ReBrain: Brain MRI Reconstruction from Sparse CT Slice via Retrieval-Augmented Diffusion

TL;DR

ReBrain introduces a retrieval-augmented diffusion framework that reconstructs brain MRI from sparse CT scans by synthesizing slices with guidance from similar retrieved slices, improving accuracy in challenging low-data scenarios.

Contribution

The paper presents a novel retrieval-augmented diffusion method for MRI reconstruction from sparse CT scans, integrating retrieval and interpolation to enhance structural fidelity.

Findings

ReBrain achieves state-of-the-art results on SynthRAD2023 and BraTS datasets.

The method effectively synthesizes MRI slices with structural consistency from limited CT data.

Incorporating retrieved slices significantly improves reconstruction quality in sparse conditions.

Abstract

Magnetic Resonance Imaging (MRI) plays a crucial role in brain disease diagnosis, but it is not always feasible for certain patients due to physical or clinical constraints. Recent studies attempt to synthesize MRI from Computed Tomography (CT) scans; however, low-dose protocols often result in highly sparse CT volumes with poor through-plane resolution, making accurate reconstruction of the full brain MRI volume particularly challenging. To address this, we propose ReBrain, a retrieval-augmented diffusion framework for brain MRI reconstruction. Given any 3D CT scan with limited slices, we first employ a Brownian Bridge Diffusion Model (BBDM) to synthesize MRI slices along the 2D dimension. Simultaneously, we retrieve structurally and pathologically similar CT slices from a comprehensive prior database via a fine-tuned retrieval model. These retrieved slices are used as references, incorporated through a ControlNet branch to guide the generation of intermediate MRI slices and ensure structural continuity. We further account for rare retrieval failures when the database lacks suitable references and apply spherical linear interpolation to provide supplementary guidance. Extensive experiments on SynthRAD2023 and BraTS demonstrate that ReBrain achieves state-of-the-art performance in cross-modal reconstruction under sparse conditions.