Towards 3D Semantic Image Synthesis for Medical Imaging
This addresses data scarcity and privacy issues in medical imaging for researchers and practitioners, though it is incremental as it adapts existing diffusion models to the 3D domain.
The study tackled the challenge of limited and private medical data by proposing Med-LSDM, a 3D semantic image synthesis model that generates synthetic data, achieving a 3D-FID score of 0.0054 and Dice scores close to real images (0.70964 vs. 0.71496).
In the medical domain, acquiring large datasets is challenging due to both accessibility issues and stringent privacy regulations. Consequently, data availability and privacy protection are major obstacles to applying machine learning in medical imaging. To address this, our study proposes the Med-LSDM (Latent Semantic Diffusion Model), which operates directly in the 3D domain and leverages de-identified semantic maps to generate synthetic data as a method of privacy preservation and data augmentation. Unlike many existing methods that focus on generating 2D slices, Med-LSDM is designed specifically for 3D semantic image synthesis, making it well-suited for applications requiring full volumetric data. Med-LSDM incorporates a guiding mechanism that controls the 3D image generation process by applying a diffusion model within the latent space of a pre-trained VQ-GAN. By operating in the compressed latent space, the model significantly reduces computational complexity while still preserving critical 3D spatial details. Our approach demonstrates strong performance in 3D semantic medical image synthesis, achieving a 3D-FID score of 0.0054 on the conditional Duke Breast dataset and similar Dice scores (0.70964) to those of real images (0.71496). These results demonstrate that the synthetic data from our model have a small domain gap with real data and are useful for data augmentation.