Automated Fast Marching Method for Segmentation and Tracking of Region of Interest in Scintigraphic Images Sequences

摘要

This article introduces an efficient method that combines the advantages of Fast Marching Method (FMM) in conjunction with Harris corner descriptor. An application of Dynamic Renal Scintigraphy imaging has been chosen and a new approach has been applied to see its ability to have a high accuracy of Region Of Interest (ROI) segmentation and tracking in scintigraphic images sequences. The introduced system starts with an image processing algorithm to enhance the contrast of the input images. This is followed by the segmentation phase which consists of an automated algorithm. Finally, the ROI tracking phase was described. To evaluate the performance of the presented approach, we present tests on synthetic and real images are presented. The experimental results obtained show that the effectiveness and performance of the proposed system is satisfactory.