Study on various defuzzification methods for fuzzy clustering algorithms to improve ROIs detection in lung CTs

The detection of pulmonary nodules is one of the most studied areas and challenging task in the field of medical image analysis, due the current relevance of the lung carcinoma. The difficulty and complexity of this task has led to the development of CAD systems for the automated detection of lung nodules in CT scans, which provides valuable assistance for radiologists and could improve the detection rate. A common phase of these systems is the detection of regions of interest (ROIs) that could be marked as nodules, in order to reduce the searching space problem. In this paper, we evaluate and compare the combination of various approaches of supervised vector machines (SVMs) with different kinds of fuzzy clustering algorithms, so as to improve the detection and segmentation of ROIs that could represent lung nodules in high resolution CT scans. These images are provided by the LIDC database (Lung Internet Database Consortium).