Automatic identification of vulnerable plaque based on flexible neural tree

Wei Tian, Yishen Pang, Sijie Niu, Haochen Yang, Jiwen Dong, Jin Zhou, Yuehui Chen

Abstract: Identification of vulnerable plaque plays an important role in coronary heart disease diagnosis for clinicians. In this paper we propose a novel method based on flexible neural tree (FNT) to identify vulnerable plaques in intravascular optical coherence tomography (IVOCT) images. First, a flexible neural tree classifier is constructed by selecting features of the image. Then, the probabilistic incremental program evolution (PIPE) algorithm optimizes the flexible neural tree structure and uses particle swarm optimization (PSO) to optimize the parameters. Experimental results show that this method can effectively identify vulnerable plaques in IVOCT images.