An intelligent framework for clinical decision making from lung CT slices

Abstract

Computer Aided Diagnosis CAD is one of the major research areas in the field of medical imaging and radiology CAD systems are used by radiologists for detection and differential diagnosis of different types of abnormalities The output of a CAD system can be used by radiologists along with laboratory results to get a second opinion before making a diagnosis CAD systems are developed based on an understanding of the radiological patterns which have to be observed in the image for a particular disease newlineIn this research work three approaches have been proposed for improving the diagnosis of lung disorders from chest computed tomography CT slices The first approach is for the classification of Interstitial Lung Diseases ILDs such as emphysema fibrosis ground glass opacities GGOs and miliary tuberculosis TB using a particle swarm optimized support vector machine SVM The second approach is a novel feature extraction scheme for the classification of cavitary and miliary TB The third approach is a scheme to extract and classify the pleural effusion and pneumothorax regions in lung CT slices newline newline