On Differentially Private 3D Medical Image Synthesis with Controllable Latent Diffusion Models
It addresses privacy concerns for medical imaging datasets to advance deep learning models, but it is incremental as it applies known methods to a new domain.
This study tackled the problem of generating synthetic 3D cardiac MRI images while ensuring patient privacy through differentially private training, achieving a Fréchet Inception Distance (FID) of 26.77 at ε=10 with pre-training compared to 92.52 without.
Generally, the small size of public medical imaging datasets coupled with stringent privacy concerns, hampers the advancement of data-hungry deep learning models in medical imaging. This study addresses these challenges for 3D cardiac MRI images in the short-axis view. We propose Latent Diffusion Models that generate synthetic images conditioned on medical attributes, while ensuring patient privacy through differentially private model training. To our knowledge, this is the first work to apply and quantify differential privacy in 3D medical image generation. We pre-train our models on public data and finetune them with differential privacy on the UK Biobank dataset. Our experiments reveal that pre-training significantly improves model performance, achieving a Fréchet Inception Distance (FID) of 26.77 at $ε=10$, compared to 92.52 for models without pre-training. Additionally, we explore the trade-off between privacy constraints and image quality, investigating how tighter privacy budgets affect output controllability and may lead to degraded performance. Our results demonstrate that proper consideration during training with differential privacy can substantially improve the quality of synthetic cardiac MRI images, but there are still notable challenges in achieving consistent medical realism.