Generative Adversarial Networks in Medical Image augmentation: A review

• Published in: Computers in biology and medicine Vol. 144; p. 105382
• Main Authors: Chen, Yizhou, Yang, Xu-Hua, Wei, Zihan, Heidari, Ali Asghar, Zheng, Nenggan, Li, Zhicheng, Chen, Huiling, Hu, Haigen, Zhou, Qianwei, Guan, Qiu
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.05.2022; Elsevier Limited
• Subjects: Augmentation; Data augmentation; Datasets; Deep learning; Diagnosis; Generative adversarial networks; Image processing; Image Processing, Computer-Assisted - methods; Image synthesis; Internal Medicine; Machine learning; Medical diagnosis; Medical image; Medical imaging; Medical research; Methods; Neural Networks, Computer; Optimization; Organs; Other; Researchers; Reviews; Sample size; Statistical methods; Training; Augmentation; Deep learning; Medical image; Generative adversarial networks; Image synthesis
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2022.105382

With the development of deep learning, the number of training samples for medical image-based diagnosis and treatment models is increasing. Generative Adversarial Networks (GANs) have attracted attention in medical image processing due to their excellent image generation capabilities and have been widely used in data augmentation. In this paper, a comprehensive and systematic review and analysis of medical image augmentation work are carried out, and its research status and development prospects are reviewed. This paper reviews 105 medical image augmentation related papers, which mainly collected by ELSEVIER, IEEE Xplore, and Springer from 2018 to 2021. We counted these papers according to the parts of the organs corresponding to the images, and sorted out the medical image datasets that appeared in them, the loss function in model training, and the quantitative evaluation metrics of image augmentation. At the same time, we briefly introduce the literature collected in three journals and three conferences that have received attention in medical image processing. First, we summarize the advantages of various augmentation models, loss functions, and evaluation metrics. Researchers can use this information as a reference when designing augmentation tasks. Second, we explore the relationship between augmented models and the amount of the training set, and tease out the role that augmented models may play when the quality of the training set is limited. Third, the statistical number of papers shows that the development momentum of this research field remains strong. Furthermore, we discuss the existing limitations of this type of model and suggest possible research directions. We discuss GAN-based medical image augmentation work in detail. This method effectively alleviates the challenge of limited training samples for medical image diagnosis and treatment models. It is hoped that this review will benefit researchers interested in this field. •A systematic review on medical image augmentation based on GAN is provided.•A total of 105 papers are reviewed in groups, covering the beginning to the latest advances in the field.•The benchmark models, loss functions, and evaluation metrics are classified, counted, and analyzed.•Phenomena of interest to readers, challenges, and prospects of current methods are discussed.