Generative Adversarial Network for Image Synthesis
arXiv:2012.15446
Abstract
This chapter reviews recent developments of generative adversarial networks (GAN)-based methods for medical and biomedical image synthesis tasks. These methods are classified into conditional GAN and Cycle-GAN according to the network architecture designs. For each category, a literature survey is given, which covers discussions of the network architecture designs, highlights important contributions and identifies specific challenges.
References in corpus (6)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Deep Learning in Medical Image Registration: A Review
- Unsupervised Image-to-Image Translation Networks
- Generating Semi-Synthetic Validation Benchmarks for Embryomics
- Deep Learning in Multi-organ Segmentation
- Synthetic MRI-aided Head-and-Neck Organs-at-Risk Auto-Delineation for CBCT-guided Adaptive Radiotherapy