A machine learning system for carotid plaque vulnerability assessment based on ultrasound images

Purpose/Background/Objectives: Carotid plaque vulnerability assessment is essential for the identification of high-risk patients. A specific mouse model for the study of carotid atherosclerosis has been recently developed. Aim of this study was to develop a predictive mathematical model for carotid plaque vulnerability assessment based on the post processing of micro-Ultrasound (μUS) images only. Methods: 17 ApoE-/- male mice (16 weeks) were employed. After three weeks of high-fat diet, a tapered cast, designed to induce the formation of an unstable plaque upstream from the cast and a stable one downstream from it, was surgically placed around the right common carotid. μUS examination was repeated before the surgical procedure and after three months from it. Color-Doppler, B-mode and Pulsed-wave Doppler images were acquired to assess morphological, functional and hemodynamic parameters. In particular, texture analysis was applied on both the atherosclerotic lesions post-processing B-mode images. Peak velocity (Vp), Relative Turbolence Intensity (rTI) and velocity range (rangevel) were assessed from PW-Doppler images. Relative Distension (relD) and Pulse Wave Velocity (PWV) were evaluated for both the regions. All the μUS indexes underwent a feature reduction process and were used to train different machine learning approaches. Results: The downstream region presented higher PWV values than the upstream one; furthermore, it was characterized by higher values of rTI and rangevel. The weighted kNN classifier supplied the best providing 92.6% accuracy, 91% sensitivity and 94% specificity. Conclusions: The mathematical predictive model could represent a valid approach to be translated in the clinical field and easily employed in clinical practice.