cyclegan-abnormal2normal

Accurate detection and segmentation of brain tumors is critical for medical diagnosis. We propose a novel framework Two-Stage Generative Model (TSGM) that combines Cycle Generative Adversarial Network (CycleGAN) and Variance Exploding stochastic differential equation using joint probability (VE-JP) to improve brain tumor segmentation. TSGM was trained on the BraTs2020 brain tumor dataset. The CycleGAN is trained on unpaired data to generate abnormal images from healthy images. Then VE-JP is implemented to reconstruct healthy images using synthetic paired abnormal images as a guide, which alters only pathological regions but not regions of healthy. We validated the proposed TSGM method on three datasets, and compared with other unsupervised methods for anomaly detection and segmentation. The results show that our method achieves better segmentation performance and has better generalization.