{"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/synthesizing-new-retinal-symptom-images-by","title":"Synthesizing New Retinal Symptom Images by Multiple Generative Models","arxiv_id":"1902.04147","date":"2019-02-11","proceeding":null,"authors":["Yi-Chieh Liu","Hao-Hsiang Yang","Chao-Han Huck Yang","Jia-Hong Huang","Meng Tian","Hiromasa Morikawa","Yi-Chang James Tsai","Jesper Tegner"],"abstract":"Age-Related Macular Degeneration (AMD) is an asymptomatic retinal disease\nwhich may result in loss of vision. There is limited access to high-quality\nrelevant retinal images and poor understanding of the features defining\nsub-classes of this disease. Motivated by recent advances in machine learning\nwe specifically explore the potential of generative modeling, using Generative\nAdversarial Networks (GANs) and style transferring, to facilitate clinical\ndiagnosis and disease understanding by feature extraction. We design an\nanalytic pipeline which first generates synthetic retinal images from clinical\nimages; a subsequent verification step is applied. In the synthesizing step we\nmerge GANs (DCGANs and WGANs architectures) and style transferring for the\nimage generation, whereas the verified step controls the accuracy of the\ngenerated images. We find that the generated images contain sufficient\npathological details to facilitate ophthalmologists' task of disease\nclassification and in discovery of disease relevant features. In particular,\nour system predicts the drusen and geographic atrophy sub-classes of AMD.\nFurthermore, the performance using CFP images for GANs outperforms the\nclassification based on using only the original clinical dataset. Our results\nare evaluated using existing classifier of retinal diseases and class activated\nmaps, supporting the predictive power of the synthetic images and their utility\nfor feature extraction. Our code examples are available online.","url_abs":"http://arxiv.org/abs/1902.04147v1","url_pdf":"http://arxiv.org/pdf/1902.04147v1.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":"synthesizing-new-retinal-symptom-images-by","repo_url":"https://github.com/huckiyang/EyeNet-GANs","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}