Active MRI Acquisition with Diffusion Guided Bayesian Experimental Design

TL;DR

This paper introduces a novel active MRI acquisition method using diffusion-guided Bayesian experimental design to adaptively select measurements, significantly improving acquisition efficiency while maintaining image quality for various analysis tasks.

Contribution

It presents a new active Bayesian experimental design framework leveraging diffusion models for adaptive, task-dependent MRI measurement selection, handling high-dimensional images effectively.

Findings

Improved MRI acquisition speed without sacrificing image quality.

Versatile approach applicable to multiple image analysis tasks.

Demonstrated effectiveness on several MRI datasets.

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.