Anatomically and metabolically informed diffusion for unified denoising and segmentation in low-count PET imaging.
Journal
Medical image analysis
Journal Volume
107
Journal Issue
Pt B
Start Page
103831
ISSN
1361-8423
Date Issued
2026-01
Author(s)
Xia, Menghua
Wang, Der-Shiun
Chen, Ming-Kai
Liu, Qiong
Xie, Huidong
Guo, Liang
Ji, Wei
Ouyang, Jinsong
Bayerlein, Reimund
Spencer, Benjamin A
Li, Quanzheng
Badawi, Ramsey D
El Fakhri, Georges
Liu, Chi
Abstract
Positron emission tomography (PET) image denoising, along with lesion and organ segmentation, are critical steps in PET-aided diagnosis. However, existing methods typically treat these tasks independently, overlooking inherent synergies between them as correlated steps in the analysis pipeline. In this work, we present the anatomically and metabolically informed diffusion (AMDiff) model, a unified framework for denoising and lesion/organ segmentation in low-count PET imaging. By integrating multi-task functionality and exploiting the mutual benefits of these tasks, AMDiff enables direct quantification of clinical metrics, such as total lesion glycolysis (TLG), from low-count inputs. The AMDiff model incorporates a semantic-informed denoiser based on diffusion strategy and a denoising-informed segmenter utilizing nnMamba architecture. The segmenter constrains denoised outputs via a lesion-organ-specific regularizer, while the denoiser enhances the segmenter by providing enriched image information through a denoising revision module. These components are connected via a warming-up mechanism to optimize multi-task interactions. Experiments on multi-vendor, multi-center, and multi-noise-level datasets demonstrate the superior performance of AMDiff. For test cases below 20% of the clinical count levels from participating sites, AMDiff achieves TLG quantification biases of -21.60±47.26%, outperforming its ablated versions which yield biases of -30.83±59.11% (without the lesion-organ-specific regularizer) and -35.63±54.08% (without the denoising revision module). By leveraging its internal multi-task synergies, AMDiff surpasses standalone PET denoising and segmentation methods. Compared to the benchmark denoising diffusion model, AMDiff reduces the normalized root-mean-square error for lesion/liver by 22.92/17.27% on average. Compared to the benchmark nnMamba segmentation model, AMDiff improves lesion/liver Dice coefficients by 10.17/2.02% on average.
Subjects
Denoising diffusion model
Multi-task learning
Positron emission tomography
nnMamba
Type
journal article