Active MRI Acquisition with Diffusion Guided Bayesian Experimental Design

2025-06-19

AI Summary

To address the challenge of jointly optimizing image reconstruction quality and downstream task performance in clinical MRI acceleration, this paper proposes a diffusion-model-guided active Bayesian experimental design framework. We introduce, for the first time, a diffusion-based generative prior into the Bayesian inference framework, enabling differentiable, constraint-aware, k-space sampling optimization directly in high-dimensional image space. The method supports end-to-end, task-driven sampling strategy learning—e.g., optimized explicitly for lesion segmentation. Evaluated on multi-sequence MRI datasets, our approach achieves substantial improvements at low acceleration factors: +3.2 dB PSNR in reconstruction quality and +5.7% Dice score in segmentation accuracy, while reducing scan time by over 30%. This work establishes a novel paradigm for task-oriented, intelligent MRI acquisition acceleration.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition
• Machine Learning: Active Learning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Web Mining and Content Analysis: Content-based information diffusion

Abstract

A key challenge in maximizing the benefits of Magnetic Resonance Imaging (MRI) in clinical settings is to accelerate acquisition times without significantly degrading image quality. This objective requires a balance between under-sampling the raw k-space measurements for faster acquisitions and gathering sufficient raw information for high-fidelity image reconstruction and analysis tasks. To achieve this balance, we propose to use sequential Bayesian experimental design (BED) to provide an adaptive and task-dependent selection of the most informative measurements. Measurements are sequentially augmented with new samples selected to maximize information gain on a posterior distribution over target images. Selection is performed via a gradient-based optimization of a design parameter that defines a subsampling pattern. In this work, we introduce a new active BED procedure that leverages diffusion-based generative models to handle the high dimensionality of the images and employs stochastic optimization to select among a variety of patterns while meeting the acquisition process constraints and budget. So doing, we show how our setting can optimize, not only standard image reconstruction, but also any associated image analysis task. The versatility and performance of our approach are demonstrated on several MRI acquisitions.

Problem

• Accelerate MRI acquisition without losing image quality
• Balance under-sampling and high-fidelity image reconstruction
• Optimize image reconstruction and analysis tasks adaptively

Innovation

• Sequential Bayesian experimental design for adaptive sampling
• Diffusion-based generative models handle high-dimensional images
• Gradient-based optimization for informative measurement selection