EUVIMEDOntdek EUVIMED
Crossref

Diffusion‐based novel view synthesis for X ‐ray imaging

Meijie Wang, Hongsen Cai, Yan Li, Twaha Kabika, Linxiang Dai, Muyang Yan, Wenguang Hou

Medical Physics · 2026-07 · 53 (7)

DOI: 10.1002/mp.70541 ↗

At a glance

Journal article in Medical Physics, published online on 2026-06-25. Written by Meijie Wang and 6 co-authors. Institution: School of Life Science and Technology, Huazhong University of Science and Technology, Wuhan, China. Major MEDLINE topics: Image Processing, Computer-Assisted. 32 references. Funded by: Hubei Provincial Natural Science Foundation, General Program, Hubei Provincial Natural Science Foundation, Youth Program.

SamenvattingSubjectsBibliografische gegevensCiteRelated studies

Abstract (original language)

Background

X ‐ray imaging is extensively used in clinical practice due to its low cost, accessibility, and relatively low radiation dose. However, its intrinsic two‐dimensional (2D) projection mechanism inevitably leads to severe structural overlap and lesion occlusion in single‐view acquisitions, substantially limiting the completeness and reliability of anatomical interpretation.

Purpose

To overcome the loss of spatial information caused by limited viewing angles, this study proposes a diffusion‐based novel view synthesis framework for X ‐ray imaging that directly generates target‐view X ‐ray images from a small number of reference views, without relying on explicit three‐dimensional reconstruction.

Methods

Built upon the Stable Diffusion framework, the proposed method introduces a lightweight and physically interpretable angular‐difference conditioning mechanism to explicitly model cross‐view geometric relationships. By embedding the relative angular offset between reference and target views into the attention‐based feature interaction process, the model effectively captures view‐dependent structural transformations and synthesizes anatomically consistent novel‐view X ‐ray images.

Results

Extensive experiments on a synthesized multi‐view X ‐ray dataset demonstrate that the proposed approach achieves robust and stable performance under sparse‐view input conditions, significantly outperforming existing methods in terms of view generalization and structural preservation. In particular, for target view offsets of , , and , the proposed method achieves PSNR values of dB, dB, and dB, respectively, together with consistently improved SSIM and LPIPS scores.

Conclusions

These results indicate that the proposed framework provides an efficient and flexible solution for supplementing missing X ‐ray views in clinically constrained imaging scenarios.

Subjects

MeSH terms (MEDLINE)

Image Processing, Computer-AssistedDiffusionImaging, Three-Dimensional

Author keywords

X‐ray image generationdiffusion modelsmedical image enhancementmedical imagingnovel view synthesis

Authors and institutions

  • School of Life Science and Technology, Huazhong University of Science and Technology, Wuhan, China.

Funding

  • Hubei Provincial Natural Science Foundation, General Program
  • Hubei Provincial Natural Science Foundation, Youth Program

Cite

APA

Wang, M., Cai, H., Li, Y., Kabika, T., Dai, L., Yan, M., & Hou, W. (2026). Diffusion‐based novel view synthesis for X ‐ray imaging. Medical Physics, 53(7). https://doi.org/10.1002/mp.70541

Vancouver

Wang M, Cai H, Li Y, Kabika T, Dai L, Yan M, et al. Diffusion‐based novel view synthesis for X ‐ray imaging. Medical Physics. 2026;53(7). doi:10.1002/mp.70541

BibTeX
@article{Wang2026,
  author = {Wang, Meijie and Cai, Hongsen and Li, Yan and Kabika, Twaha and Dai, Linxiang and Yan, Muyang and Hou, Wenguang},
  title = {Diffusion‐based novel view synthesis for X ‐ray imaging},
  journal = {Medical Physics},
  year = {2026},
  volume = {53},
  number = {7},
  doi = {10.1002/mp.70541}
}
Start for free →