EUVIMEDDescoperă EUVIMED
Open access

Low‐dose CT imaging using a regularization‐enhanced efficient diffusion probabilistic model

Qiang Li, Mojtaba Safari, Shansong Wang, Huiqiao Xie, Jie Ding, Tonghe Wang, Xiaofeng Yang

Medical Physics · 2026-08 · 53 (8)

DOI: 10.1002/mp.70626 ↗

At a glance

Journal article in Medical Physics, published online on 2026-08-06. Written by Qiang Li and 6 co-authors. Institution: Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, Georgia, USA. Major MEDLINE topics: Tomography, X-Ray Computed, Radiation Dosage, Image Processing, Computer-Assisted, Models, Statistical. 55 references. The full text is freely available in PubMed Central. Funded by: NIH HHS, NCI NIH HHS, National Institutes of Health.

RezumatSubjectsDate bibliograficeCiteRelated studies

Abstract (original language)

Background

Low‐dose CT (LDCT) imaging reduces patient radiation exposure but introduces elevated noise levels that degrade image quality and undermine downstream clinical tasks such as diagnosis and quantitative analysis. Existing denoising approaches often require extensive diffusion steps that impede real‑time clinical applicability.

Purpose

To address this challenge, we propose a regularization‐enhanced efficient diffusion probabilistic model (RE‐EDPM), a rapid and high‐fidelity denoising framework that incorporates residual guidance between low dose and full dose CT scans and employs hybrid perceptual and total variation (TV) regularization to preserve anatomical fidelity and diagnostic quality.

Methods

RE‐EDPM incorporates a residual‐shifting mechanism into the forward diffusion process to better align the LDCT and FDCT distributions, followed by four reverse diffusion steps using a Swin‐based U‐Net backbone. A composite loss function combining pixel‐level reconstruction, perceptual similarity (LPIPS), and spatially TV is used to suppress spatially varying noise while preserving fine structural details. We evaluated RE‐EDPM on a public LDCT benchmark dataset across different dose levels and anatomical sites. Quantitative performance was assessed using structural similarity index measure (SSIM), peak signal‐to‐noise ratio (PSNR), and visual information fidelity (VIFp), and RE‐EDPM was compared against several state‐of‐the‐art methods.

Results

On public LDCT benchmarks at 10% dose for chest and 25% dose for abdomen, RE‐EDPM achieved SSIM of 0.879 ± 0.068, PSNR of 31.60 ± 2.52 dB, and VIFp of 0.366 ± 0.121 for chest images, and SSIM of 0.971 ± 0.000, PSNR of 36.69 ± 2.54 dB, and VIFp of 0.510 ± 0.007 for abdominal images. Visualizations of residual and difference maps confirmed superior noise suppression and structural fidelity. Ablation studies and Wilcoxon signed‐rank tests ( p < 0.05) validated the significant contributions of the residual‐shifting mechanism and each regularization component. RE‐EDPM processes two 512 × 512 slices in approximately 0.25 s (≈ 0.125 s per slice) on modern high‐performance hardware, supporting near‐real‐time clinical application.

Conclusions

RE‐EDPM offers robust LDCT denoising with minimal inference time, achieving an optimal balance between noise reduction and anatomical preservation. Its efficiency and high performance make it a strong candidate for real‐time clinical deployment and for broader applications in transforming low‐quality to high‐quality medical imaging tasks.

Subjects

MeSH terms (MEDLINE)

Tomography, X-Ray ComputedRadiation DosageImage Processing, Computer-AssistedModels, StatisticalSignal-To-Noise RatioHumansDiffusion

Author keywords

Swin U‐Netdenoisingdiffusion probabilistic modellearned perceptual image patch similaritylow‐dose CTperceptual regularizationresidual‐shiftingtotal variation loss

Authors and institutions

  • Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, Georgia, USA.
  • Department of Radiation and Cellular Oncology, The University of Chicago, Chicago, Illinois, USA.
  • Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, New York, USA.

Funding

  • NIH HHS
  • NCI NIH HHS
  • National Institutes of Health

Cite

APA

Li, Q., Safari, M., Wang, S., Xie, H., Ding, J., Wang, T., & Yang, X. (2026). Low‐dose CT imaging using a regularization‐enhanced efficient diffusion probabilistic model. Medical Physics, 53(8). https://doi.org/10.1002/mp.70626

Vancouver

Li Q, Safari M, Wang S, Xie H, Ding J, Wang T, et al. Low‐dose CT imaging using a regularization‐enhanced efficient diffusion probabilistic model. Medical Physics. 2026;53(8). doi:10.1002/mp.70626

BibTeX
@article{Li2026,
  author = {Li, Qiang and Safari, Mojtaba and Wang, Shansong and Xie, Huiqiao and Ding, Jie and Wang, Tonghe and Yang, Xiaofeng},
  title = {Low‐dose CT imaging using a regularization‐enhanced efficient diffusion probabilistic model},
  journal = {Medical Physics},
  year = {2026},
  volume = {53},
  number = {8},
  doi = {10.1002/mp.70626}
}
Start for free →