Unpaired Volumetric Harmonization of Brain MRI with Conditional Latent Diffusion
This addresses the challenge of combining multi-site MRI data for neuroimaging studies, which is crucial for diversifying cohorts but often hindered by site-related artifacts, representing an incremental improvement over existing 2D or feature-based methods.
The paper tackles the problem of harmonizing brain MRI images from multiple sites to remove non-biological variations, proposing a 3D conditional latent diffusion framework that achieves effective harmonization without requiring paired training data, as demonstrated on 4,158 T1-weighted MRIs across three datasets.
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