{"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-network-for-medical","title":"Generative Adversarial Network for Medical Images (MI-GAN)","arxiv_id":"1810.00551","date":"2018-10-01","proceeding":null,"authors":["Talha Iqbal","Hazrat Ali"],"abstract":"Deep learning algorithms produces state-of-the-art results for different\nmachine learning and computer vision tasks. To perform well on a given task,\nthese algorithms require large dataset for training. However, deep learning\nalgorithms lack generalization and suffer from over-fitting whenever trained on\nsmall dataset, especially when one is dealing with medical images. For\nsupervised image analysis in medical imaging, having image data along with\ntheir corresponding annotated ground-truths is costly as well as time consuming\nsince annotations of the data is done by medical experts manually. In this\npaper, we propose a new Generative Adversarial Network for Medical Imaging\n(MI-GAN). The MI-GAN generates synthetic medical images and their segmented\nmasks, which can then be used for the application of supervised analysis of\nmedical images. Particularly, we present MI-GAN for synthesis of retinal\nimages. The proposed method generates precise segmented images better than the\nexisting techniques. The proposed model achieves a dice coefficient of 0.837 on\nSTARE dataset and 0.832 on DRIVE dataset which is state-of-the-art performance\non both the datasets.","url_abs":"http://arxiv.org/abs/1810.00551v1","url_pdf":"http://arxiv.org/pdf/1810.00551v1.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-network-for-medical","repo_url":"https://github.com/hazratali/MI-GAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":null,"task_name":"Generative Adversarial Network"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1810.00551","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}