• Rohit Ashok Palve
• Mayuresh Krishna Ghodke

The technique of estimating one picture (sequence, modality) from another image (sequence, modality) in medical imaging is known as image synthesis. Multi-modality imaging is essential in medicine since it captures distinct aspects and offers a variety of biomarkers. Although multi-screening is costly and time-consuming to report to radiologists, missing modalities can be artificially generated using image synthesis techniques. High dimensional characteristics may be automatically extracted and captured by deep learning algorithms. In particular, one of the most well-liked generative-based deep learning techniques is the generative adversarial network (GAN), which classifies estimated pictures as true or false using a discriminator network and convolutional networks as generators. This review presents GAN-based brain image synthesis. The most current advancements in GANs for cross-modality brain image synthesis—from CT to PET, from MRI to PET, and vice versa—were compiled here.

Generative Adversarial Networks, Image Synthesis, CT, MRI, PET

"GENERATIVE ADVERSAIRAL NETWORKS FOR BRAIN IMAGE SYNTHESIS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 12, page no.f325-f337, December-2023, Available :http://www.jetir.org/papers/JETIR2312537.pdf

"GENERATIVE ADVERSAIRAL NETWORKS FOR BRAIN IMAGE SYNTHESIS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 12, page no. ppf325-f337, December-2023, Available at : http://www.jetir.org/papers/JETIR2312537.pdf