364-04-003 ISMRM Abstract

Improved training of energy-based models using score distillation for accelerated MRI

Primary: Acquisition & Reconstruction - Image Reconstruction: AI

Secondary: Analysis Methods - Generative Models

364-04-003 · Image Reconstruction Using Generative Models · Monday, 11 May, 2:45 PM–3:40 PM · Digital Posters Row E

Keywords: Sampling algorithm Generative AI Uncertainty estimation Inverse Problem Energy-based models

Accepted

Jyothi Rikhab Chand ¹, Sahil Murtaza¹, Mathews Jacob¹

¹Department of Electrical and Computer Engineering, University of Virginia, Charlottesville, United States of America

Presenting Author: Jyothi Rikhab Chand

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.

References

1. J. R. Chand and M. Jacob, “Multi-scale energy (muse) framework for inverse problems in imaging,” IEEE Transactions on Computational Imaging, pp. 1–16, 2024

2. Song and D. P. Kingma, “How to train your energy-based models,” arXiv preprint arXiv:2101.03288, 2021.

3. J. Thornton, et al. "Composition and control with distilled energy diffusion models and sequential Monte Carlo." arXiv preprint arXiv:2502.12786, 2025.

4. Y. Arefeen, B. Levac, B. Patel et al., “Diffusion probabilistic generative models for accelerated, in-nicu permanent magnet neonatal mri,” Magnetic Resonance in Medicine, 2025.

Cite this abstract

http://echo.ismrm.org/p/ISMRM2026/364-04-003