Kim Justin N, Song Yingnan, Wu Hao, Subramaniam Ananya, Lee Jihye, Makhlouf Mohamed H E, Hassani Neda S, Al-Kindi Sadeer, Wilson David L, Lee Juhwan
Case Western Reserve University, Department of Biomedical Engineering, Cleveland, Ohio, United States.
Harrington Heart and Vascular Institute, University Hospitals Cleveland Medical Center, Cardiovascular Imaging Core Laboratory, Cleveland, Ohio, United States.
J Med Imaging (Bellingham). 2025 Jan;12(1):016002. doi: 10.1117/1.JMI.12.1.016002. Epub 2025 Feb 17.
Coronary artery disease (CAD) is a leading cause of morbidity and mortality worldwide, with coronary computed tomography angiography (CCTA) playing a crucial role in its diagnosis. The mean Hounsfield unit (HU) of pericoronary adipose tissue (PCAT) is linked to cardiovascular risk. We utilized a self-supervised learning framework (SSL) to improve the accuracy and generalizability of coronary artery segmentation on CCTA volumes while addressing the limitations of small-annotated datasets.
We utilized self-supervised pretraining followed by supervised fine-tuning to segment coronary arteries. To evaluate the data efficiency of SSL, we varied the number of CCTA volumes used during pretraining. In addition, we developed an automated PCAT segmentation algorithm utilizing centerline extraction, spatial-geometric coronary identification, and landmark detection. We evaluated our method on a multi-institutional dataset by assessing coronary artery and PCAT segmentation accuracy via Dice scores and comparing mean PCAT HU values with the ground truth.
Our approach significantly improved coronary artery segmentation, achieving Dice scores up to 0.787 after self-supervised pretraining. The automated PCAT segmentation achieved near-perfect performance, with -squared values of 0.9998 for both the left anterior descending artery and the right coronary artery indicating excellent agreement between predicted and actual mean PCAT HU values. Self-supervised pretraining notably enhanced model generalizability on external datasets, improving overall segmentation accuracy.
We demonstrate the potential of SSL to advance CCTA image analysis, enabling more accurate CAD diagnostics. Our findings highlight the robustness of SSL for automated coronary artery and PCAT segmentation, offering promising advancements in cardiovascular care.
冠状动脉疾病（CAD）是全球发病和死亡的主要原因，冠状动脉计算机断层扫描血管造影（CCTA）在其诊断中起着关键作用。冠状动脉周围脂肪组织（PCAT）的平均亨氏单位（HU）与心血管风险相关。我们利用自监督学习框架（SSL）来提高CCTA容积上冠状动脉分割的准确性和通用性，同时解决小标注数据集的局限性。
我们利用自监督预训练，然后进行监督微调来分割冠状动脉。为了评估SSL的数据效率，我们改变了预训练期间使用的CCTA容积数量。此外，我们开发了一种利用中心线提取、空间几何冠状动脉识别和地标检测的自动PCAT分割算法。我们通过Dice分数评估冠状动脉和PCAT分割的准确性，并将平均PCAT HU值与真实值进行比较，在一个多机构数据集上评估我们的方法。
我们的方法显著改善了冠状动脉分割，自监督预训练后Dice分数高达0.787。自动PCAT分割取得了近乎完美的性能，左前降支和右冠状动脉的R平方值均为0.9998，表明预测的和实际的平均PCAT HU值之间具有极好的一致性。自监督预训练显著提高了模型在外部数据集上的通用性，提高了整体分割准确性。
我们证明了SSL在推进CCTA图像分析方面的潜力，能够实现更准确的CAD诊断。我们的研究结果突出了SSL在自动冠状动脉和PCAT分割方面的稳健性，为心血管护理提供了有前景的进展。
