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

2026-03-13

AI Summary

This study addresses the challenge of accelerated MRI reconstruction in clinical stroke imaging, where high-quality fully sampled data in the target domain are scarce. To overcome this limitation, the authors introduce, for the first time, a foundation model paradigm into diffusion-based MRI reconstruction. They first pretrain a diffusion probabilistic model on large-scale public brain MRI datasets and then fine-tune it on an extremely limited target dataset—only 20 stroke FLAIR cases. This approach substantially reduces reliance on target-domain data while achieving high reconstruction fidelity. At a 2× acceleration rate, reconstructed images were rated by two blinded neuroradiologists as non-inferior in quality to standard clinical images. Moreover, across multiple acceleration factors, the method matches the performance of models trained on substantially larger amounts of task-specific data.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Deep Neural Architectures and Foundation Models
• Cognitive Modeling & Cognitive Systems: Other Foundations of Cognitive Modeling & Systems

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• Web Mining and Content Analysis: Large pretrained models with web data
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

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 $2 \times$ 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.

Problem

• accelerated MRI
• stroke MRI
• data-efficient reconstruction
• limited fully-sampled data
• clinical imaging

Innovation

• Diffusion Probabilistic Models
• MRI acceleration
• foundation model
• target-specific fine-tuning
• stroke imaging