{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,5]],"date-time":"2026-11-05T08:03:58Z","timestamp":1793865838080,"version":"4.6.1"},"reference-count":16,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T00:00:00Z","timestamp":1729641600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:sec><jats:title>Background<\/jats:title><jats:p>Calcium pyrophosphate deposition (CPPD) disease is a leading cause of arthritis, which can mimic or strongly interfere with other rheumatic diseases such as gout, osteoarthritis (OA) or rheumatoid arthritis (RA). In the recently established ACR\/EULAR CPPD classification criteria, calcification and OA features of the wrist and hand joints are substantial features.<\/jats:p><\/jats:sec><jats:sec><jats:title>Objectives<\/jats:title><jats:p>To develop and test a deep-learning algorithm for automatically and reliably detecting CPPD features in hand radiographs, focusing on calcification of the triangular fibrocartilage complex (TFCC) and metacarpophalangeal (MCP)-2 and -3 joints, in separate or combined models.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>Two radiologists independently labeled a dataset of 926 hand radiographs, yielding 319 CPPD positive and 607 CPPD negative cases across the three sites of interest after adjudicating discrepant cases. CPPD presence was then predicted using a convolutional neural network. We tested seven CPPD models, each with a different combination of sites out of TFCC, MCP-2 and MCP-3. The model performance was assessed using the area under the receiver operating characteristic (AUROC) and area under the precision-recall (AUPR) curves, with heatmaps (Grad-CAM) aiding in case discrimination.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>All models trialed gave good class separation, with the combined TFCC, MCP-2 and MCP-3 model showing the most robust performance with a mean AUROC of 0.86, mean AUPR of 0.77, sensitivity of 0.77, specificity of 0.80, and precision of 0.67. The TFCC-alone model had a slightly lower mean AUROC of 0.85 with a mean AUPR of 0.73. The MCP-2-alone and MCP-3-alone models exhibited mean AUROCs of 0.78\u20130.87, but lower mean AUPRs of 0.29\u20130.47. Heatmap analysis revealed activation in the regions of interest for positive cases (true and false positives), but unexpected highlights were encountered possibly due to correlated features in different hand regions.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>A combined deep-learning model detecting CPPD at the TFCC and MCP-2\/3 joints in hand radiographs provides the highest diagnostic performance. The algorithm could be used to screen larger OA or RA databases or electronic medical records for CPPD cases. Future work includes dataset expansion and validation with external datasets.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fmed.2024.1431333","type":"journal-article","created":{"date-parts":[[2024,10,24]],"date-time":"2024-10-24T07:53:30Z","timestamp":1729756410000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Development of a deep learning model for automated detection of calcium pyrophosphate deposition in hand radiographs"],"prefix":"10.3389","volume":"11","author":[{"given":"Thomas","family":"H\u00fcgle","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elisabeth","family":"Rosoux","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guillaume","family":"Fahrni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deborah","family":"Markham","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tobias","family":"Manigold","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fabio","family":"Becce","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2024,10,23]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"e497","DOI":"10.1016\/s2665-9913(23)00188-1","article-title":"Calcium pyrophosphate deposition disease moves into the spotlight","volume":"5","author":"Dalbeth","year":"2023","journal-title":"Lancet Rheumatol"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"1248","DOI":"10.1136\/ard-2023-224575","article-title":"The 2023 ACR\/EULAR classification criteria for calcium pyrophosphate deposition disease","volume":"82","author":"Abhishek","year":"2023","journal-title":"Ann Rheum Dis"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1038\/s41584-023-01074-5","article-title":"Deep learning in rheumatological image interpretation","volume":"20","author":"Stoel","year":"2024","journal-title":"Nat Rev Rheumatol"},{"key":"ref4","article-title":"FDA: artificial intelligence and machine learning (AI\/ML)-enabled medical devices","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"262","DOI":"10.1186\/s13075-021-02634-4","article-title":"A deep learning method for predicting knee osteoarthritis radiographic progression from MRI","volume":"23","author":"Schiratti","year":"2021","journal-title":"Arthritis Res Ther"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1136\/annrheumdis-2020-217998","article-title":"Criterion validity of ultrasound in the identification of calcium pyrophosphate crystal deposits at the knee: an OMERACT ultrasound study","volume":"80","author":"Filippou","year":"2021","journal-title":"Ann Rheum Dis"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"825","DOI":"10.1002\/acr.24898","article-title":"Imaging features of calcium pyrophosphate deposition disease: consensus definitions from an international multidisciplinary working group","volume":"75","author":"Tedeschi","year":"2023","journal-title":"Arthritis Care Res"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"630","DOI":"10.1002\/art.42368","article-title":"Reliability and diagnostic accuracy of radiography for the diagnosis of calcium pyrophosphate deposition: performance of the novel definitions developed by an international multidisciplinary working group","volume":"75","author":"Sirotti","year":"2023","journal-title":"Arthritis Rheumatol"},{"key":"ref9","volume-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","author":"Tan","year":"2020"},{"key":"ref10","article-title":"Grad-CAM: visual explanations from deep networks via gradient-based localization","author":"Selvaraju","year":"2019"},{"key":"ref11","first-page":"99","article-title":"Prevalence of calcium pyrophosphate deposition disease in a cohort of patients diagnosed with seronegative rheumatoid arthritis","volume":"38","author":"Paalanen","year":"2020","journal-title":"Clin Exp Rheumatol"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1136\/annrheumdis-2019-215315","article-title":"2018 updated European league against rheumatism evidence-based recommendations for the diagnosis of gout","volume":"79","author":"Richette","year":"2020","journal-title":"Ann Rheum Dis"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"752","DOI":"10.1136\/ard-2023-224771","article-title":"2023 EULAR recommendations on imaging in diagnosis and management of crystal-induced arthropathies in clinical practice","volume":"83","author":"Mandl","year":"2024","journal-title":"Ann Rheum Dis"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13075-022-02972-x","article-title":"Artificial intelligence and the future of radiographic scoring in rheumatoid arthritis: a viewpoint","volume":"24","author":"Bird","year":"2022","journal-title":"Arthritis Res Ther"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"388","DOI":"10.1002\/acr2.11665","article-title":"Detection and Grading of Radiographic Hand Osteoarthritis Using an Automated Machine Learning Platform","volume":"6","author":"Caratsch","year":"2024","journal-title":"ACR Open Rheumatol"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1159\/000525061","article-title":"Dorsal finger fold recognition by convolutional neural networks for the detection and monitoring of joint swelling in patients with rheumatoid arthritis","volume":"6","author":"H\u00fcgle","year":"2022","journal-title":"Digit Biomark"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2024.1431333\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,24]],"date-time":"2024-10-24T07:53:34Z","timestamp":1729756414000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2024.1431333\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,23]]},"references-count":16,"alternative-id":["10.3389\/fmed.2024.1431333"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2024.1431333","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,23]]},"article-number":"1431333"}}