Abstract
This study aims to develop a new computer-aided detection (CAD) scheme to detect early interstitial lung disease (ILD) using low-dose computed tomography (CT) examinations. The CAD scheme classifies each pixel depicted on the segmented lung areas into positive or negative groups for ILD using a mesh-grid-based region growth method and a multi-feature-based artificial neural network (ANN). A genetic algorithm was applied to select optimal image features and the ANN structure. In testing each CT examination, only pixels selected by the mesh-grid region growth method were analyzed and classified by the ANN to improve computational efficiency. All unselected pixels were classified as negative for ILD. After classifying all pixels into the positive and negative groups, CAD computed a detection score based on the ratio of the number of positive pixels to all pixels in the segmented lung areas, which indicates the likelihood of the test case being positive for ILD. When applying to an independent testing dataset of 15 positive and 15 negative cases, the CAD scheme yielded the area under receiver operating characteristic curve (AUC = 0.884 ± 0.064) and 80.0% sensitivity at 85.7% specificity. The results demonstrated the feasibility of applying the CAD scheme to automatically detect early ILD using low-dose CT examinations.
Export citation and abstract BibTeX RIS
General scientific summary. Interstitial lung disease (ILD) is a group of heterogeneous diseases that cause considerable morbidity and mortality rate of patients. Early detection and treatment of ILD provides a better chance of increasing patients' survival probability. Although computed tomography (CT) has been widely used in ILD detection, visual assessment of CT examinations is difficult and time-consuming, which results in substantial intra- and inter-reader variability. This study developed and tested a new computer-aided detection (CAD) scheme to detect early ILD from asymptomatic participants using low-dose CT examinations. The CAD scheme scans images using a mesh-grid based region growth method and an artificial neural network to classify between positive and negative pixels and then generates a quantitative score to detect ILD cases. When applying to an independent testing dataset, CAD yielded 80.0% sensitivity at 85.7% specificity in this study. The results demonstrated the feasibility of applying CAD to detect early ILD using low-dose CT examinations.