CVAIMar 2

MAP-Diff: Multi-Anchor Guided Diffusion for Progressive 3D Whole-Body Low-Dose PET Denoising

arXiv:2603.02012v1h-index: 11
AI Analysis

This work addresses noise reduction in low-dose PET scans for medical imaging applications, offering incremental improvements over existing diffusion-based methods by incorporating clinically observed intermediate-dose scans as trajectory anchors.

The paper tackled the problem of severe noise and quantitative degradation in low-dose Positron Emission Tomography (PET) by proposing MAP-Diff, a multi-anchor guided diffusion framework for progressive 3D whole-body PET denoising, which improved PSNR from 42.48 dB to 43.71 dB and reduced NMAE from 0.115 to 0.103 compared to a baseline method.

Low-dose Positron Emission Tomography (PET) reduces radiation exposure but suffers from severe noise and quantitative degradation. Diffusion-based denoising models achieve strong final reconstructions, yet their reverse trajectories are typically unconstrained and not aligned with the progressive nature of PET dose formation. We propose MAP-Diff, a multi-anchor guided diffusion framework for progressive 3D whole-body PET denoising. MAP-Diff introduces clinically observed intermediate-dose scans as trajectory anchors and enforces timestep-dependent supervision to regularize the reverse process toward dose-aligned intermediate states. Anchor timesteps are calibrated via degradation matching between simulated diffusion corruption and real multi-dose PET pairs, and a timestep-weighted anchor loss stabilizes stage-wise learning. At inference, the model requires only ultra-low-dose input while enabling progressive, dose-consistent intermediate restoration. Experiments on internal (Siemens Biograph Vision Quadra) and cross-scanner (United Imaging uEXPLORER) datasets show consistent improvements over strong CNN-, Transformer-, GAN-, and diffusion-based baselines. On the internal dataset, MAP-Diff improves PSNR from 42.48 dB to 43.71 dB (+1.23 dB), increases SSIM to 0.986, and reduces NMAE from 0.115 to 0.103 (-0.012) compared to 3D DDPM. Performance gains generalize across scanners, achieving 34.42 dB PSNR and 0.141 NMAE on the external cohort, outperforming all competing methods.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes