Pseudo-healthy synthesis with pathology disentanglement and adversarial learning
Medical Image Analysis(2020)
摘要
•Pseudo healthy synthesis with adversarial training and pathology disentanglement.•Method can be trained without pairs of image and pathology segmentations.•Numerical metrics to evaluate the quality of synthetic ’healthy’ images.•Extensive experiments including an expert observational study.
更多查看译文
关键词
Pseudo-healthy synthesis,Generative adversarial networks,Pathology disentanglement
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络