arXiv 2407.146162024-07eess.IVcs.CV

DeepCA：基于深度学习的两幅二维非同步X射线血管造影投影三维冠状动脉树重建

DeepCA: Deep Learning-based 3D Coronary Artery Tree Reconstruction from Two 2D Non-simultaneous X-ray Angiography Projections

University of Oxford（牛津大学）；Institute of Biomedical Engineering（生物医学工程研究所）；Division of Cardiovascular Medicine（心血管医学部）；Radcliffe Department of Medicine（拉德克利夫医学系）；Oxford Acute Vascular Imaging Centre（牛津急性血管成像中心）

Yiying Wang, Abhirup Banerjee, Robin P. Choudhury, Vicente Grau

备注：: 17 pages, 13 figures, 3 tables; Early accepted to the WACV 2025

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对非同步X射线血管造影投影难以重建三维冠状动脉树的问题，提出DeepCA深度学习流程，利用Wasserstein条件生成对抗网络等隐式补偿运动，实现三维重建，并在真实数据上验证了良好性能。

摘要：

心血管疾病（CVDs）是全球最常见的死亡原因。侵入性X射线冠状动脉造影（ICA）是诊断心血管疾病最重要的影像学手段之一。ICA通常仅获取两幅二维投影，这使得冠状动脉血管的三维几何结构难以解读，因此需要从两幅投影中重建三维冠状动脉树。现有最先进的方法需要大量人工交互，且无法校正非同步投影之间非刚性的心脏和呼吸运动。在本研究中，我们提出了一种名为DeepCA的新型深度学习流程。我们利用带梯度惩罚的Wasserstein条件生成对抗网络、潜在卷积变换器层和动态蛇形卷积判别器，隐式补偿非刚性运动并提供三维冠状动脉树重建。通过模拟冠状动脉计算机断层扫描血管造影（CCTA）的投影，我们实现了在真实非同步ICA投影上的三维冠状动脉树重建的泛化。我们引入了一种应用特定的评估指标，在CCTA数据集和真实ICA数据集上验证了我们提出的模型，同时使用Chamfer ℓ2距离。结果表明，我们的DeepCA模型在血管拓扑保留、缺失特征恢复以及对真实ICA数据的泛化能力方面表现出令人满意的性能。据我们所知，这是首个利用深度学习从两幅真实非同步X射线血管造影投影实现三维冠状动脉树重建的研究。

英文摘要：

Cardiovascular diseases (CVDs) are the most common cause of death worldwide. Invasive x-ray coronary angiography (ICA) is one of the most important imaging modalities for the diagnosis of CVDs. ICA typically acquires only two 2D projections, which makes the 3D geometry of coronary vessels difficult to interpret, thus requiring 3D coronary artery tree reconstruction from two projections. State-of-the-art approaches require significant manual interactions and cannot correct the non-rigid cardiac and respiratory motions between non-simultaneous projections. In this study, we propose a novel deep learning pipeline named \emph{DeepCA}. We leverage the Wasserstein conditional generative adversarial network with gradient penalty, latent convolutional transformer layers, and a dynamic snake convolutional critic to implicitly compensate for the non-rigid motion and provide 3D coronary artery tree reconstruction. Through simulating projections from coronary computed tomography angiography (CCTA), we achieve the generalisation of 3D coronary tree reconstruction on real non-simultaneous ICA projections. We incorporate an application-specific evaluation metric to validate our proposed model on both a CCTA dataset and a real ICA dataset, together with Chamfer $\ell_2$ distance. The results demonstrate promising performance of our DeepCA model in vessel topology preservation, recovery of missing features, and generalisation ability to real ICA data. To the best of our knowledge, this is the first study that leverages deep learning to achieve 3D coronary tree reconstruction from two real non-simultaneous x-ray angiographic projections.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

AI总结：

摘要：

英文摘要：

相关论文