mlsanityData to 7 Oct 2026

Accelerating Stroke MRI with Diffusion Probabilistic Models through Large-Scale Pre-training and Target-Specific Fine-Tuning

arXiv 2603.13007 ↗First posted 13 Mar 2026eess.IV cs.CV cs.LGcited by 0

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

Purpose: To develop a data-efficient strategy for accelerated MRI reconstruction with Diffusion Probabilistic Generative Models (DPMs) that enables faster scan times in clinical stroke MRI when only limited fully-sampled data samples are available. Methods: Our simple training strategy, inspired by the foundation model paradigm, first trains a DPM on a large, diverse collection of publicly available brain MRI data in fastMRI and then fine-tunes on a small dataset from the target application using carefully selected learning rates and fine-tuning durations. The approach is evaluated on controlled fastMRI experiments and on clinical stroke MRI data with a blinded clinical reader study. Results: DPMs pre-trained on approximately 4000 subjects with non-FLAIR contrasts and fine-tuned on FLAIR data from only 20 target subjects achieve reconstruction performance comparable to models trained with substantially more target-domain FLAIR data across multiple acceleration factors. Experiments reveal that moderate fine-tuning with a reduced learning rate yields improved performance, while insufficient or excessive fine-tuning degrades reconstruction quality. When applied to clinical stroke MRI, a blinded reader study involving two neuroradiologists indicates that images reconstructed using the proposed approach from 2 × accelerated data are non-inferior to standard-of-care in terms of image quality and structural delineation. Conclusion: Large-scale pre-training combined with targeted fine-tuning enables DPM-based MRI reconstruction in data-constrained, accelerated clinical stroke MRI. The proposed approach substantially reduces the need for large application-specific datasets while maintaining clinically acceptable image quality, supporting the use of foundation-inspired diffusion models for accelerated MRI in targeted applications.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 36 of its 58 references that are in the map. First posted on arXiv 13 Mar 2026.

Builds on

36 of 58 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025Diffusion Probabilistic Generative Models for Accelerated, in-NICU Permanent Magnet Neonatal MRI21 May
  2. 2023Steerable Conditional Diffusion for Out-of-Distribution Adaptation in Medical Image Reconstruction28 Aug
  3. 2023Self-Supervised MRI Reconstruction with Unrolled Diffusion Models29 Jun
  4. 2022Adaptive Diffusion Priors for Accelerated MRI Reconstruction12 Jul
  5. 2022Bayesian MRI Reconstruction with Joint Uncertainty Estimation using Diffusion Models3 Feb
  6. 2021Score-based diffusion models for accelerated MRI8 Oct

Other references · 30

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  5. 2023Segment Anythingcited by 8,158
  6. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  7. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  8. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
  9. 2023A Survey of Large Language Modelscited by 2,537
  10. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,375
  11. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,107
  12. 2021Robust Compressed Sensing MRI with Deep Generative Priorscited by 284
18 more
  1. 2023Concept Sliders: LoRA Adaptors for Precise Control in Diffusion Modelscited by 148
  2. 2024Reuse, Don't Retrain: A Recipe for Continued Pretraining of Language Modelscited by 69
  3. 2025InverseBench: Benchmarking Plug-and-Play Diffusion Priors for Inverse Problems in Physical Sciencescited by 67
  4. 2021Zero-Shot Self-Supervised Learning for MRI Reconstructioncited by 53
  5. 2025Overcoming catastrophic forgetting in neural networkscited by 52
  6. 2022Physics-Driven Deep Learning for Computational Magnetic Resonance Imagingcited by 49
  7. 2022SKM-TEA: A Dataset for Accelerated MRI Reconstruction with Dense Image Labels for Quantitative Clinical Evaluationcited by 42
  8. 2017MR image reconstruction using deep density priorscited by 37
  9. 2022Test-Time Training Can Close the Natural Distribution Shift Performance Gap in Deep Learning Based Compressed Sensingcited by 37
  10. 2022A theoretical framework for self-supervised MR image reconstruction using sub-sampling via variable density Noisier2Noisecited by 29
  11. 2019MRI Reconstruction Using Deep Bayesian Estimationcited by 28
  12. 2023IMJENSE: Scan-specific Implicit Representation for Joint Coil Sensitivity and Image Estimation in Parallel MRIcited by 22
  13. 2024Deep Diffusion Image Prior for Efficient OOD Adaptation in 3D Inverse Problemscited by 21
  14. 2023Robustness of Deep Learning for Accelerated MRI: Benefits of Diverse Training Datacited by 10
  15. 2025PISCO: Self-Supervised k-Space Regularization for Improved Neural Implicit k-Space Representations of Dynamic MRIcited by 4
  16. 2025Benchmarking Self-Supervised Learning Methods for Accelerated MRI Reconstructioncited by 4
  17. 2025On the Utility of Foundation Models for Fast MRI: Vision-Language-Guided Image Reconstructioncited by 3
  18. 2025Self-supervised feature learning for cardiac Cine MR image reconstructioncited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Lesion-Aware Post-Training of Latent Diffusion Models for Synthesizing Diffusion MRI from CT Perfusion
  2. 2024Accelerating MRI with Longitudinally-informed Latent Posterior Sampling
  3. 2023A Survey of Emerging Applications of Diffusion Probabilistic Models in MRI
  4. 2025Dual-domain Multi-path Self-supervised Diffusion Model for Accelerated MRI Reconstruction
  5. 2023Optimizing Sampling Patterns for Compressed Sensing MRI with Diffusion Generative Models
  6. 2023Learning Fourier-Constrained Diffusion Bridges for MRI Reconstruction
  7. 2025Patch-Based Diffusion for Data-Efficient, Radiologist-Preferred MRI Reconstruction
  8. 2024Fast-DDPM: Fast Denoising Diffusion Probabilistic Models for Medical Image-to-Image Generation