Development of Machine Learning Based Classification Method for Carotid Plaques Using Portable 3D Ultrasound

Vulnerable carotid plaques are extremely unstable and prone to rupture and fall off, which are closely related to transient ischemic attacks and ischemic strokes. Portable 3D ultrasound is a radiation-free and non-invasive technique that can conveniently provide more comprehensive dimensional information compared to 2D ultrasound. Five types of feature parameters including the carotid volumetric stenosis rate (CSR), low-intensity rate (LIR), grayscale median (GSM), fractal dimension (FD), and 3D gray level co-occurrence matrix (GLCM) properties were extracted from the 3D image volumes respectively and input into a support vector machine (SVM) classifier. The average accuracy of the SVM model was 0.73±0.05, with a sensitivity of 0.75±0.08 and a specificity of 0.74 ± 0.05. The SVM classifier using extracted features as input performed acceptably in the classification of carotid plaque vulnerability since dimension, grayscale, spatial structure, and texture features were considered. It demonstrated that the proposed method has the potential to screen and diagnose carotid plaques based on portable 3D ultrasound.

I. Introduction

Carotid atherosclerosis (CA) is a common cardiovascular disease characterized by the formation of atherosclerotic plaques [1]. If the vulnerable plaque ruptures and falls off, the fragments of plaque can enter the brain along with the bloodstream and obstruct the cerebral capillaries. Therefore, CA especially the vulnerable plaque has long been considered one of the main causes of stroke. As a radiation-free and non-invasive technique, ultrasound (US) imaging is the most used and effective approach for early detection and timely intervention of carotid plaques [2].