Generative Adversarial Network in Medical Imaging: A Review

By Xin Yi, Ekta Walia, Paul S. Babyn. 2018

1,691 citations recorded by the source corpus.

Generative adversarial networks have gained a lot of attention in the computer vision community due to their capability of data generation without explicitly modelling the probability density function. The adversarial loss brought by the discriminator provides a clever way of incorporating unlabeled samples into training and imposing higher order consistency. This has proven to be useful in many cases, such as domain adaptation, data augmentation, and image-to-image translation. These properties have attracted researchers in the medical imaging community, and we have seen rapid adoption in many traditional and novel applications, such as image reconstruction, segmentation, detection, classification, and cross-modality synthesis. Based on our observations, this trend will continue and we therefore conducted a review of recent advances in medical imaging using the adversarial training scheme with the hope of benefiting researchers interested in this technique.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Generative Models

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Generative Models

Citations in the corpus

Training Generative Adversarial Networks with Limited Data (2020, background): “This curbs the increasing use of generative models in fields such as medicine [47].”
GAN Inversion: A Survey (2021, background): “GAN inversion techniques have been recently introduced to medical applications [157].”
Black-Box vs. White-Box: Understanding Their Advantages and Weaknesses From a Practical Point of View (2019, background): “It is important to highlight that ANN-based models (CNN and GANs families) are the most difficult to understand by both machine learning experts and specialist in the application area due to the several transformations made to the input data.”
Medical image data augmentation: techniques, comparisons and interpretations (2023, background): “A significant problem is vanishing gradient and mode collapsing (Yi et al. 2019).”
Artificial Intelligence and COVID-19: Deep Learning Approaches for Diagnosis and Treatment (2020, background): “GANs are of two different users in medical imaging [56].”
On Leveraging Pretrained GANs for Limited-Data Generation (2020, background): “Motivated by the significant value of released pretrained GAN models, we propose to leverage the valuable information therein to facilitate downstream tasks with limited target data, which arise frequently due to expensive data collection in target domain or privacy regulations like in medical or bi”
Recent advances and clinical applications of deep learning in medical image analysis (2021, background): “Interested readers can refer to the paper (Yi et al., 2019) for a detailed review of architecture changes.”
Hi-Net: Hybrid-Fusion Network for Multi-Modal MR Image Synthesis (2020, neutral): “In addition, GAN-based methods have also achieved promising results in synthesizing various types of medical images, such as CT images [15], retinal images [34], [35], MR images [19], ultrasound images [36], [37] and so on.”
On Leveraging Pretrained GANs for Generation with Limited Data (2020, background): “, 2019a)), this generalization of GANs is extremely appealing for scenarios in which there are limited data (Yi et al., 2019; Han et al., 2019).”
All One Needs to Know about Metaverse: A Complete Survey on Technological Singularity, Virtual Ecosystem, and Research Agenda (2021, background): “art deep learning model in learning the distribution of training samples and generate data following the same distribution [270].”
Synthetic Data for Deep Learning (2019, methodology): “GANs have been widely applied to generating realistic medical images [40, 46,326,423,666,673].”
GAN-Leaks: A Taxonomy of Membership Inference Attacks against Generative Models (2019, background): “For instance, GANs have been applied to health record data and medical images [12, 19, 69] whose membership is sensitive as it may reveal a patient’s disease history.”
U-Net and Its Variants for Medical Image Segmentation: A Review of Theory and Applications (2020, background): “GAN, in particular, has seen tremendous success in synthesizing medical images [375].”