X-Diffusion: Generating Detailed 3D MRI Volumes From a Single Image Using Cross-Sectional Diffusion Models

TL;DR

X-Diffusion introduces a cross-sectional diffusion model that reconstructs detailed 3D MRI volumes from minimal 2D input slices, outperforming existing methods and generalizing across different body parts, thereby potentially reducing MRI scan times and costs.

Contribution

It is the first approach to generate detailed 3D MRI volumes from extremely sparse 2D slices using a holistic cross-sectional diffusion model.

Findings

Surpasses state-of-the-art in PSNR accuracy on unseen data.

Preserves critical anatomical features such as tumors and brain structures.

Successfully generalizes to knee MRIs despite training only on brain data.

Abstract

Magnetic Resonance Imaging (MRI) is a crucial diagnostic tool, but high-resolution scans are often slow and expensive due to extensive data acquisition requirements. Traditional MRI reconstruction methods aim to expedite this process by filling in missing frequency components in the K-space, performing 3D-to-3D reconstructions that demand full 3D scans. In contrast, we introduce X-Diffusion, a novel cross-sectional diffusion model that reconstructs detailed 3D MRI volumes from extremely sparse spatial-domain inputs, achieving 2D-to-3D reconstruction from as little as a single 2D MRI slice or few slices. A key aspect of X-Diffusion is that it models MRI data as holistic 3D volumes during the cross-sectional training and inference, unlike previous learning approaches that treat MRI scans as collections of 2D slices in standard planes (coronal, axial, sagittal). We evaluated X-Diffusion on brain tumor MRIs from the BRATS dataset and full-body MRIs from the UK Biobank dataset. Our results demonstrate that X-Diffusion not only surpasses state-of-the-art methods in quantitative accuracy (PSNR) on unseen data but also preserves critical anatomical features such as tumor profiles, spine curvature, and brain volume. Remarkably, the model generalizes beyond the training domain, successfully reconstructing knee MRIs despite being trained exclusively on brain data. Medical expert evaluations further confirm the clinical relevance and fidelity of the generated images. To our knowledge, X-Diffusion is the first method capable of producing detailed 3D MRIs from highly limited 2D input data, potentially accelerating MRI acquisition and reducing associated costs. The code is available on the project website https://emmanuelleb985.github.io/XDiffusion/ .