Detection of pulmonary nodules on chest CT images with support vector machine classifier

The incidence of lung cancer has been increasing, and it is the leading cause of death among males in the United States, Europe and etc. Due to the low survival rates among lung cancer patients, it is necessary to detect and treat the cancer at an early stage. This paper describes a Computer-Aided Diagnosis (CAD) system for pulmonary nodules detection on serial CT scans based on Support vector machine classification (SVM) scheme. Compared with the simple thresholding approach, the SVM yields a more accurate segmentation of the lungs from the chest volume. to identifying initial nodule candidates within the lungs, the proposed system proves to be effective for initial nodule candidates detection and segmentation, as well as existing approaches. False-positive is reduced by rule-based filtering operations in combination with a feature-based support SVM classifier. The proposed system was validated on 147 patient cases from the publicly available online LIDC (Lung Image Database Consortium) database. Experimental results showed that our CADe system obtained an overall sensitivity of 90% at a specificity of 3.9 FPs/scan. and is improved compared to previous systems.

کلیدواژه ها:

Computer-aided detection ، CT scan ، false-positive ، Solitary Pulmonary Nodules ، support vector machine