grew the airway and vasculature branches separately and iteratively without intersecting each other using cylindrical models with diameters estimated by order-based anatomical measurements. Geometrical features of the extended branches were compared with the literature anatomy values to quantitatively evaluate the models. These features include branching angle, length to diameter ratio, daughter to parent diameter ratio, asymmetrical branching pattern, diameter, and length ratios. The XCAT phantoms were then used to simulate CT images to qualitatively compare them with the original phantom images. The proposed growth model produced 46369 ± 12521 airways, 44737 ± 11773 arteries, and 39819 ± 9988 veins to the XCAT phantoms. Furthermore, the growth model was shown to produce asymmetrical airway, artery, and vein networks with geometrical attributes close to morphometry and model based studies. The simulated CT images of the phantoms were judged to be more realistic, including more airways and pulmonary vessels compared with the original phantoms. Future work will seek to add a heterogeneous parenchymal background into the XCAT lungs to make the phantoms even more representative of human anatomy, paving the way towards the use of XCAT models as a tool to virtually evaluate the current and emerging medical imaging technologies.

Description: We propose a multi-input multi-output fully convolutional neural network model for MRI synthesis. The model is robust to missing data, as it benefits from, but does not require, additional input modalities. The model is trained end-to-end, and learns to embed all input modalities into a shared modality-invariant latent space. These latent representations are then combined into a single fused representation, which is transformed into the target output modality with a learnt decoder. We avoid the need for curriculum learning by exploiting the fact that the various input modalities are highly correlated. We also show that by incorporating information from segmentation masks the model can both decrease its error and generate data with synthetic lesions. We evaluate our model on the ISLES and BRATS data sets and demonstrate statistically significant improvements over state-of-the-art methods for single input tasks. This improvement increases further when multiple input modalities are used, demonstrating the benefits of learning a common latent space, again resulting in a statistically significant improvement over the current best method. Finally, we demonstrate our approach on non skull-stripped brain images, producing a statistically significant improvement over the previous best method. Code is made publicly available at https://github.com/agis85/multimodal_brain_synthesis .

Description: Numerical simulation of ultrasound images can facilitate the training of sonographers. An efficient and realistic model for the simulation of ultrasonic speckle is the convolution of the ultrasound point-spread function with a distribution of point scatterers. Nevertheless, for a given arbitrary tissue type, a scatterer map that would generate a realistic appearance of that tissue is not known a priori. In this paper, we introduce a principled approach to estimate (reconstruct) such a scatterer map from images, by solving the inverse-problem of ultrasound speckle formation, such that images from arbitrary view angles and transducer settings can be generated from those scatterer maps later in simulations. Robust reconstructions are achieved by using multiple measurements of the same tissue with different viewing parameters. For this purpose, a novel use of beam-steering to rapidly and conveniently acquire multiple images of the same scene is proposed. We demonstrate in numerical and physical phantoms and $textit {in vivo}$ images that the appearance of synthesized images closely match real images for a range of viewing parameters and probe settings. We also present a scene editing scenario exploiting these scatterer representations to create realistic images of augmented anatomy.

Description: Presents a listing of the editorial board, board of governors, current staff, committee members, and/or society editors for this issue of the publication.

Description: Predicting tumor growth and its response to therapy remains a major challenge in cancer research and strongly relies on tumor growth models. In this paper, we introduce, calibrate, and verify a novel image-driven reaction-diffusion model of avascular tumor growth. The model allows for proliferation, death and spread of tumor cells, and accounts for nutrient distribution and hypoxia. It is constrained by longitudinal time series of dynamic contrast-enhancement-MRI images. Tumor specific parameters are estimated from two early time points and used to predict the spatio-temporal evolution of the tumor volume and cell densities at later time points. We first test our parameter estimation approach on synthetic data from 15 generated tumors. Our in silico study resulted in small volume errors (<5%) and high Dice overlaps (>97%), showing that model parameters can be successfully recovered and used to accurately predict the tumor growth. Encouraged by these results, we apply our model to seven pre-clinical cases of breast carcinoma. We are able to show promising preliminary results, especially for the estimation for early time points. Processes like angiogenesis and apoptosis should be included to further improve predictions for later time points.

Description: Geometric distortion induced by the main B0 field disrupts the consistency of fetal echo planar imaging (EPI) data, on which diffusion and functional magnetic resonance imaging is based. In this paper, we present a novel data-driven method for simultaneous motion and distortion correction of fetal EPI. A motion-corrected and reconstructed T2 weighted single shot fast spin echo (ssFSE) volume is used as a model of undistorted fetal brain anatomy. Our algorithm interleaves two registration steps: estimation of fetal motion parameters by aligning EPI slices to the model; and deformable registration of EPI slices to slices simulated from the undistorted model to estimate the distortion field. The deformable registration is regularized by a physically inspired Laplacian constraint, to model distortion induced by a source-free background B0 field. Our experiments show that distortion correction significantly improves consistency of reconstructed EPI volumes with ssFSE volumes. In addition, the estimated distortion fields are consistent with fields calculated from acquired field maps, and the Laplacian constraint is essential for estimation of plausible distortion fields. The EPI volumes reconstructed from different scans of the same subject were more consistent when the proposed method was used in comparison with EPI volumes reconstructed from data distortion corrected using a separately acquired B0 field map.

Description: In this paper, we propose a generalized joint sparsity regularization prior and reconstruction framework for the synergistic reconstruction of positron emission tomography (PET) and under sampled sensitivity encoded magnetic resonance imaging data with the aim of improving image quality beyond that obtained through conventional independent reconstructions. The proposed prior improves upon the joint total variation (TV) using a non-convex potential function that assigns a relatively lower penalty for the PET and MR gradients, whose magnitudes are jointly large, thus permitting the preservation and formation of common boundaries irrespective of their relative orientation. The alternating direction method of multipliers (ADMM) optimization framework was exploited for the joint PET-MR image reconstruction. In this framework, the joint maximum a posteriori objective function was effectively optimized by alternating between well-established regularized PET and MR image reconstructions. Moreover, the dependency of the joint prior on the PET and MR signal intensities was addressed by a novel alternating scaling of the distribution of the gradient vectors. The proposed prior was compared with the separate TV and joint TV regularization methods using extensive simulation and real clinical data. In addition, the proposed joint prior was compared with the recently proposed linear parallel level sets (PLSs) method using a benchmark simulation data set. Our simulation and clinical data results demonstrated the improved quality of the synergistically reconstructed PET-MR images compared with the unregularized and conventional separately regularized methods. It was also found that the proposed prior can outperform both the joint TV and linear PLS regularization methods in assisting edge preservation and recovery of details, which are otherwise impaired by noise and aliasing artifacts. In conclusion, the proposed joint sparsity regularization within the presented a- ADMM reconstruction framework is a promising technique, nonetheless our clinical results showed that the clinical applicability of joint reconstruction might be limited in current PET-MR scanners, mainly due to the lower resolution of PET images.

Description: Diffusion-weighted magnetic resonance imaging (DWI) is a key non-invasive imaging technique for cancer diagnosis and tumor treatment assessment, reflecting Brownian movement of water molecules in tissues. Since densely packed cells restrict molecule mobility, tumor tissues produce usually higher signal (a.k.a. less attenuated signal) on isotropic maps compared with normal tissues. However, no general quantitative relation between DWI data and the cell density has been established. In order to link low-resolution clinical cross-sectional data with high-resolution histological information, we developed an image processing and analysis chain, which was used to study the correlation between the diffusion coefficient (D value) estimated from DWI and tumor cellularity from serial histological slides of a resected non-small cell lung cancer tumor. Color deconvolution followed by cell nuclei segmentation was performed on digitized histological images to determine local and cell-type specific 2d (two-dimensional) densities. From these, the 3d cell density was inferred by a model-based sampling technique, which is necessary for the calculation of local and global 3d tumor cell count. Next, DWI sequence information was overlaid with high-resolution CT data and the resected histology using prominent anatomical hallmarks for co-registration of histology tissue blocks and non-invasive imaging modalities’ data. The integration of cell numbers information and DWI data derived from different tumor areas revealed a clear negative correlation between cell density and D value. Importantly, spatial tumor cell density can be calculated based on DWI data. In summary, our results demonstrate that tumor cell count and heterogeneity can be predicted from DWI data, which may open new opportunities for personalized diagnosis and therapy optimization.

Description: Magnetic particle imaging (MPI) is a promising new tomographic imaging method to detect the spatial distribution of superparamagnetic iron-oxide nanoparticles (SPIOs). The aim of this paper was to investigate the potential of MPI to quantify artificial stenoses in vessel phantoms. Custom-made stenosis phantoms (length 40 mm; inner diameter 8 mm) with different degrees of stenosis (0%, 25%, 50%, 75%, and 100%) were scanned in a custom-built MPI scanner (in-plane resolution: ~1–1.5 mm and field of view: 65 $times $ 29 $times $ 29 mm 3 ). Phantoms were filled with diluted Feru-carbotran [SPIO agent, 5 mmol (Fe)/l]. Each measurement (overall acquisition time: 20 ms per image, 400 averages) was repeated ten times to assess reproducibility. The MPI signal was used for semi-automatic stenosis quantification. Two stenosis evaluation approaches were compared based on the signal intensity profile alongside the stenosis phantoms. Using a novel multi-step image evaluation approach, MPI allowed for accurate quantification of different stenosis grades. While low grade stenoses were slightly over-estimated, high grade stenoses were slightly underestimated. In particular, the 0%, 25%, and 50% stenosis phantoms revealed a 6.2% ± 0.8, 25.7% ± 1.0, and 48.0% ± 1.5 stenosis, respectively. The higher grade 75% stenosis phantom revealed a 73.3% ± 2.8 and the 100% stenosis phantom a 95.8%± 1.9 stenosis. MPI accu- ately visualized and quantified different stenosis grades in vessel phantoms with high reproducibility demonstrating its great potential for fast and radiation-free preclinical cardiovascular imaging.