Enregistré dans:
Détails bibliographiques
Auteurs principaux: Li, Qiang, Safari, Mojtaba, Wang, Shansong, Xie, Huiqiao, Ding, Jie, Wang, Tonghe, Yang, Xiaofeng
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2510.23859
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909873236606976
author Li, Qiang
Safari, Mojtaba
Wang, Shansong
Xie, Huiqiao
Ding, Jie
Wang, Tonghe
Yang, Xiaofeng
author_facet Li, Qiang
Safari, Mojtaba
Wang, Shansong
Xie, Huiqiao
Ding, Jie
Wang, Tonghe
Yang, Xiaofeng
contents Low-dose computed tomography (LDCT) reduces patient radiation exposure but introduces substantial noise that degrades image quality and hinders diagnostic accuracy. Existing denoising approaches often require many diffusion steps, limiting real-time applicability. We propose a Regularization-Enhanced Efficient Diffusion Probabilistic Model (RE-EDPM), a rapid and high-fidelity LDCT denoising framework that integrates a residual shifting mechanism to align low-dose and full-dose distributions and performs only four reverse diffusion steps using a Swin-based U-Net backbone. A composite loss combining pixel reconstruction, perceptual similarity (LPIPS), and total variation (TV) regularization effectively suppresses spatially varying noise while preserving anatomical structures. RE-EDPM was evaluated on a public LDCT benchmark across dose levels and anatomical sites. On 10 percent dose chest and 25 percent dose abdominal scans, it achieved SSIM = 0.879 (0.068), PSNR = 31.60 (2.52) dB, VIFp = 0.366 (0.121) for chest, and SSIM = 0.971 (0.000), PSNR = 36.69 (2.54) dB, VIFp = 0.510 (0.007) for abdomen. Visual and statistical analyses, including ablation and Wilcoxon signed-rank tests (p < 0.05), confirm significant contributions from residual shifting and regularization terms. RE-EDPM processes two 512x512 slices in about 0.25 s on modern GPUs, supporting near real-time clinical use. The proposed framework achieves an optimal balance between noise suppression and anatomical fidelity, offering an efficient solution for LDCT restoration and broader medical image enhancement tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2510_23859
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Low-Dose CT Imaging Using a Regularization-Enhanced Efficient Diffusion Probabilistic Model
Li, Qiang
Safari, Mojtaba
Wang, Shansong
Xie, Huiqiao
Ding, Jie
Wang, Tonghe
Yang, Xiaofeng
Medical Physics
Low-dose computed tomography (LDCT) reduces patient radiation exposure but introduces substantial noise that degrades image quality and hinders diagnostic accuracy. Existing denoising approaches often require many diffusion steps, limiting real-time applicability. We propose a Regularization-Enhanced Efficient Diffusion Probabilistic Model (RE-EDPM), a rapid and high-fidelity LDCT denoising framework that integrates a residual shifting mechanism to align low-dose and full-dose distributions and performs only four reverse diffusion steps using a Swin-based U-Net backbone. A composite loss combining pixel reconstruction, perceptual similarity (LPIPS), and total variation (TV) regularization effectively suppresses spatially varying noise while preserving anatomical structures. RE-EDPM was evaluated on a public LDCT benchmark across dose levels and anatomical sites. On 10 percent dose chest and 25 percent dose abdominal scans, it achieved SSIM = 0.879 (0.068), PSNR = 31.60 (2.52) dB, VIFp = 0.366 (0.121) for chest, and SSIM = 0.971 (0.000), PSNR = 36.69 (2.54) dB, VIFp = 0.510 (0.007) for abdomen. Visual and statistical analyses, including ablation and Wilcoxon signed-rank tests (p < 0.05), confirm significant contributions from residual shifting and regularization terms. RE-EDPM processes two 512x512 slices in about 0.25 s on modern GPUs, supporting near real-time clinical use. The proposed framework achieves an optimal balance between noise suppression and anatomical fidelity, offering an efficient solution for LDCT restoration and broader medical image enhancement tasks.
title Low-Dose CT Imaging Using a Regularization-Enhanced Efficient Diffusion Probabilistic Model
topic Medical Physics
url https://arxiv.org/abs/2510.23859