Cape Town - 2026 ISMRM-ISMRT Annual Meeting and Exhibition
9 May 2026 – 14 May 2026 · Cape Town, South Africa
360-02-003 ISMRM Abstract

Principled hyperparameter tuning for diffusion-based MRI solvers

Primary: Acquisition & Reconstruction - Image Reconstruction: AI
Secondary: Acquisition & Reconstruction - AI methods
360-02-003 · Machine Learning for Image Reconstruction · Monday, 11 May, 9:15 AM–10:10 AM · Digital Posters Row A
Keywords: Optimization Diffusion models
Accepted
Irmak Sivgin 1, Julio Oscanoa2,3,4, Cagan Alkan1,5, Daniel B Ennis4,6,7,8,9,10, John Pauly1,5,6, Mert Pilanci1, Shreyas Vasanawala6,7,11,12
1Electrical Engineering, Stanford University, Stanford, United States of America
2Bioengineering Department, Stanford University, Stanford, United States of America
3Bioengineering, Stanford University, Stanford, United States of America
4Department of Bioengineering, Stanford University, Stanford, United States of America
5Department of Electrical Engineering, Stanford University, Stanford, United States of America
6Stanford University, Stanford, United States of America
7Department of Radiology, Stanford University, Stanford, United States of America
8Division of Radiology, Veterans Administration Health Care System, Palo Alto, United States of America
9Cardiovascular Institute, Stanford University, Stanford, United States of America
10Department of Radiology, Stanford, California, USA, Stanford University, Stanford, United States of America
11Stanford Medicine, Stanford, United States of America
12Pediatric Radiology, Stanford Medicine, Stanford, United States of America
Presenting Author: Irmak Sivgin

Synopsis

Motivation:
Goals:
Approach:
Results:
Full abstract & presentation

The full text, figures, and any recorded presentation for this abstract are not shown here. Log in if you are a member or registered attendee with access.

Full abstracts, figures, and presentations for Cape Town - 2026 ISMRM-ISMRT Annual Meeting and Exhibition are available to registered attendees. This content becomes freely available to the public roughly two years after the meeting.

To request or purchase access, contact the ISMRM Central Office at info@ismrm.org.

Log in

References

1. Ho J, Jain A, and Abbeel P. Denoising diffusion probabilistic models. Advances in neural information processing systems 2020; 33:6840–51
2. Song Y, Sohl-Dickstein J, Kingma DP, Kumar A, Ermon S, and Poole B. Score-Based Generative Modeling through Stochastic Differential Equations. International Conference on Learning Representations. 2020
3. Zhang B, Chu W, Berner J, Meng C, Anandkumar A, and Song Y. Improving Diffusion Inverse Problem Solving with Decoupled Noise Annealing. 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2025 Jun :20895–905. doi: 10.1109/cvpr52734.2025.01946. Available from: http://dx.doi.org/10.1109/CVPR52734.2025.01946 [doi]
4. Daras G, Chung H, Lai CH, Mitsufuji Y, Ye JC, Milanfar P, Dimakis AG, and Delbracio M. A survey on diffusion models for inverse problems. arXiv preprint arXiv:2410.00083 2024
5. Ramesh V and Mardani M. Test-Time Scaling of Diffusion Models via Noise Trajectory Search. 2025. arXiv: 2506 . 03164 [cs.LG]. Available from: https://arxiv.org/abs/2506.03164
6. Karras T, Aittala M, Aila T, and Laine S. Elucidating the design space of diffusion-based generative models. Advances in neural information processing systems 2022; 35:26565–77
7. Falck F, Pandeva T, Zahirnia K, Lawrence R, Turner R, Meeds E, Zazo J, and Karmalkar S. A Fourier Space Perspective on Diffusion Models. 2025. arXiv: 2505.11278 [stat.ML]. Available from: https://arxiv.org/abs/2505.11278
8. Ozturkler B, Liu C, Eckart B, Mardani M, Song J, and Kautz J. SMRD: SURE-Based Robust MRI Reconstruction with Diffusion Models. International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer. 2023 :199–209
9. Mardani M, Song J, Kautz J, and Vahdat A. A Variational Perspective on Solving Inverse Problems with Diffusion Models. arXiv preprint arXiv:2305.04391 2023

Cite this abstract

http://echo.ismrm.org/p/ISMRM2026/360-02-003