Accelerating MRI With Longitudinally‐Informed Latent Posterior Sampling
We demonstrate that prior scans can be effectively integrated with state-of-the-art diffusion-based reconstruction methods to improve image quality and enable greater scan acceleration, without requiring an extensive longitudinally paired training data set.
Authors
- Abhinav Kumar (ORCID: https://orcid.org/0000-0001-9367-7069)
- Yonatan Urman (ORCID: https://orcid.org/0000-0002-5763-8174)
- Zachary Shah
- Kawin Setsompop
- Bruno P. Soares
Institutions
- University Radiology (US)
- Stanford University (US)
Publication Details
- Journal
- Magnetic Resonance in Medicine
- Published
- 2026-02-22
- DOI
- https://doi.org/10.1002/mrm.70257
- Primary Topic
- Advanced MRI Techniques and Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00