Anatomy-Preserving Latent Diffusion for Generation of Brain Segmentation Masks with Ischemic Infarct
This addresses a bottleneck for medical image analysis in data-scarce scenarios, particularly for neuroimaging, but is incremental as it builds on existing generative methods.
The authors tackled the scarcity of high-quality segmentation masks in non-contrast CT neuroimaging by proposing an anatomy-preserving generative framework for unconditional synthesis of multi-class brain segmentation masks, including ischemic infarcts, resulting in generated masks that preserve global brain anatomy and realistic variability while avoiding structural artifacts.
The scarcity of high-quality segmentation masks remains a major bottleneck for medical image analysis, particularly in non-contrast CT (NCCT) neuroimaging, where manual annotation is costly and variable. To address this limitation, we propose an anatomy-preserving generative framework for the unconditional synthesis of multi-class brain segmentation masks, including ischemic infarcts. The proposed approach combines a variational autoencoder trained exclusively on segmentation masks to learn an anatomical latent representation, with a diffusion model operating in this latent space to generate new samples from pure noise. At inference, synthetic masks are obtained by decoding denoised latent vectors through the frozen VAE decoder, with optional coarse control over lesion presence via a binary prompt. Qualitative results show that the generated masks preserve global brain anatomy, discrete tissue semantics, and realistic variability, while avoiding the structural artifacts commonly observed in pixel-space generative models. Overall, the proposed framework offers a simple and scalable solution for anatomy-aware mask generation in data-scarce medical imaging scenarios.