AUTHOR=Chen Ya-Fang , Chen Zhen-Jie , Lin You-Yu , Lin Zhi-Qiang , Chen Chun-Nuan , Yang Mei-Li , Zhang Jin-Yin , Li Yuan-zhe , Wang Yi , Huang Yin-Hui 

TITLE=Stroke risk study based on deep learning-based magnetic resonance imaging carotid plaque automatic segmentation algorithm

JOURNAL=Frontiers in Cardiovascular Medicine

VOLUME=Volume 10 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/cardiovascular-medicine/articles/10.3389/fcvm.2023.1101765

DOI=10.3389/fcvm.2023.1101765

ISSN=2297-055X

ABSTRACT=The primary factor for cardiovascular disease and upcoming cardiovascular events is atherosclerosis. Recently, carotid plaque texture, as observed on ultrasonography, is varied and difficult to classify with the human eye due to substantial inter-observer variability. High-resolution MR plaque imaging offers naturally superior soft tissue contrasts to CT and ultrasonography, and a combination of different contrast weightings may provide more useful information. Radiation-freeness and operator independence are two additional benefits of MRI. However, other from preliminary research on MR texture analysis of basilar artery plaque, there is currently no information available addressing MR radiomics on carotid plaque. For the automatic segmentation of MRI scans to detect carotid plaque for stroke risk assessment, there is a need for a computer-aided autonomous framework to classify MRI scans automatically. We used to detect carotid plaque from MRI scans for stroke risk assessment pre-trained models, fine-tuned them, and adjusted hyper parameters according to our problem. Our trained YOLO V3 model achieved 94.81% accuracy, RCNN achieved 92.53% accuracy, and Mobile Net achieved 90.23% in identification carotid plaque from MRI scans into for stroke risk assessment.