Let Distortion Guide Restoration (DGR): A physics-informed learning framework for Prostate Diffusion MRI
arXiv:2601.00226v2 Announce Type: replace Abstract: We present Distortion-Guided Restoration (DGR), a physics-informed hybrid CNN-diffusion framework for acquisition-free correction of severe susceptibility-induced distortions in prostate single-shot EPI diffusion-weighted imaging (DWI). DGR is trained to invert a realistic forward distortion model using large-scale paired distorted and undistorted data synthesized from distortion-free prostate DWI and co-registered T2-weighted images from 410 multi-institutional studies, together with 11 measured B0 field maps from metal-implant cases incorporated into a forward simulator to generate low-b DWI (b = 50 s per mm squared), high-b DWI (b = 1400 s per mm squared), and ADC distortions. The network couples a CNN-based geometric correction module
Authors:Ziyang Long, Binesh Nader, Lixia Wang, Archana Vadiraj Malaji, Chia-Chi Yang, Haoran Sun, Rola Saouaf, Timothy Daskivich, Hyung Kim, Yibin Xie, Debiao Li, Hsin-Jung Yang
View PDF HTML (experimental)
Abstract:We present Distortion-Guided Restoration (DGR), a physics-informed hybrid CNN-diffusion framework for acquisition-free correction of severe susceptibility-induced distortions in prostate single-shot EPI diffusion-weighted imaging (DWI). DGR is trained to invert a realistic forward distortion model using large-scale paired distorted and undistorted data synthesized from distortion-free prostate DWI and co-registered T2-weighted images from 410 multi-institutional studies, together with 11 measured B0 field maps from metal-implant cases incorporated into a forward simulator to generate low-b DWI (b = 50 s per mm squared), high-b DWI (b = 1400 s per mm squared), and ADC distortions. The network couples a CNN-based geometric correction module with conditional diffusion refinement under T2-weighted anatomical guidance. On a held-out synthetic validation set (n = 34) using ground-truth simulated distortion fields, DGR achieved higher PSNR and lower NMSE than FSL TOPUP and FUGUE. In 34 real clinical studies with severe distortion, including hip prostheses and marked rectal distension, DGR improved geometric fidelity and increased radiologist-rated image quality and diagnostic confidence. Overall, learning the inverse of a physically simulated forward process provides a practical alternative to acquisition-dependent distortion-correction pipelines for prostate DWI.
Subjects:
Image and Video Processing (eess.IV); Medical Physics (physics.med-ph)
Cite as: arXiv:2601.00226 [eess.IV]
(or arXiv:2601.00226v2 [eess.IV] for this version)
https://doi.org/10.48550/arXiv.2601.00226
arXiv-issued DOI via DataCite
Submission history
From: Ziyang Long [view email] [v1] Thu, 1 Jan 2026 06:18:30 UTC (1,412 KB) [v2] Wed, 1 Apr 2026 01:16:58 UTC (1,412 KB)
Sign in to highlight and annotate this article
Conversation starters
Daily AI Digest
Get the top 5 AI stories delivered to your inbox every morning.
More about
modelannounceacquisition
Microsoft’s new Rho-alpha model brings tactile sensing to robotics
Microsoft’s Rho-Alpha upgrades Vision-Language-Action models with tactile data to bridge the gap between semantic reasoning and low-level motor control. The post Microsoft’s new Rho-alpha model brings tactile sensing to robotics first appeared on TechTalks .
Recursive Language Models: A new framework for infinite context in LLMs
Brute-forcing larger context windows is hitting a mathematical wall. Here is how MIT’s new framework solves "context rot" to process 10 million tokens and beyond. The post Recursive Language Models: A new framework for infinite context in LLMs first appeared on TechTalks .
The Model You Love Is Probably Just the One You Use
The following article originally appeared on Medium and is being republished here with the author’s permission. Ask 10 developers which LLM they’d recommend and you’ll get 10 different answers—and almost none of them are based on objective comparison. What you’ll get instead is a reflection of the models they happen to have access to, the [ ]
Knowledge Map
Connected Articles — Knowledge Graph
This article is connected to other articles through shared AI topics and tags.
More in Models
Microsoft’s new Rho-alpha model brings tactile sensing to robotics
Microsoft’s Rho-Alpha upgrades Vision-Language-Action models with tactile data to bridge the gap between semantic reasoning and low-level motor control. The post Microsoft’s new Rho-alpha model brings tactile sensing to robotics first appeared on TechTalks .
Recursive Language Models: A new framework for infinite context in LLMs
Brute-forcing larger context windows is hitting a mathematical wall. Here is how MIT’s new framework solves "context rot" to process 10 million tokens and beyond. The post Recursive Language Models: A new framework for infinite context in LLMs first appeared on TechTalks .
The Model You Love Is Probably Just the One You Use
The following article originally appeared on Medium and is being republished here with the author’s permission. Ask 10 developers which LLM they’d recommend and you’ll get 10 different answers—and almost none of them are based on objective comparison. What you’ll get instead is a reflection of the models they happen to have access to, the [ ]
Discussion
Sign in to join the discussion
No comments yet — be the first to share your thoughts!