{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T05:24:03Z","timestamp":1783488243332,"version":"3.55.0"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,2,9]],"date-time":"2024-02-09T00:00:00Z","timestamp":1707436800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,2,9]],"date-time":"2024-02-09T00:00:00Z","timestamp":1707436800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100004047","name":"Karolinska Institute","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100004047","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Musculoskelet Disord"],"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>Background<\/jats:title>\n                <jats:p>Hip dysplasia is a condition where the acetabulum is too shallow to support the femoral head and is commonly considered a risk factor for hip osteoarthritis. The objective of this study was to develop a deep learning model to diagnose hip dysplasia from plain radiographs and classify dysplastic hips based on their severity.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Methods<\/jats:title>\n                <jats:p>We collected pelvic radiographs of 571 patients from two single-center cohorts and one multicenter cohort. The radiographs were split in half to create hip radiographs (<jats:italic>n<\/jats:italic>\u2009=\u20091022). One orthopaedic surgeon and one resident assessed the radiographs for hip dysplasia on either side. We used the center edge (CE) angle as the primary diagnostic criteria. Hips with a CE angle\u2009&lt;\u200920\u00b0, 20\u00b0 to 25\u00b0, and &gt;\u200925\u00b0 were labeled as dysplastic, borderline, and normal, respectively. The dysplastic hips were also classified with both Crowe and Hartofilakidis classification of dysplasia. The dataset was divided into train, validation, and test subsets using 80:10:10 split-ratio that were used to train two deep learning models to classify images into normal, borderline and (1) Crowe grade 1\u20134 or (2) Hartofilakidis grade 1\u20133. A pre-trained on Imagenet VGG16 convolutional neural network (CNN) was utilized by performing layer-wise fine-turning.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>Both models struggled with distinguishing between normal and borderline hips. However, achieved high accuracy (Model 1: 92.2% and Model 2: 83.3%) in distinguishing between normal\/borderline vs. dysplastic hips. The overall accuracy of Model 1 was 68% and for Model 2 73.5%. Most misclassifications for the Crowe and Hartofilakidis classifications were +\/- 1 class from the correct class.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusions<\/jats:title>\n                <jats:p>This pilot study shows promising results that a deep learning model distinguish between normal and dysplastic hips with high accuracy. Future research and external validation are warranted regarding the ability of deep learning models to perform complex tasks such as identifying and classifying disorders using plain radiographs.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Level of Evidence<\/jats:title>\n                <jats:p>Diagnostic level IV<\/jats:p>\n              <\/jats:sec>","DOI":"10.1186\/s12891-024-07244-0","type":"journal-article","created":{"date-parts":[[2024,2,9]],"date-time":"2024-02-09T09:02:32Z","timestamp":1707469352000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Application of deep learning for automated diagnosis and classification of hip dysplasia on plain radiographs"],"prefix":"10.1186","volume":"25","author":[{"given":"Martin","family":"Magn\u00e9li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alireza","family":"Borjali","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eiji","family":"Takahashi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Axenhus","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Henrik","family":"Malchau","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Orhun K.","family":"Moratoglu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kartik M.","family":"Varadarajan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,2,9]]},"reference":[{"issue":"2","key":"7244_CR1","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1080\/00016470510030517","volume":"76","author":"S Jacobsen","year":"2005","unstructured":"Jacobsen S, Sonne-Holm S, S\u00f8balle K, Gebuhr P, Lund B. Hip dysplasia and osteoarthrosis: a survey of 4151 subjects from the Osteoarthrosis Substudy of the Copenhagen City Heart Study. Acta Orthop. 2005;76(2):149\u201358.","journal-title":"Acta Orthop"},{"issue":"4","key":"7244_CR2","doi-asserted-by":"publisher","first-page":"771","DOI":"10.1007\/s11999-008-0132-8","volume":"466","author":"E Peled","year":"2008","unstructured":"Peled E, Eidelman M, Katzman A, Bialik V. Neonatal incidence of hip dysplasia: ten years of experience. Clin Orthop Relat Res. 2008;466(4):771\u20135.","journal-title":"Clin Orthop Relat Res"},{"key":"7244_CR3","doi-asserted-by":"crossref","unstructured":"Leide R, Wenger D, Overgaard S, Tiderius C, Rogmark C. Hip dysplasia is not uncommon but frequently overlooked: a cross-sectional study based on radiographic examination of 1,870 adults. ACTA ORTHOP 2021 (June 4): 1\u20136.","DOI":"10.1080\/17453674.2021.1936918"},{"issue":"5","key":"7244_CR4","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1007\/s00256-005-0061-5","volume":"35","author":"R Decking","year":"2006","unstructured":"Decking R, Brunner A, Decking J, Puhl W, G\u00fcnther KP. Reliability of the Crowe und Hartofilakidis classifications used in the assessment of the adult dysplastic hip. Skeletal Radiol. 2006;35(5):282\u20137.","journal-title":"Skeletal Radiol"},{"issue":"5","key":"7244_CR5","doi-asserted-by":"publisher","first-page":"579","DOI":"10.1302\/0301-620X.90B5.19724","volume":"90","author":"CK Yiannakopoulos","year":"2008","unstructured":"Yiannakopoulos CK, Chougle A, Eskelinen A, Hodgkinson JP, Hartofilakidis G. Inter- and intra-observer variability of the Crowe and Hartofilakidis classification systems for congenital hip disease in adults. J Bone Joint Surg Br. 2008;90(5):579\u201383.","journal-title":"J Bone Joint Surg Br"},{"issue":"6 Suppl","key":"7244_CR6","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1016\/j.otsr.2014.07.007","volume":"100","author":"A Clav\u00e9","year":"2014","unstructured":"Clav\u00e9 A, Kerboull L, Musset T, Flecher X, Huten D, Lef\u00e8vre C, et al. Comparison of the inter- and intra-observer reproducibility of the Crowe, Hartofilakidis and modified Cochin classification systems for the diagnosis of developmental dysplasia of the hip. Orthop Traumatol Surg Res. 2014;100(6 Suppl):323\u20136.","journal-title":"Orthop Traumatol Surg Res"},{"issue":"5","key":"7244_CR7","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1136\/ard.50.5.308","volume":"50","author":"P Croft","year":"1991","unstructured":"Croft P, Cooper C, Wickham C, Coggon D. Osteoarthritis of the hip and acetabular dysplasia. Ann Rheum Dis. 1991;50(5):308\u201310.","journal-title":"Ann Rheum Dis"},{"issue":"7","key":"7244_CR8","doi-asserted-by":"publisher","first-page":"745","DOI":"10.1093\/rheumatology\/39.7.745","volume":"39","author":"K Inoue","year":"2000","unstructured":"Inoue K, Wicart P, Kawasaki T, Huang J, Ushiyama T, Hukuda S, et al. Prevalence of hip osteoarthritis and acetabular dysplasia in French and Japanese adults. Rheumatology (Oxford). 2000;39(7):745\u20138.","journal-title":"Rheumatology (Oxford)"},{"issue":"2","key":"7244_CR9","doi-asserted-by":"publisher","first-page":"444","DOI":"10.1016\/j.arthro.2017.08.285","volume":"34","author":"DK Matsuda","year":"2018","unstructured":"Matsuda DK, Wolff AB, Nho SJ, Salvo JP, Christoforetti JJ, Kivlan BR, et al. Hip dysplasia: prevalence, Associated findings, and procedures from large Multicenter Arthroscopy Study Group. Arthroscopy. 2018;34(2):444\u201353.","journal-title":"Arthroscopy"},{"issue":"3","key":"7244_CR10","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1136\/ard.54.3.179","volume":"54","author":"RW Smith","year":"1995","unstructured":"Smith RW, Egger P, Coggon D, Cawley MI, Cooper C. Osteoarthritis of the hip joint and acetabular dysplasia in women. Ann Rheum Dis. 1995;54(3):179\u201381.","journal-title":"Ann Rheum Dis"},{"issue":"2","key":"7244_CR11","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1302\/0301-620X.95B2.30744","volume":"95\u2013B","author":"I\u00d8 Enges\u00e6ter","year":"2013","unstructured":"Enges\u00e6ter I\u00d8, Laborie LB, Lehmann TG, Fevang JM, Lie SA, Enges\u00e6ter LB, et al. Prevalence of radiographic findings associated with hip dysplasia in a population-based cohort of 2081 19-year-old norwegians. Bone Joint J. 2013;95\u2013B(2):279\u201385.","journal-title":"Bone Joint J"},{"issue":"6","key":"7244_CR12","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1080\/17453674.2017.1344459","volume":"88","author":"J Olczak","year":"2017","unstructured":"Olczak J, Fahlberg N, Maki A, Razavian AS, Jilert A, Stark A, et al. Artificial intelligence for analyzing orthopedic trauma radiographs. Acta Orthop. 2017;88(6):581\u20136.","journal-title":"Acta Orthop"},{"issue":"4","key":"7244_CR13","doi-asserted-by":"publisher","first-page":"468","DOI":"10.1080\/17453674.2018.1453714","volume":"89","author":"SW Chung","year":"2018","unstructured":"Chung SW, Han SS, Lee JW, Oh KS, Kim NR, Yoon JP, et al. Automated detection and classification of the proximal humerus fracture by using deep learning algorithm. Acta Orthop. 2018;89(4):468\u201373.","journal-title":"Acta Orthop"},{"key":"7244_CR14","doi-asserted-by":"crossref","unstructured":"Kim CY, Sivasundaram L, LaBelle MW, Trivedi NN, Liu RW, Gillespie RJ. Predicting adverse events, length of stay, and discharge disposition following shoulder arthroplasty: a comparison of the Elixhauser Comorbidity measure and Charlson Comorbidity Index. J Shoulder Elb Surg. 2018.","DOI":"10.1016\/j.jse.2018.03.001"},{"issue":"4","key":"7244_CR15","doi-asserted-by":"publisher","first-page":"394","DOI":"10.1080\/17453674.2019.1600125","volume":"90","author":"K Gan","year":"2019","unstructured":"Gan K, Xu D, Lin Y, Shen Y, Zhang T, Hu K, et al. Artificial intelligence detection of distal radius fractures: a comparison between the convolutional neural network and professional assessments. Acta Orthop. 2019;90(4):394\u2013400.","journal-title":"Acta Orthop"},{"key":"7244_CR16","unstructured":"Borjali A, Chen AF, Muratoglu OK, Morid MA, Varadarajan KM. Detecting mechanical loosening of total hip replacement implant from plain radiograph using deep convolutional neural network. arXiv:191200943 [cs, eess] [Internet]. 2019 Dec 2 [cited 2020 Oct 28]; Available from: http:\/\/arxiv.org\/abs\/1912.00943."},{"issue":"2","key":"7244_CR17","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1007\/s00256-018-3016-3","volume":"48","author":"T Urakawa","year":"2019","unstructured":"Urakawa T, Tanaka Y, Goto S, Matsuzawa H, Watanabe K, Endo N. Detecting intertrochanteric hip fractures with orthopedist-level accuracy using a deep convolutional neural network. Skeletal Radiol. 2019;48(2):239\u201344.","journal-title":"Skeletal Radiol"},{"key":"7244_CR18","doi-asserted-by":"crossref","unstructured":"Borjali A, Chen AF, Muratoglu OK, Morid MA, Varadarajan KM. Detecting total hip replacement prosthesis design on plain radiographs using deep convolutional neural network. J Orthop Res. 2020.","DOI":"10.1002\/jor.24617"},{"key":"7244_CR19","doi-asserted-by":"publisher","first-page":"104140","DOI":"10.1016\/j.compbiomed.2020.104140","volume":"129","author":"A Borjali","year":"2020","unstructured":"Borjali A, Magn\u00e9li M, Shin D, Malchau H, Muratoglu OK, Varadarajan KM. Natural language processing with deep learning for medical adverse event detection from free-text medical narratives: a case study of detecting total hip replacement dislocation. Comput Biol Med. 2020;129:104140.","journal-title":"Comput Biol Med"},{"issue":"1","key":"7244_CR20","doi-asserted-by":"publisher","first-page":"97","DOI":"10.5301\/hipint.5000297","volume":"26","author":"NH Sillesen","year":"2016","unstructured":"Sillesen NH, Greene ME, Nebergall AK, Huddleston JI, Emerson R, Gebuhr P, et al. 3-year follow-up of a long-term registry-based multicentre study on vitamin E diffused polyethylene in total hip replacement. Hip Int. 2016;26(1):97\u2013103.","journal-title":"Hip Int"},{"key":"7244_CR21","unstructured":"Wiberg G. Studies on dysplastic acetabula and congenital subluxation of the hip joint. With special referance to the complication of osteoarthritis. 1939. (Acta Chir Scand. Suppl.)."},{"issue":"1","key":"7244_CR22","doi-asserted-by":"publisher","first-page":"65","DOI":"10.2106\/00004623-195335010-00007","volume":"35\u2013A","author":"G Wiberg","year":"1953","unstructured":"Wiberg G. Shelf operation in congenital dysplasia of the acetabulum and in subluxation and dislocation of the hip. J Bone Joint Surg Am. 1953;35\u2013A(1):65\u201380.","journal-title":"J Bone Joint Surg Am"},{"issue":"4","key":"7244_CR23","doi-asserted-by":"publisher","first-page":"403","DOI":"10.3109\/17453677608988709","volume":"47","author":"N Fredensborg","year":"1976","unstructured":"Fredensborg N. The CE angle of normal hips. Acta Orthop Scand. 1976;47(4):403\u20135.","journal-title":"Acta Orthop Scand"},{"key":"7244_CR24","doi-asserted-by":"crossref","unstructured":"T\u00f6nnis D. Normal values of the hip joint for the evaluation of X-rays in children and adults. Clin Orthop Relat Res. 1976;(119):39\u201347.","DOI":"10.1097\/00003086-197609000-00007"},{"issue":"1","key":"7244_CR25","doi-asserted-by":"publisher","first-page":"15","DOI":"10.2106\/00004623-197961010-00004","volume":"61","author":"JF Crowe","year":"1979","unstructured":"Crowe JF, Mani VJ, Ranawat CS. Total hip replacement in congenital dislocation and dysplasia of the hip. J Bone Joint Surg Am. 1979;61(1):15\u201323.","journal-title":"J Bone Joint Surg Am"},{"issue":"2","key":"7244_CR26","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1302\/0301-620X.70B2.3346284","volume":"70","author":"G Hartofilakidis","year":"1988","unstructured":"Hartofilakidis G, Stamos K, Ioannidis TT. Low friction arthroplasty for old untreated congenital dislocation of the hip. J Bone Joint Surg Br. 1988;70(2):182\u20136.","journal-title":"J Bone Joint Surg Br"},{"issue":"2","key":"7244_CR27","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1302\/0301-620X.43B2.268","volume":"43\u2013B","author":"Sharp","year":"1961","unstructured":"Sharp IK. Acetabular dysplasia. J Bone Joint Surg Br Volume. 1961;43\u2013B(2):268\u201372.","journal-title":"J Bone Joint Surg Br Volume"},{"issue":"1","key":"7244_CR28","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1177\/001316446002000104","volume":"20","author":"J Cohen","year":"1960","unstructured":"Cohen J. A coefficient of Agreement for Nominal scales. Educ Psychol Meas. 1960;20(1):37\u201346.","journal-title":"Educ Psychol Meas"},{"key":"7244_CR29","unstructured":"Li F-F. ImageNet: crowdsourcing, benchmarking & other cool things [Internet]. CMU VASC Seminar; 2010 Mar. Available from: http:\/\/www.image-net.org\/papers\/ImageNet_2010.pdf."},{"key":"7244_CR30","doi-asserted-by":"publisher","first-page":"104115","DOI":"10.1016\/j.compbiomed.2020.104115","volume":"128","author":"MA Morid","year":"2021","unstructured":"Morid MA, Borjali A, Del Fiol G. A scoping review of transfer learning research on medical image analysis using ImageNet. Comput Biol Med. 2021;128:104115.","journal-title":"Comput Biol Med"},{"key":"7244_CR31","doi-asserted-by":"publisher","unstructured":"Borjali A, Chen AF, Muratoglu OK, Morid MA, Varadarajan KM. Deep Learning in Orthopedics: How Do We Build Trust in the Machine? Healthcare Transformation [Internet]. 2020 Mar 30 [cited 2021 Jan 15]; Available from: https:\/\/www.liebertpub.com\/doi\/full\/https:\/\/doi.org\/10.1089\/heat.2019.0006.","DOI":"10.1089\/heat.2019.0006"},{"issue":"Suppl 2","key":"7244_CR32","doi-asserted-by":"publisher","first-page":"35","DOI":"10.2106\/JBJS.J.01717","volume":"93","author":"PC Rhee","year":"2011","unstructured":"Rhee PC, Woodcock JA, Clohisy JC, Millis M, Sucato DJ, Beaul\u00e9 PE, et al. The Shenton line in the diagnosis of acetabular dysplasia in the skeletally mature patient. J Bone Joint Surg Am. 2011;93(Suppl 2):35\u20139.","journal-title":"J Bone Joint Surg Am"},{"key":"7244_CR33","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1097\/01.blo.0000167669.26068.c5","volume":"438","author":"M Tannast","year":"2005","unstructured":"Tannast M, Zheng G, Anderegg C, Burckhardt K, Langlotz F, Ganz R, et al. Tilt and rotation correction of acetabular version on pelvic radiographs. Clin Orthop Relat Res. 2005;438:182\u201390.","journal-title":"Clin Orthop Relat Res"},{"issue":"11","key":"7244_CR34","doi-asserted-by":"publisher","first-page":"2597","DOI":"10.3390\/diagnostics12112597","volume":"12","author":"J Jensen","year":"2022","unstructured":"Jensen J, Graumann O, Overgaard S, Gerke O, Lundemann M, Haubro MH, et al. A deep learning algorithm for Radiographic measurements of the hip in Adults\u2014A reliability and agreement study. Diagnostics. 2022;12(11):2597.","journal-title":"Diagnostics"},{"issue":"11","key":"7244_CR35","doi-asserted-by":"publisher","first-page":"877","DOI":"10.1302\/2633-1462.311.BJO-2022-0125.R1","volume":"3","author":"H Archer","year":"2022","unstructured":"Archer H, Reine S, Alshaikhsalama A, Wells J, Kohli A, Vazquez L, et al. Artificial intelligence-generated hip radiological measurements are fast and adequate for reliable assessment of hip dysplasia: an external validation study. Bone Jt Open. 2022;3(11):877\u201384.","journal-title":"Bone Jt Open"}],"container-title":["BMC Musculoskeletal Disorders"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12891-024-07244-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12891-024-07244-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12891-024-07244-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,9]],"date-time":"2024-02-09T09:04:56Z","timestamp":1707469496000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcmusculoskeletdisord.biomedcentral.com\/articles\/10.1186\/s12891-024-07244-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,9]]},"references-count":35,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["7244"],"URL":"https:\/\/doi.org\/10.1186\/s12891-024-07244-0","relation":{},"ISSN":["1471-2474"],"issn-type":[{"value":"1471-2474","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,9]]},"assertion":[{"value":"8 October 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 January 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 February 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"For data source 1, written informed consent was collected for all participants in the clinical study. A separate IRB approval for continuing radiographic analysis exists, Partners Human Research, protocol no. 2007P001955. For data source 2 and 3, written informed consent was collected for all participants in the clinical study. IRB committee of Kanazawa Medical University. Receipt number: 134, date of approval: June 18, 2012.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"117"}}