ALBERT

Description: Multioriented text detection and recognition in natural scene images are still challenges in the document analysis and computer vision communities. In particular, character segmentation plays an important role in the complete end-to-end recognition system performance. In this work, a robust multioriented text detection and segmentation method based on a biological visual system model is proposed. The proposed method exploits the local energy model instead of a common approach based on variations of local image pixel intensities. Features such as lines and edges are obtained by searching for the maximum local energy utilizing the scale-space monogenic signal framework. The candidate text components are extracted from maximally stable extremal regions of the local phase information of the image. The candidate regions are filtered by their phase congruency and classified as text and nontext components by the AdaBoost classifier. Finally, misclassified characters are restored, and all final characters are grouped into words. Experimental results show that the proposed text detection and segmentation method is invariant to scale and rotation changes and robust to perspective distortions, blurring, low resolution, and illumination variations (low contrast, high brightness, shadows, and nonuniform illumination). Besides, the proposed method achieves often a better performance compared with state-of-the-art methods on typical natural scene datasets.

Description: Overweight (OW) and obesity (OB) during childhood/adolescence are major public health problems in Mexico. Several obesogenic lifestyle (OL) risk factors have been identified, but the burden and consequences of them in Mexican children/adolescents remain unclear. The objective of this study was to estimate the prevalence of OL components and describe their relationships with adiposity, and OW/OB. A population-based cross-sectional study of Mexican children/adolescents with nutritional assessment, data collection on daily habits and adiposity as fat-mass index (FMI) by dual-energy X-ray absorptiometry was performed. Individual OL-components: “inactivity,” “excessive screen time,” “insufficient sleep,” “unhealthy-diet”, were defined according to non-adherence to previously published healthy recommendations. Results: 1449 subjects were assessed between March 2015 to April 2018. Sixteen percent of subjects had all four OL-components, 40% had three, 35% had two, 9% had one, and 0.5% had none. A cumulative OL score showed a significant dose–response effect with FMI. The combination of inactivity, excessive screen time, and insufficient sleep showed the highest risk association to OW/OB and higher values of FMI. Conclusions: The prevalence of OL-components was extremely high and associated with increased adiposity and OW/OB. Several interventions are needed to revert this major public health threat.

Description: Acrylic bone cements (ABCs) have played a key role in orthopedic surgery mainly in arthroplasties, but their use is increasingly extending to other applications, such as remodeling of cancerous bones, cranioplasties, and vertebroplasties. However, these materials present some limitations related to their inert behavior and the risk of infection after implantation, which leads to a lack of attachment and makes necessary new surgical interventions. In this research, the physicochemical, thermal, mechanical, and biological properties of ABCs modified with chitosan (CS) and graphene oxide (GO) were studied. Fourier transform infrared (FTIR) spectroscopy, proton nuclear magnetic resonance (1H-NMR) scanning electron microscopy (SEM), Raman mapping, thermogravimetric analysis (TGA), differential scanning calorimetry (DSC), compression resistance, mechanical dynamic analysis (DMA), hydrolytic degradation, cell viability, alkaline phosphatase (ALP) activity with human osteoblasts (HOb), and antibacterial activity against Gram-negative bacteria Escherichia coli were used to characterize the ABCs. The results revealed good dispersion of GO nanosheets in the ABCs. GO provided an increase in antibacterial activity, roughness, and flexural behavior, while CS generated porosity, increased the rate of degradation, and decreased compression properties. All ABCs were not cytotoxic and support good cell viability of HOb. The novel formulation of ABCs containing GO and CS simultaneously, increased the thermal stability, flexural modulus, antibacterial behavior, and osteogenic activity, which gives it a high potential for its uses in orthopedic applications.

Description: Illumination-invariant method for computing local feature points and descriptors, referred to as LUminance Invariant Feature Transform (LUIFT), is proposed. The method helps us to extract the most significant local features in images degraded by nonuniform illumination, geometric distortions, and heavy scene noise. The proposed method utilizes image phase information rather than intensity variations, as most of the state-of-the-art descriptors. Thus, the proposed method is robust to nonuniform illuminations and noise degradations. In this work, we first use the monogenic scale-space framework to compute the local phase, orientation, energy, and phase congruency from the image at different scales. Then, a modified Harris corner detector is applied to compute the feature points of the image using the monogenic signal components. The final descriptor is created from the histograms of oriented gradients of phase congruency. Computer simulation results show that the proposed method yields a superior feature detection and matching performance under illumination change, noise degradation, and slight geometric distortions comparing with that of the state-of-the-art descriptors.

Description: Background The COVID-19 pandemic has exposed the vulnerability of healthcare services worldwide, especially in underdeveloped countries. There is a clear need to develop novel computer-assisted diagnosis tools to provide rapid and cost-effective screening in places where massive traditional testing is not feasible. Lung ultrasound is a portable, easy to disinfect, low cost and non-invasive tool that can be used to identify lung diseases. Computer-assisted analysis of lung ultrasound imagery is a relatively recent approach that has shown great potential for diagnosing pulmonary conditions, being a viable alternative for screening and diagnosing COVID-19. Objective To evaluate and compare the performance of deep-learning techniques for detecting COVID-19 infections from lung ultrasound imagery. Methods We adapted different pre-trained deep learning architectures, including VGG19, InceptionV3, Xception, and ResNet50. We used the publicly available POCUS dataset comprising 3326 lung ultrasound frames of healthy, COVID-19, and pneumonia patients for training and fine-tuning. We conducted two experiments considering three classes (COVID-19, pneumonia, and healthy) and two classes (COVID-19 versus pneumonia and COVID-19 versus non-COVID-19) of predictive models. The obtained results were also compared with the POCOVID-net model. For performance evaluation, we calculated per-class classification metrics (Precision, Recall, and F1-score) and overall metrics (Accuracy, Balanced Accuracy, and Area Under the Receiver Operating Characteristic Curve). Lastly, we performed a statistical analysis of performance results using ANOVA and Friedman tests followed by post-hoc analysis using the Wilcoxon signed-rank test with the Holm’s step-down correction. Results InceptionV3 network achieved the best average accuracy (89.1%), balanced accuracy (89.3%), and area under the receiver operating curve (97.1%) for COVID-19 detection from bacterial pneumonia and healthy lung ultrasound data. The ANOVA and Friedman tests found statistically significant performance differences between models for accuracy, balanced accuracy and area under the receiver operating curve. Post-hoc analysis showed statistically significant differences between the performance obtained with the InceptionV3-based model and POCOVID-net, VGG19-, and ResNet50-based models. No statistically significant differences were found in the performance obtained with InceptionV3- and Xception-based models. Conclusions Deep learning techniques for computer-assisted analysis of lung ultrasound imagery provide a promising avenue for COVID-19 screening and diagnosis. Particularly, we found that the InceptionV3 network provides the most promising predictive results from all AI-based techniques evaluated in this work. InceptionV3- and Xception-based models can be used to further develop a viable computer-assisted screening tool for COVID-19 based on ultrasound imagery.