NerT-CA: Efficient Dynamic Reconstruction from Sparse-view X-ray Coronary Angiography

2025-07-25

AI Summary

To address challenges in sparse-view X-ray coronary angiography (CA)—including sparse vascular structures, low background contrast, severe motion artifacts, and limited angular sampling—this paper proposes a neuro-tensor hybrid representation. Specifically, dynamic coronary arteries are decomposed into a low-rank static component and a sparse dynamic component; for the first time, a fast tensor field model is integrated within a Neural Radiance Fields (NeRF) framework, augmented with differentiable rendering and dynamic neural fields to enable end-to-end 4D reconstruction. The method achieves high-fidelity dynamic 3D coronary reconstruction from only three input views. Evaluated on a 4D synthetic dataset, it accelerates training significantly over state-of-the-art methods while reducing reconstruction error by 21.6%. Moreover, it demonstrates strong robustness to noise and motion artifacts, and exhibits high clinical applicability.

Technology Category

• Computer Vision: 3D Computer Vision
• Machine Learning: Matrix & Tensor Methods
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Three-dimensional (3D) and dynamic 3D+time (4D) reconstruction of coronary arteries from X-ray coronary angiography (CA) has the potential to improve clinical procedures. However, there are multiple challenges to be addressed, most notably, blood-vessel structure sparsity, poor background and blood vessel distinction, sparse-views, and intra-scan motion. State-of-the-art reconstruction approaches rely on time-consuming manual or error-prone automatic segmentations, limiting clinical usability. Recently, approaches based on Neural Radiance Fields (NeRF) have shown promise for automatic reconstructions in the sparse-view setting. However, they suffer from long training times due to their dependence on MLP-based representations. We propose NerT-CA, a hybrid approach of Neural and Tensorial representations for accelerated 4D reconstructions with sparse-view CA. Building on top of the previous NeRF-based work, we model the CA scene as a decomposition of low-rank and sparse components, utilizing fast tensorial fields for low-rank static reconstruction and neural fields for dynamic sparse reconstruction. Our approach outperforms previous works in both training time and reconstruction accuracy, yielding reasonable reconstructions from as few as three angiogram views. We validate our approach quantitatively and qualitatively on representative 4D phantom datasets.

Problem

• Efficient 4D reconstruction from sparse-view X-ray angiography
• Overcoming vessel sparsity and motion challenges in CA
• Reducing training time while improving reconstruction accuracy

Innovation

• Hybrid neural and tensorial representations for 4D reconstruction
• Low-rank static and dynamic sparse decomposition
• Fast tensorial fields for accelerated training