What type of study is this?

This is a Experimental Study study.

September 17, 2025

Training Diffusion Probabilistic Models with Limited Data for Accelerated MRI Reconstruction with Application to Stroke MRI

Key Points

The proposed method reduces MRI scan time by 50%, improving speed for stroke diagnosis and treatment.
Improvements have been validated through numerical error metrics along with qualitative neurologist assessments.
A large foundation model was trained initially before fine-tuning on a smaller, specific dataset using a decayed learning rate.
This approach addresses critical needs in time-sensitive situations, offering a solution for accelerated MRI protocols.

Abstract

Motivation: Faster MRI reduces motion artifacts, costs, and time to treatment, crucial for stroke diagnosis; however, current protocols are lengthy, often making CT the preferred option. Goal(s): To accelerate the stroke MRI protocol using diffusion probabilistic models, reducing scan time by half. Approach: A foundation model is initially trained on a large public dataset, followed by fine-tuning on a smaller, contrast-specific dataset with a decayed learning rate and a short training period. Results: The proposed method applied to retrospective data supports a 50% reduction in scan time, with improvements validated through both numerical error metrics and a qualitative neurologist assessment. Impact: Training diffusion probabilistic models with limited data across various MRI contrasts holds substantial potential to accelerate diverse MRI protocols, addressing a critical unmet need in time-sensitive care scenarios, such as stroke diagnosis.

AI에게 질문

Bookmark