The segmentation of lumen boundaries at intravascular ultrasound images using fuzzy approach

The segmentation of the lumen in intravascular images (IVUS) of the coronary artery is the first step for the evaluation of the morphology of the vessel under analysis and the detection of possible atherosclerotic lesions. In this paper, the segmentation of lumen boundaries at intravascular ultrasound images using fuzzy approach is investigated. In order to diagnose lumen boundaries at IVUS, the noise of images are removed using median filter and also spatial filters in polar coordinates are employed with the purpose of identifying and removing the catheter. In the processing step using two fragmentation algorithm based on Integration i.e. FCM and RHMF and at the same time using a boundary detection algorithm based on tissue leads to finding a more accurate initial guess about the boundaries, then in the second step using approximations that are based on RBF results in improving boundary detection and also decreasing fault detections. The simulation results showed the effectiveness of proposed method with 86.06% of accuracy.