{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/generative-adversarial-networks-for-image-to","title":"Generative Adversarial Networks for Image-to-Image Translation on Multi-Contrast MR Images - A Comparison of CycleGAN and UNIT","arxiv_id":"1806.07777","date":"2018-06-20","proceeding":null,"authors":["Per Welander","Simon Karlsson","Anders Eklund"],"abstract":"In medical imaging, a general problem is that it is costly and time consuming\nto collect high quality data from healthy and diseased subjects. Generative\nadversarial networks (GANs) is a deep learning method that has been developed\nfor synthesizing data. GANs can thereby be used to generate more realistic\ntraining data, to improve classification performance of machine learning\nalgorithms. Another application of GANs is image-to-image translations, e.g.\ngenerating magnetic resonance (MR) images from computed tomography (CT) images,\nwhich can be used to obtain multimodal datasets from a single modality. Here,\nwe evaluate two unsupervised GAN models (CycleGAN and UNIT) for image-to-image\ntranslation of T1- and T2-weighted MR images, by comparing generated synthetic\nMR images to ground truth images. We also evaluate two supervised models; a\nmodification of CycleGAN and a pure generator model. A small perceptual study\nwas also performed to evaluate how visually realistic the synthesized images\nare. It is shown that the implemented GAN models can synthesize visually\nrealistic MR images (incorrectly labeled as real by a human). It is also shown\nthat models producing more visually realistic synthetic images not necessarily\nhave better quantitative error measurements, when compared to ground truth\ndata. Code is available at https://github.com/simontomaskarlsson/GAN-MRI","url_abs":"http://arxiv.org/abs/1806.07777v1","url_pdf":"http://arxiv.org/pdf/1806.07777v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"generative-adversarial-networks-for-image-to","repo_url":"https://github.com/simontomaskarlsson/GAN-MRI","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"generative-adversarial-networks-for-image-to","repo_url":"https://github.com/Siddhartha24795/Medical-Image-Synthesis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"generative-adversarial-networks-for-image-to","repo_url":"https://github.com/pgdelbosque/GAN-MRI","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"computed-tomography-ct","task_name":"Computed Tomography (CT)"},{"task_slug":"image-to-image-translation","task_name":"Image-to-Image Translation"},{"task_slug":"medical-image-generation","task_name":"Medical Image Generation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"cycle-consistency-loss","method_name":"Cycle Consistency Loss"},{"method_slug":"gan-least-squares-loss","method_name":"GAN Least Squares Loss"},{"method_slug":"instance-normalization","method_name":"Instance Normalization"},{"method_slug":"patchgan","method_name":"PatchGAN"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.07777","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}