Atherosclerotic plaque classification in carotid ultrasound images using machine learning and explainable deep learning  

作　　者：Soni Singh Pankaj K.Jain Neeraj Sharma Mausumi Pohit Sudipta Roy 

机构地区：[1]School of Vocational Studies and Applied Sciences,Gautam Buddha University,Greater Noida,Uttar Pradesh,India [2]Artificial Intelligence and Data Science Jio Institute,Navi Mumbai,Maharashtra,India [3]School of Biomedical Engineering,Indian Institute of Technology,Varanasi,Uttar Pradesh,India

出　　处：《Intelligent Medicine》2024年第2期83-95,共13页智慧医学（英文）

基　　金：supported by a Council of Scientific and Industrial Research-Junior Research Fellowship(CSIR-JRF#09/1013(0003)/2018);RFIER-Jio Institute"CVMI-Computer Vision in Medical Imaging"research project(RFIER-Jio Institute,Grant No.2022/33185004),under the"AI for ALL"research center.

摘　　要：Objective The incidence of cardiovascular diseases(CVD)is rising rapidly worldwide.Some forms of CVD,such as stroke and heart attack,are more common among patients with certain conditions.Atherosclerosis development is a major factor underlying cardiovascular events,such as heart attack and stroke,and its early detection may prevent such events.Ultrasound imaging of carotid arteries is a useful method for diagnosis of atherosclerotic plaques;however,an automated method to classify atherosclerotic plaques for evaluation of early-stage CVD is needed.Here,we propose an automated method for classification of high-risk atherosclerotic plaque ultrasound images.Methods Five deep learning(DL)models(VGG16,ResNet-50,GoogLeNet,XceptionNet,and SqueezeNet)were used for automated classification and the results compared with those of a machine learning(ML)-based technique,involving extraction of 23 texture features from ultrasound images and classification using a Support Vector Machine classifier.To enhance model interpretability,output gradient-weighted convolutional activation maps(GradCAMs)were generated and overlayed on original images.Results A series of indices,including accuracy,sensitivity,specificity,F1-score,Cohen-kappa index,and area under the curve values,were calculated to evaluate model performance.GradCAM output images allowed visualization of the most significant ultrasound image regions.The GoogLeNet model yielded the highest accuracy(98.20%).Conclusion ML models may be also suitable for applications requiring low computational resource.Further,DL models could be more completely automated than ML models.

关 键 词：Explainable deep learning Carotid artery CLASSIFICATION VGG 16 ResNet-50 GoogLeNet XceptionNet SqueezeNet 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TP181[自动化与计算机技术—计算机科学与技术]