Pretrained subtraction and segmentation model for coronary angiograms

作者全名："Zeng, Yunjie; Liu, Han; Hu, Juan; Zhao, Zhengbo; She, Qiang"

作者地址："[Zeng, Yunjie; Zhao, Zhengbo; She, Qiang] Chongqing Med Univ, Dept Cardiol, Affiliated Hosp 2, Chongqing 400010, Peoples R China; [Zeng, Yunjie] Chongqing Med Univ, Affiliated Dazus Hosp, Dept Cardiol, Chongqing 402360, Peoples R China; [Liu, Han] Jiulongpo Dist Peoples Hosp, Dept Neurol, Chongqing 400050, Peoples R China; [Hu, Juan] Chongqing Med & Pharmaceut Coll, Affiliated Hosp 1, Chongqing 400060, Peoples R China"

通信作者："She, Q (通讯作者)，Chongqing Med Univ, Dept Cardiol, Affiliated Hosp 2, Chongqing 400010, Peoples R China."

来源：SCIENTIFIC REPORTS

ESI学科分类：Multidisciplinary

WOS号：WOS:001299817400018

JCR分区：Q1

影响因子：4.6

年份：2024

卷号：14

期号：1

开始页：　

结束页：　

文献类型：Article

关键词：Vessel segmentation; Coronary angiogram; Deep learning; Digital subtraction angiography

摘要："This study introduces a novel self-supervised learning method for single-frame subtraction and vessel segmentation in coronary angiography, addressing the scarcity of annotated medical samples in AI applications. We pretrain a U-Net model on a large dataset of unannotated coronary angiograms using an image-to-image translation framework, then fine-tune it on a limited set of manually annotated samples. The pretrained model excels at comprehensive single-frame subtraction, outperforming existing DSA methods. Fine-tuning with just 40 samples yields a Dice coefficient of 0.828 for vessel segmentation. On the public XCAD dataset, our model sets a new state-of-the-art benchmark with a Dice coefficient of 0.755, surpassing both unsupervised and supervised learning approaches. This method achieves robust single-frame subtraction and demonstrates that combining pretraining with minimal fine-tuning enables accurate coronary vessel segmentation with limited manual annotations. We successfully apply this approach to assist physicians in visualizing potential vascular stenosis sites during coronary angiography. Code, dataset, and a live demo will be available available at: https://github.com/newfyu/DeepSA."

基金机构：the Key project of Technology Innovation and Application Development in Chongqing [CSTB2023TIAD-KPX0048]; Key Project of Technology Innovation and Application Development in Chongqing [CSTB2024NSCQ-MSX0251]; Chongqing Natural Science Foundation [KJQN202402805]; Scientific and Technological Research Program of Chongqing Municipal Education Commission

基金资助正文："This work was supported by the Key Project of Technology Innovation and Application Development in Chongqing (Grant No. CSTB2023TIAD-KPX0048), the Chongqing Natural Science Foundation (Grant No. CSTB2024NSCQ-MSX0251), and the Scientific and Technological Research Program of Chongqing Municipal Education Commission (Grant No. KJQN202402805)."