{"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/towards-adversarial-retinal-image-synthesis","title":"Towards Adversarial Retinal Image Synthesis","arxiv_id":"1701.08974","date":"2017-01-31","proceeding":null,"authors":["Pedro Costa","Adrian Galdran","Maria Inês Meyer","Michael David Abràmoff","Meindert Niemeijer","Ana Maria Mendonça","Aurélio Campilho"],"abstract":"Synthesizing images of the eye fundus is a challenging task that has been\npreviously approached by formulating complex models of the anatomy of the eye.\nNew images can then be generated by sampling a suitable parameter space. In\nthis work, we propose a method that learns to synthesize eye fundus images\ndirectly from data. For that, we pair true eye fundus images with their\nrespective vessel trees, by means of a vessel segmentation technique. These\npairs are then used to learn a mapping from a binary vessel tree to a new\nretinal image. For this purpose, we use a recent image-to-image translation\ntechnique, based on the idea of adversarial learning. Experimental results show\nthat the original and the generated images are visually different in terms of\ntheir global appearance, in spite of sharing the same vessel tree.\nAdditionally, a quantitative quality analysis of the synthetic retinal images\nconfirms that the produced images retain a high proportion of the true image\nset quality.","url_abs":"http://arxiv.org/abs/1701.08974v1","url_pdf":"http://arxiv.org/pdf/1701.08974v1.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":"towards-adversarial-retinal-image-synthesis","repo_url":"https://github.com/costapt/vess2ret","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"anatomy","task_name":"Anatomy"},{"task_slug":"image-generation","task_name":"Image Generation"},{"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":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1701.08974","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}