Lesion-DDPM: Lesion-Enhanced 3D Diffusion for MS MRI Synthesis
For researchers developing robust neuroimaging models for multiple sclerosis, this method addresses the scarcity of diverse, lesion-rich MRI data by generating high-quality synthetic scans that improve downstream segmentation performance.
Lesion-DDPM, a 3D conditional diffusion framework with lesion-weighted loss and multi-level mask injection, improves FLAIR MRI synthesis for multiple sclerosis, achieving a downstream segmentation Dice score of 0.616 (vs. 0.569 for best competitor) and 0.685 when combined with real data.
3D FLAIR MRI is widely recommended as one of the standard MRI sequences for brain imaging in multiple sclerosis (MS), but publicly available MS datasets remain relatively small and vary across scanners, acquisition protocols, and lesion patterns. This scarcity and variability hinder the development of robust neuroimaging machine learning models and are particularly challenging for generative models that aim to synthesize images while preserving small, sparse lesions. We propose Lesion-DDPM, a 3D conditional diffusion framework for lesion-aware FLAIR synthesis that incorporates multi-level anatomical mask injection together with a lesion-weighted reconstruction loss to emphasize lesion voxels while maintaining global brain structure. Using a curated subset of the MSLesSeg dataset, we compare Lesion-DDPM with representative state-of-the-art GAN- and diffusion-based models, assessing both image-generation metrics and downstream 3D U-Net segmentation. In our experiments, Lesion-DDPM achieved the lowest lesion-region reconstruction error among all methods. In a downstream 3D U-Net lesion segmentation task, a model trained only on Lesion-DDPM-generated scans and evaluated on real MRIs reached a Dice score of 0.616 compared with 0.569 for the best competing synthetic dataset. When Lesion-DDPM images were added to the real training set, the Dice score further increased to 0.685.