Department of Cardiology, The Second Affiliated Hospital of Chongqing Medical University, Chongqing, 400010, China.
Department of Cardiology, The Affiliated Dazu's Hospital of Chongqing Medical University, Chongqing, 402360, China.
Sci Rep. 2024 Aug 27;14(1):19888. doi: 10.1038/s41598-024-71063-5.
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 .
本研究提出了一种新颖的基于自监督学习的冠状动脉造影单帧减影和血管分割方法，解决了人工智能应用中医学样本标注不足的问题。我们使用图像到图像转换框架在大量未标注的冠状动脉造影数据集上对 U-Net 模型进行预训练，然后在有限的手动标注样本上进行微调。该预训练模型在全面的单帧减影方面表现出色，优于现有的 DSA 方法。仅使用 40 个样本进行微调，血管分割的 Dice 系数达到 0.828。在公共 XCAD 数据集上，我们的模型以 0.755 的 Dice 系数创下了新的技术水平，超过了无监督和监督学习方法。该方法实现了稳健的单帧减影，并证明了结合预训练和最小化微调可以在有限的手动标注下实现准确的冠状动脉血管分割。我们成功地将该方法应用于辅助医生在冠状动脉造影中可视化潜在的血管狭窄部位。代码、数据集和实时演示将在：https://github.com/newfyu/DeepSA 上提供。
