A Machine Learning Pipeline for Measurement of Arterial Stiffness in A-Mode Ultrasound

• Published in: IEEE transactions on ultrasonics, ferroelectrics, and frequency control ferroelectrics, and frequency control, 2022-01, Vol.69 (1), p.106-113
• Main Authors: Sahani, Ashish Kumar, Srivastava, Divyansh, Sivaprakasam, Mohanasankar, Joseph, Jayaraj
• Format: Article
• Language: English
• Subjects: Arterial stiffness (AS); Artificial neural networks; Biomedical measurement; Blood pressure; Carotid Arteries - diagnostic imaging; Correlation coefficients; Current measurement; Data acquisition; Diameters; Graphical user interfaces; Health care facilities; Humans; Machine Learning; machine learning (ML); Measuring instruments; Modulus of elasticity; neural network; Pulse measurements; Signal processing; Signal processing algorithms; Signal Processing, Computer-Assisted; Stiffness; Tracking systems; Ultrasonic imaging; Ultrasonic variables measurement; Ultrasonography; ultrasound; Vascular Stiffness
• ISSN: 0885-3010; 1525-8955
• DOI: 10.1109/TUFFC.2021.3109117

Arterial stiffness (AS) of the carotid artery is an early marker of stratifying cardiovascular disease risk. This article aims to improve the performance of ARTSENS, a noninvasive A-mode ultrasound-based device for measuring AS. The primary objective of ARTSENS is to enable the measurement of elastic modulus using A-Mode ultrasound and blood pressure. As this device is image-free, there is a need to automate: 1) carotid detection; 2) wall localization; and 3) inner lumen diameter measurement. This has been performed using conventional signal processing methods in some of the earlier works in this domain. In this article, deep neural network (DNN) models are employed to perform the above three tasks. The DNNs were trained over data acquired from 82 subjects at two different medical centers. Ground-truth labeling was performed by a trained operator using corresponding measurements from the state-of-the-art Aloka e-Tracking system. All three DNN models had significantly lower errors compared to earlier signal processing methods and could perform their measurements using a single A-Mode frame. Using the DNNs, two different machine learning pipelines have been proposed here to measure the elastic modulus; the best among them could achieve an error of 9.3% with the Pearson correlation coefficient of 0.94 ( {p} < 0.001 ). The models were tested on Raspberry Pi and Jetson Nano single board computers to demonstrate real-time processing on low computational resources.