Ultrasound-based internal carotid artery plaque characterization using deep learning paradigm on a supercomputer: a cardiovascular disease/stroke risk assessment system
- 9 January 2021
- journal article
- research article
- Published by Springer Science and Business Media LLC in The International Journal of Cardiovascular Imaging
- Vol. 37 (5), 1511-1528
- https://doi.org/10.1007/s10554-020-02124-9
Abstract
Visual or manual characterization and classification of atherosclerotic plaque lesions are tedious, error-prone, and time-consuming. The purpose of this study is to develop and design an automated carotid plaque characterization and classification system into binary classes, namely symptomatic and asymptomatic types via the deep learning (DL) framework implemented on a supercomputer. We hypothesize that on ultrasound images, symptomatic carotid plaques have (a) a low grayscale median because of a histologically large lipid core and relatively little collagen and calcium, and (b) a higher chaotic (heterogeneous) grayscale distribution due to the composition. The methodology consisted of building a DL model of Artificial Intelligence (called Atheromatic 2.0, AtheroPoint, CA, USA) that used a classic convolution neural network consisting of 13 layers and implemented on a supercomputer. The DL model used a cross-validation protocol for estimating the classification accuracy (ACC) and area-under-the-curve (AUC). A sample of 346 carotid ultrasound-based delineated plaques were used (196 symptomatic and 150 asymptomatic, mean age 69.9 ± 7.8 years, with 39% females). This was augmented using geometric transformation yielding 2312 plaques (1191 symptomatic and 1120 asymptomatic plaques). K10 (90% training and 10% testing) cross-validation DL protocol was implemented and showed an (i) accuracy and (ii) AUC without and with augmentation of 86.17%, 0.86 (p-value < 0.0001), and 89.7%, 0.91 (p-value < 0.0001), respectively. The DL characterization system consisted of validation of the two hypotheses: (a) mean feature strength (MFS) and (b) Mandelbrot's fractal dimension (FD) for measuring chaotic behavior. We demonstrated that both MFS and FD were higher in symptomatic plaques compared to asymptomatic plaques by 64.15 ± 0.73% (p-value < 0.0001) and 6 ± 0.13% (p-value < 0.0001), respectively. The benchmarking results show that DL with augmentation (ACC: 89.7%, AUC: 0.91 (p-value < 0.0001)) is superior to previously published machine learning (ACC: 83.7%) by 6.0%. The Atheromatic runs the test patient in < 2 s. Deep learning can be a useful tool for carotid ultrasound-based characterization and classification of symptomatic and asymptomatic plaques.Keywords
This publication has 72 references indexed in Scilit:
- The size of juxtaluminal hypoechoic area in ultrasound images of asymptomatic carotid plaques predicts the occurrence of strokeJournal of Vascular Surgery, 2013
- Carotid Atherosclerosis and Risk of Subsequent Coronary Event in Outpatients With AtherothrombosisStroke, 2013
- Ovarian Tumor Characterization and Classification Using Ultrasound—A New Online ParadigmJournal of Digital Imaging, 2012
- Atherosclerotic Risk Stratification Strategy for Carotid Arteries Using Texture-Based FeaturesJapanese Journal of Clinical Oncology, 2012
- Asymptomatic internal carotid artery stenosis and cerebrovascular risk stratificationJournal of Vascular Surgery, 2010
- Characterization of Single Thyroid Nodules by Contrast-Enhanced 3-D UltrasoundJapanese Journal of Clinical Oncology, 2010
- High cardiovascular event rates in patients with asymptomatic carotid stenosis: the REACH registry*European Journal of Neurology, 2009
- Fractal dimension and lacunarity analysis of dental radiographsDento maxillo facial radiology, 2005
- Texture-based classification of atherosclerotic carotid plaquesIEEE Transactions on Medical Imaging, 2003
- Ultrasound plaque characterisation, genetic markers and risksPathophysiology of Haemostasis and Thrombosis, 2002