Nonperiodic dynamic CT reconstruction using backward-warping implicit neural representation with diffeomorphism regularization.
Authors
Affiliations (7)
Affiliations (7)
- Engineering Physics, Tsinghua University, Tsinghua University, Haidian District, Beijing, China, 100084, China.
- Department of Radiology, Beijing Tsinghua Changgung Hospital, School of Clinical Medicine, Tsinghua Medicine, Tsinghua University, Department of Radiology, Beijing Tsinghua Changgung Hospital, School of Clinical Medicine, Tsinghua Medicine, Tsinghua University, Beijing, 102218, China.
- United Imaging Healthcare North America Inc, United Imaging Healthcare, North America, Houston, Texas, 77054, United States.
- Shanghai United Imaging Healthcare Co Ltd, Shanghai United Imaging Healthcare Co Ltd, Shanghai, Shanghai, 201807, China.
- Tsinghua University Department of Engineering Physics, Tsinghua University, Beijing, Beijing, 100084, China.
- Tsinghua University Department of Engineering Physics, TsinghuaUniversity, Beijing, Beijing, 100084, China.
- Department of Engineering Physics, Tsinghua University Department of Engineering Physics, Tsinghua University, Beijing, Beijing, 100084, China.
Abstract
\textit{Objective.} Motion artifacts remain a major obstacle in dynamic computed tomography (CT) reconstruction, particularly for nonperiodic rapid motion such as cardiac imaging in patients with fast or irregular heart rates, where ECG-gated approaches are unreliable. The extreme limited-angle problem arising from insufficient angular coverage within a single cardiac phase makes accurate reconstruction of fine cardiac structures especially challenging. This work aims to develop a self-supervised framework that recovers high-resolution dynamic CT images from nonperiodic motion scenarios without external training datasets.

\textit{Approach.} We propose BIRD, an implicit neural representation (INR) framework for nonperiodic dynamic CT reconstruction, with three components: (1) a dual-feature representation decomposing the dynamic scene into topology-preserving and free-form features, enabling modeling of both deformable motion and residual variations such as contrast kinetics; (2) a backward-warping deformation model enabling direct ray-based training, overcoming the resolution limitations of prior forward-warping INR approaches at clinically relevant sub-millimeter resolution; and (3) a diffeomorphism-based regularization enforcing anatomically plausible deformation vector fields through bidirectional inverse consistency, without restricting representational capacity.

\textit{Main results.} BIRD was validated on digital and physical cardiac phantoms and retrospective patient data. In the XCAT phantom study under severe limited-angle conditions (0.5 s/rot, 120 bpm), BIRD improved PSNR over the next-best method by 1.43 dB on the right coronary artery and 1.21 dB on the right ventricle. Curved planar reformation confirmed improved vessel continuity and boundary sharpness. On real projection data from a physical cardiac phantom and a retrospective patient scan, BIRD reduced motion artifacts and improved depiction of cardiac and vascular structures compared with conventional reconstructions.

\textit{Significance.} The proposed framework performs self-supervised reconstruction of nonperiodic dynamic CT images solely from projection data. It offers potential clinical applications including non-ECG-gated cardiac imaging for patients with arrhythmia, cinematic image sequences, and retrospective motion artifact correction in conventional CT scans.