Abstract: This study presents a localized region based lankton algorithm with decision median filter for the segmentation of abdominal organs and tumors in CT images. Active contour algorithms based on discrete representation of implicit functions are widely used in medical image segmentation. The decision median filter can filter the gaussian noise and impulse noise efficiently than conventional spatial domain filters with better edge preservation. A comparative analysis of various active contour models is done and the decision median filter based lankton segmentation algorithm gives best result. The performance of the proposed segmentation algorithm was evaluated in terms of metrics like dice coefficient and hausdorff distance. The proposed algorithm effectively segments the abdominal organs and tumors in computer tomography images with well-defined boundaries.
S.N. Kumar, A. Lenin Fred, S. Lalitha Kumari and P. Sebastian Varghese, 2016. Localized Region Based Active Contour Algorithm for Segmentation of Abdominal Organs and Tumors in Computer Tomography Images. Asian Journal of Information Technology, 15: 4783-4789.