Plaque Territory Detection in IVUS Images based on Concentration of Entropy and Gradient Magnitude via Spiral Random Walk-based Approach

Abstract

This paper presents a simple and optimal approach for automatically identifying the location and size of plaque territories in IVUS images, thus improving plaque territory classification. Unlike existing circular-based algorithms, we leverage the anatomical structure of IVUS images to enhance accuracy. The adventitia, which constitutes the largest part of the image, serves as a landmark; however, its low contrast makes edge detection challenging. To address this issue, we enhance the brightness of the adventitia, identify and remove intima blobs, and accurately determine the media boundary. This aids in simplifying the calculation of plaque territory. To locate the plaque territory, we employ a spiral random walk-based approach that utilizes the concentration of entropy and gradient magnitude in the target area. Our approach outperforms existing methods, contributing to automated plaque analysis for cardiovascular disease diagnosis and treatment. The results show that the proposed approach achieves an accuracy of 0.89, precision of 0.81, recall of 0.77, and F1-Score of 0.83, respectively.