Detection of Pulmonary Nodules Using MTANN in Chest

Abstract- Computer aided scheme for pulmonary nodule detection in chest radiographs are to detect the pulmonary nodules (lung nodules) that are overlapped by ribs and clavicles and to minimize the false positive results caused by the ribs. Computed Tomography is used to detect lung nodules, but X-Rays are preferred due to low cost and low radiation dose. But x-rays does not effectively detect lung nodules because ribs and clavicles suppress the nodules and produce a false positive result to the radiologists. The purpose is to develop the CADe scheme with improved sensitivity and specificity by use of Virtual Dual Energy (VDE) chest radiographs. Ribs and clavicles in the chest radiographs (X-ray images) are suppressed with MTANN. A non linear support vector classifier is used for classification of nodule candidate. But there are few subtle nodules, still being missed and one of the main reasons could be the use of single fixed contrast parameter for suppressing the ribs. By implementing different rib contrast parameter, subtle nodules can be detected. This will still improve the accuracy and reduce the false positive induced by ribs. Keywords-- MTANN, Ribs contrast suppression, VDE I