{"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/deep-learning-based-early-detection-and","title":"Deep Learning based Early Detection and Grading of Diabetic Retinopathy Using Retinal Fundus Images","arxiv_id":"1812.10595","date":"2018-12-27","proceeding":null,"authors":["Sheikh Muhammad Saiful Islam","Md Mahedi Hasan","Sohaib Abdullah"],"abstract":"Diabetic Retinopathy (DR) is a constantly deteriorating disease, being one of\nthe leading causes of vision impairment and blindness. Subtle distinction among\ndifferent grades and existence of many significant small features make the task\nof recognition very challenging. In addition, the present approach of\nretinopathy detection is a very laborious and time-intensive task, which\nheavily relies on the skill of a physician. Automated detection of diabetic\nretinopathy is essential to tackle these problems. Early-stage detection of\ndiabetic retinopathy is also very important for diagnosis, which can prevent\nblindness with proper treatment. In this paper, we developed a novel deep\nconvolutional neural network, which performs the early-stage detection by\nidentifying all microaneurysms (MAs), the first signs of DR, along with\ncorrectly assigning labels to retinal fundus images which are graded into five\ncategories. We have tested our network on the largest publicly available Kaggle\ndiabetic retinopathy dataset, and achieved 0.851 quadratic weighted kappa score\nand 0.844 AUC score, which achieves the state-of-the-art performance on\nseverity grading. In the early-stage detection, we have achieved a sensitivity\nof 98% and specificity of above 94%, which demonstrates the effectiveness of\nour proposed method. Our proposed architecture is at the same time very simple\nand efficient with respect to computational time and space are concerned.","url_abs":"http://arxiv.org/abs/1812.10595v1","url_pdf":"http://arxiv.org/pdf/1812.10595v1.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":"deep-learning-based-early-detection-and","repo_url":"https://github.com/saifulislampharma/ratinopathy","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"specificity","task_name":"Specificity"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1812.10595","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}