TomoGRAF: An X-ray physics-driven generative radiance field framework for extremely sparse view CT reconstruction
PLOS One · 2025
DOI: 10.1371/journal.pone.0330463 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, 2025. Verfasst von Di Xu und 6 weiteren Autor:innen. Beteiligte Einrichtung: Radiation Oncology, University of California, San Francisco, California, United States of America. Hauptthemen laut MEDLINE: Tomography, X-Ray Computed, Imaging, Three-Dimensional, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 68 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NCI NIH HHS, NIBIB NIH HHS, NIH.
Abstract (Originalsprache)
Objectives
Computed tomography (CT) provides high spatial-resolution visualization of 3D structures for various applications. Traditional analytical/iterative CT reconstruction algorithms require hundreds of angular samplings, a condition may not be met practically for physical and mechanical limitations. Sparse view CT reconstruction has been proposed using constrained optimization and machine learning methods with varying success, less so for ultra-sparse view reconstruction. Neural radiance field (NeRF) is a powerful tool for reconstructing and rendering 3D natural scenes from sparse views, but its direct application to 3D medical image reconstruction has been minimally successful due to the differences in photon transportation and available prior information between optic and X-ray.
Methods
We develop TomoGRAF to reconstruct high-quality 3D CT volumes using ultra-sparse projections. TomoGRAF has two main novelties pertinent to X-ray physics and CT imaging. First, TomoGRAF’s volume rendering module accumulates x-ray material attenuation passing through an object with CT geometry rather than visible light material color and opacity from surface interaction in NeRF. Second, TomoGRAF penalizes the difference between the simulated and ground truth volume during training besides the 2D views, thus significantly improving the prior fidelity.
Results
TomoGRAF is trained on LIDC-IDRI dataset (1011 scans) and evaluated on an unseen in-house dataset (100 scans) of distinct imaging characteristics from training and demonstrates a vast leap in performance compared with state-of-the-art deep learning and NeRF methods.
Conclusion
TomoGRAF provides the first generalizable solution for image-guided radiotherapy and interventional radiology applications, where only one/a few X-ray views are available, but 3D volumetric information is desired.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Radiation Oncology, University of California, San Francisco, California, United States of America.
- Radiology, University of California, San Francisco, California, United States of America.
- Radiation Oncology, University of California, Los Angeles, California, United States of America.
Förderung
- NCI NIH HHS
- NIBIB NIH HHS
- NIH
Zitieren
APA
Xu, D., Yang, Y., Liu, H., Lyu, Q., Descovich, M., Ruan, D., & Sheng, K. (2025). TomoGRAF: An X-ray physics-driven generative radiance field framework for extremely sparse view CT reconstruction. PLOS One. https://doi.org/10.1371/journal.pone.0330463
Vancouver
Xu D, Yang Y, Liu H, Lyu Q, Descovich M, Ruan D, et al. TomoGRAF: An X-ray physics-driven generative radiance field framework for extremely sparse view CT reconstruction. PLOS One. 2025. doi:10.1371/journal.pone.0330463
BibTeX
@article{Xu2025,
author = {Xu, Di and Yang, Yang and Liu, Hengjie and Lyu, Qihui and Descovich, Martina and Ruan, Dan and Sheng, Ke},
title = {TomoGRAF: An X-ray physics-driven generative radiance field framework for extremely sparse view CT reconstruction},
journal = {PLOS One},
year = {2025},
doi = {10.1371/journal.pone.0330463}
}
EUVIMED