Generative Adversarial Networks for Brain Images Synthesis: A Review
It addresses the high cost and time of multi-modality medical imaging for radiologists, but is incremental as a review paper.
This review tackles the problem of synthesizing missing brain imaging modalities (e.g., CT to MRI) using generative adversarial networks (GANs), summarizing recent developments in cross-modality synthesis to reduce the need for expensive multi-screening.
In medical imaging, image synthesis is the estimation process of one image (sequence, modality) from another image (sequence, modality). Since images with different modalities provide diverse biomarkers and capture various features, multi-modality imaging is crucial in medicine. While multi-screening is expensive, costly, and time-consuming to report by radiologists, image synthesis methods are capable of artificially generating missing modalities. Deep learning models can automatically capture and extract the high dimensional features. Especially, generative adversarial network (GAN) as one of the most popular generative-based deep learning methods, uses convolutional networks as generators, and estimated images are discriminated as true or false based on a discriminator network. This review provides brain image synthesis via GANs. We summarized the recent developments of GANs for cross-modality brain image synthesis including CT to PET, CT to MRI, MRI to PET, and vice versa.