{"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/automatic-knee-osteoarthritis-diagnosis-from","title":"Automatic Knee Osteoarthritis Diagnosis from Plain Radiographs: A Deep Learning-Based Approach","arxiv_id":"1710.10589","date":"2017-10-29","proceeding":null,"authors":["Aleksei Tiulpin","Jérôme Thevenot","Esa Rahtu","Petri Lehenkari","Simo Saarakkala"],"abstract":"Knee osteoarthritis (OA) is the most common musculoskeletal disorder. OA\ndiagnosis is currently conducted by assessing symptoms and evaluating plain\nradiographs, but this process suffers from subjectivity. In this study, we\npresent a new transparent computer-aided diagnosis method based on the Deep\nSiamese Convolutional Neural Network to automatically score knee OA severity\naccording to the Kellgren-Lawrence grading scale. We trained our method using\nthe data solely from the Multicenter Osteoarthritis Study and validated it on\nrandomly selected 3,000 subjects (5,960 knees) from Osteoarthritis Initiative\ndataset. Our method yielded a quadratic Kappa coefficient of 0.83 and average\nmulticlass accuracy of 66.71\\% compared to the annotations given by a committee\nof clinical experts. Here, we also report a radiological OA diagnosis area\nunder the ROC curve of 0.93. We also present attention maps -- given as a class\nprobability distribution -- highlighting the radiological features affecting\nthe network decision. This information makes the decision process transparent\nfor the practitioner, which builds better trust toward automatic methods. We\nbelieve that our model is useful for clinical decision making and for OA\nresearch; therefore, we openly release our training codes and the data set\ncreated in this study.","url_abs":"http://arxiv.org/abs/1710.10589v1","url_pdf":"http://arxiv.org/pdf/1710.10589v1.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":"automatic-knee-osteoarthritis-diagnosis-from","repo_url":"https://github.com/lext/DeepKnee","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1710.10589","atlas_url":"https://app.syntology.ai/?focus=1710.10589","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}