GAN based ROI conditioned synthesis of medical image for data augmentation

Abstract

Synthetic data is considered to be a promising solution for data privacy and scarcity. Some studies have shown that synthetic data generated from a simple GAN-based model enables privacy-preserving data sharing and data augmentation also in the medical imaging field. However, there are some limitations in applying this approach to real world situations: 1) Since generative models needs large amount of data to be trained, it is hard to be applied for small data situation. 2) Even after successfully training generative models, it is hard to guarantee which class the synthesized data corresponds to, especially for non-conditional generative models, so it needs to be re-labeled. Here, we propose GAN based ROI conditioned synthesis of medical Image for data augmentation. We used StyleGAN2 to learn the distribution of CXR and Bayesian image reconstruction for ROI-conditioned synthesis from the distribution. In the 4-class classification of CXRs showing normal, pneumonia, pleural effusion, and pneumothorax, using synthetic data for data sharing showed comparable performance to centralized learning, slightly better in terms of AUROC. Also, using synthetic data for augmentation, the accuracy and AUROC showed up to 6.5% and 8.9% increases, respectively.

Automated Region of Interest-Based Data Augmentation for Fallen Person Detection in Off-Road Autonomous Agricultural Vehicles

“…Unlike the previous AutoAug, RandAug proposes a more competitive technique through parameterization without a separate data augmentation policy. On the other hand, research on synthetic images using GAN and the diffusion model has also been conducted [36][37][38][39][40][41][42][43]. Especially, the diffusion model, a probabilistic generative model that generates and restores noise during training to create images, is recently used for image generation because it is well known that the synthetic qualities of diffusion models are much better than those of GAN [44].…”