Papers › Bigger Isn't Always Better: Towards a General Prior for Medical Image Reconstruction

Bigger Isn't Always Better: Towards a General Prior for Medical Image Reconstruction

13 Jan 2025arXiv:2501.07376archive 2025-07-28

Lukas Glaszner, Martin Zach

Diffusion model have been successfully applied to many inverse problems, including MRI and CT reconstruction. Researchers typically re-purpose models originally designed for unconditional sampling without modifications. Using two different posterior sampling algorithms, we show empirically that such large networks are not necessary. Our smallest model, effectively a ResNet, performs almost as good as an attention U-Net on in-distribution reconstruction, while being significantly more robust towards distribution shifts. Furthermore, we introduce models trained on natural images and demonstrate that they can be used in both MRI and CT reconstruction, out-performing model trained on medical images in out-of-distribution cases. As a result of our findings, we strongly caution against simply re-using very large networks and encourage researchers to adapt the model complexity to the respective task. Moreover, we argue that a key step towards a general diffusion-based prior is training on natural images.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

vlogroup/bigger-isnt-always-better officialmentioned in papermentioned on GitHubjax report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

CT ReconstructionImage Reconstruction

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AttentionAverage PoolingConcatenated Skip ConnectionConvolutionGlobal Average PoolingKaiming InitializationMax PoolingReLUSoftmaxU-Net

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections