RadImageGAN -- A Multi-modal Dataset-Scale Generative AI for Medical Imaging
This work addresses data scarcity and annotation costs in medical imaging for researchers and practitioners, though it is incremental as it builds on existing generative models like StyleGAN-XL and BigDatasetGAN.
The authors tackled the problem of data scarcity in medical imaging by introducing RadImageGAN, a multi-modal generative model trained on a real dataset of 102,774 patients, which can generate synthetic images across 12 anatomical regions and 130 pathological classes in 3 modalities, and demonstrated that using this synthetic data significantly improves performance on four downstream segmentation datasets.
Deep learning in medical imaging often requires large-scale, high-quality data or initiation with suitably pre-trained weights. However, medical datasets are limited by data availability, domain-specific knowledge, and privacy concerns, and the creation of large and diverse radiologic databases like RadImageNet is highly resource-intensive. To address these limitations, we introduce RadImageGAN, the first multi-modal radiologic data generator, which was developed by training StyleGAN-XL on the real RadImageNet dataset of 102,774 patients. RadImageGAN can generate high-resolution synthetic medical imaging datasets across 12 anatomical regions and 130 pathological classes in 3 modalities. Furthermore, we demonstrate that RadImageGAN generators can be utilized with BigDatasetGAN to generate multi-class pixel-wise annotated paired synthetic images and masks for diverse downstream segmentation tasks with minimal manual annotation. We showed that using synthetic auto-labeled data from RadImageGAN can significantly improve performance on four diverse downstream segmentation datasets by augmenting real training data and/or developing pre-trained weights for fine-tuning. This shows that RadImageGAN combined with BigDatasetGAN can improve model performance and address data scarcity while reducing the resources needed for annotations for segmentation tasks.