A Video-based Automated Tracking and Analysis System of Plaque Burden in Carotid Artery using Deep Learning: A Comparison with Senior Sonographers

Gao, Wenjing1; Liu, Mengmeng1; Xu, Jinfeng1; Hong, Shaofu1; Chen, Jiayi2; Cui, Chen2; Shi, Siyuan2; Dong, Yinghui1; Song, Di1; Dong, Fajin1

2024-04-01

10.2174/0115734056296233240401061756

CURRENT MEDICAL IMAGING   影响因子和分区

1573-4056

1875-6603

["Background and Objective:","The incidence of stroke is rising, and it is the second major cause of mortality and the third leading cause of disability globally. The goal of this study was to rapidly and accurately identify carotid plaques and automatically quantify plaque burden using our automated tracking and segmentation US-video system.","Methods:","We collected 88 common carotid artery transection videos (11048 frames) with a history of atherosclerosis or risk factors for atherosclerosis, which were randomly divided into training, test, and validation sets using a 6:3:1 ratio. We first trained different segmentation models to segment the carotid intima and adventitia, and calculate the maximum plaque burden automatically. Finally, we statistically analyzed the plaque burden calculated automatically by the best model and the results of manual labeling by senior sonographers.","Results:","Of the three Artificial Intelligence (AI) models, the Robust Video Matting (RVM) segmentation model's carotid intima and adventitia Dice Coefficients (DC) were the highest, reaching 0.93 and 0.95, respectively. Moreover, the RVM model has shown the strongest correlation coefficient (0.61 +/- 0.28) with senior sonographers, and the diagnostic effectiveness between the RVM model and experts was comparable with paired-t test and Bland-Altman analysis [P=0.632 and ICC 0.01 (95% CI: -0.24 similar to 0.27), respectively].","Conclusion:","Our findings have indicated that the RVM model can be used in ultrasound carotid video. The RVM model can automatically segment and quantify atherosclerotic plaque burden at the same diagnostic level as senior sonographers. The application of AI to carotid videos offers more precise and effective methods to evaluate carotid atherosclerosis in clinical practice."]

Artificial intelligence Arteriosclerosis Deep learning Maximum plaque burden Carotid artery video Sonographers

SCI

英语

第一 ; 通讯

Clinical Scientist Training Program of Shenzhen People's Hospital[SYWGSCGZH202202] ; National Key Research and Development Program of China[2022YFC3602400] ; Science and Technology Program for Social Development of Heyuan[2023038]

Radiology, Nuclear Medicine & Medical Imaging

Radiology, Nuclear Medicine & Medical Imaging

WOS:001292146900001

BENTHAM SCIENCE PUBL LTD

Web of Science

1.Southern Univ Sci & Technol, Shenzhen Peoples Hosp, Clin Med Coll 2, Affiliated Hosp 1,Jinan Univ,Dept Ultrasound, Shenzhen 518020, Guangdong, Peoples R China
2.1Illuminate LLC, Dept Artificial Intelligence, Shenzhen 518000, Guangdong, Peoples R China

Gao, Wenjing,Liu, Mengmeng,Xu, Jinfeng,et al. A Video-based Automated Tracking and Analysis System of Plaque Burden in Carotid Artery using Deep Learning: A Comparison with Senior Sonographers[J]. CURRENT MEDICAL IMAGING,2024.

Gao, Wenjing.,Liu, Mengmeng.,Xu, Jinfeng.,Hong, Shaofu.,Chen, Jiayi.,...&Dong, Fajin.(2024).A Video-based Automated Tracking and Analysis System of Plaque Burden in Carotid Artery using Deep Learning: A Comparison with Senior Sonographers.CURRENT MEDICAL IMAGING.

Gao, Wenjing,et al."A Video-based Automated Tracking and Analysis System of Plaque Burden in Carotid Artery using Deep Learning: A Comparison with Senior Sonographers".CURRENT MEDICAL IMAGING (2024).