Differentiable Forward and Back-Projector for Rigid Motion Estimation in X-Ray Imaging
IEEE Transactions on Biomedical Engineering · 2026-09 · 73 (9) · 3036-3046
DOI: 10.1109/tbme.2025.3643742 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Biomedical Engineering, 2026-09. Verfasst von Xiao Jiang und 4 weiteren Autor:innen. Hauptthemen laut MEDLINE: Imaging, Three-Dimensional, Tomography, X-Ray Computed, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIBIB NIH HHS, National Institutes of Health.
Abstract (Originalsprache)
OBJECTIVE: In this work, we propose a framework for differentiable forward and back-projector that enables scalable, accurate, and memory-efficient gradient computation for rigid motion estimation tasks. METHODS: Unlike existing approaches that rely on auto-differentiation or that are restricted to specific projector types, our method is based on a general analytical gradient formulation for forward/backprojection in the continuous domain. A key insight is that the gradients of both forward and back-projection can be expressed directly in terms of the forward and back-projection operations themselves, providing a unified gradient computation scheme across different projector types. Leveraging this analytical formulation, we develop a discretized implementation with an acceleration strategy that balances computational speed and memory usage. RESULTS: Simulation studies illustrate the numerical accuracy and computational efficiency of the proposed algorithm. Experiments demonstrates the effectiveness of this approach for multiple X-ray imaging tasks we conducted. In 2D/3D registration, the proposed method achieves $\sim 8\times$ speedup over an existing differentiable forward projector while maintaining comparable accuracy. In motion-compensated analytical reconstruction and cone-beam CT geometry calibration, the proposed method enhances image sharpness and structural fidelity on real phantom data while showing significant efficiency advantages over existing gradient-free and gradient-based solutions. CONCLUSION: The proposed differentiable projectors enable effective and efficient gradient-based solutions for X-ray imaging tasks requiring rigid motion estimation.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Förderung
- NIBIB NIH HHS
- National Institutes of Health
Zitieren
APA
Jiang, X., Wang, X., Uneri, A., Zbijewski, W. B., & Stayman, J. W. (2026). Differentiable Forward and Back-Projector for Rigid Motion Estimation in X-Ray Imaging. IEEE Transactions on Biomedical Engineering, 73(9), 3036-3046. https://doi.org/10.1109/tbme.2025.3643742
Vancouver
Jiang X, Wang X, Uneri A, Zbijewski WB, Stayman JW. Differentiable Forward and Back-Projector for Rigid Motion Estimation in X-Ray Imaging. IEEE Transactions on Biomedical Engineering. 2026;73(9):3036-3046. doi:10.1109/tbme.2025.3643742
BibTeX
@article{Jiang2026,
author = {Jiang, Xiao and Wang, Xin and Uneri, Ali and Zbijewski, Wojciech B and Stayman, J Webster},
title = {Differentiable Forward and Back-Projector for Rigid Motion Estimation in X-Ray Imaging},
journal = {IEEE Transactions on Biomedical Engineering},
year = {2026},
volume = {73},
number = {9},
pages = {3036--3046},
doi = {10.1109/tbme.2025.3643742}
}
EUVIMED