Unpaired Volumetric Harmonization of Brain MRI with Conditional Latent Diffusion

TL;DR

This paper introduces a novel 3D MRI harmonization method using conditional latent diffusion, enabling effective volume-level correction of site-related variations in brain MRI without paired data, improving multi-site neuroimaging analysis.

Contribution

It presents a new 3D autoencoder and conditional latent diffusion framework for MRI harmonization that considers volumetric and anatomical information, outperforming existing methods.

Findings

HCLD effectively removes site-related variations.

It preserves biological features better than prior methods.

Demonstrated on 4,158 brain MRIs across multiple datasets.

Abstract

Multi-site structural MRI is increasingly used in neuroimaging studies to diversify subject cohorts. However, combining MR images acquired from various sites/centers may introduce site-related non-biological variations. Retrospective image harmonization helps address this issue, but current methods usually perform harmonization on pre-extracted hand-crafted radiomic features, limiting downstream applicability. Several image-level approaches focus on 2D slices, disregarding inherent volumetric information, leading to suboptimal outcomes. To this end, we propose a novel 3D MRI Harmonization framework through Conditional Latent Diffusion (HCLD) by explicitly considering image style and brain anatomy. It comprises a generalizable 3D autoencoder that encodes and decodes MRIs through a 4D latent space, and a conditional latent diffusion model that learns the latent distribution and generates harmonized MRIs with anatomical information from source MRIs while conditioned on target image style. This enables efficient volume-level MRI harmonization through latent style translation, without requiring paired images from target and source domains during training. The HCLD is trained and evaluated on 4,158 T1-weighted brain MRIs from three datasets in three tasks, assessing its ability to remove site-related variations while retaining essential biological features. Qualitative and quantitative experiments suggest the effectiveness of HCLD over several state-of-the-arts