Automatic Vessel Segmentation and Reformation of Non-contrast Coronary Magnetic Resonance Angiography Using Transfer Learning-based 3D U-net with Attention Mechanism

Lu Lin; Yijia Zheng; Yanyu Li; Difei Jiang; Jian Cao; Jian Wang; Yueting Xiao; Xinsheng Mao; Chao Zheng; Yining Wang

doi:10.1016/j.jocmr.2024.101126

Automatic Vessel Segmentation and Reformation of Non-contrast Coronary Magnetic Resonance Angiography Using Transfer Learning-based 3D U-net with Attention Mechanism

J Cardiovasc Magn Reson. 2024 Nov 22:101126. doi: 10.1016/j.jocmr.2024.101126. Online ahead of print.

Authors

Lu Lin¹, Yijia Zheng², Yanyu Li¹, Difei Jiang³, Jian Cao¹, Jian Wang¹, Yueting Xiao³, Xinsheng Mao³, Chao Zheng³, Yining Wang⁴

Affiliations

¹ Department of Radiology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.
² Shukun Technology Co., Ltd, Beijing, China; Center for Biomedical Imaging Research, School of Biomedical Engineering, Tsinghua University, Beijing, China.
³ Shukun Technology Co., Ltd, Beijing, China.
⁴ Department of Radiology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China. Electronic address: wangyining@pumch.cn.

PMID: 39581550
DOI: 10.1016/j.jocmr.2024.101126

Abstract

Background: Coronary Magnetic Resonance Angiography (CMRA) presents distinct advantages, but its reliance on manual image post-processing is labor-intensive and requires specialized knowledge. This study aims to design and test an efficient artificial intelligence (AI) model capable of automating coronary artery segmentation and reformation from CMRA images for coronary artery disease (CAD) diagnosis.

Methods: By leveraging transfer learning from a pre-existing coronary CT angiography model, a 3D attention-aware U-Net was established, trained, and validated on a dataset of 104 subjects' CMRA. Furthermore, an independent clinical evaluation was conducted on an additional cohort of 70 patients. The AI model's performance in segmenting coronary arteries was assessed using the Dice Similarity Coefficient (DSC) and Recall. The comparison between the AI model and manual processing by experienced radiologists on vessel reformation was based on reformatted image quality (rIQ) scoring, post-processing time, and the number of necessary user interactions. The diagnostic performance of AI-segmented CMRA for significant stenosis (≥50% diameter reduction) was evaluated using conventional coronary angiography (CAG) as a reference in sub-set data.

Results: The DSC of the AI model achieved on the training and validation sets were 0.952 and 0.944, with recalls of 0.936 and 0.923, respectively. In the clinical evaluation, the model outperformed manual processes by reducing vessel post-processing time, from 632.6±17.0seconds to 77.4±8.9seconds, and the number of user interactions from 221±59 to 8±2. The AI postprocessed images maintained high rIQ scores comparable to those processed manually (2.7±0.8 vs 2.7±0.6; P=0.4806). In subjects with CAG, the prevalence of CAD was 71%. The sensitivity, specificity, and accuracy at patient-based analysis were 94%, 71%, and 88%, respectively, by AI post-processed whole-heart CMRA.

Conclusion: The AI auto-segmentation system can effectively facilitate CMRA vessel reformation and reduce the time consumption for radiologists. It has the potential to become a standard component of daily workflows, optimizing the clinical application of CMRA in the future.

Keywords: Artificial Intelligence; Coronary Magnetic Resonance Angiography; Image Reformation; Transfer Learning; Vessel Segmentation.