Segmentation of Heart Blood Vessels

The coronary arteries are essential for the proper functioning of the human heart. It is difficult to segment the volume datasets separately from blood-filled cavities of the heart. Main reason for this difficulty is the lack of sufficient spatial resolution and partial volume effects. In this paper, a method is presented to mark the coronary arteries by traversal. The algorithm starts with the extraction of vessel centerlines, which are used as guidelines for the subsequent vessel–filling phase. Then segmentation is obtained using an iterative region growing method that integrates the contents of several binary images resulting from vessel width morphological filters. Therefore an algorithm is proposed for segmenting blood vessels from MRI as the computer-aided analysis.