Deep Learning Approach for Diagnosing Early Osteonecrosis of the Femoral Head Based on Magnetic Resonance Imaging

Published:October 12, 2022DOI:



      The diagnosis of early osteonecrosis of the femoral head (ONFH) based on magnetic resonance imaging (MRI) is challenging due to variability in the surgeon’s experience level. This study developed an MRI-based deep learning system to detect early ONFH and evaluated its feasibility in the clinic.


      We retrospectively evaluated clinical MRIs of the hips that were performed in our institution from January 2019 to June 2022 and collected all MRIs diagnosed with early ONFH. An advanced convolutional neural network (CNN) was trained and optimized; then, the diagnostic performance of the CNN was evaluated according to its accuracy, sensitivity, and specificity. We also further compared the CNN’s performance with that of orthopaedic surgeons.


      Overall, 11,061 images were retrospectively included in the present study and were divided into three datasets with ratio 7:2:1. The area under the receiver operating characteristic curve, accuracy, sensitivity, and specificity of the CNN model for identifying early ONFH were 0.98, 98.4, 97.6, and 98.6%, respectively. In our review panel, the averaged accuracy, sensitivity, and specificity for identifying ONFH were 91.7, 87.0, and 94.1% for attending orthopaedic surgeons; 87.1, 84.0, and 89.3% for resident orthopaedic surgeons; and 97.1, 96.0, and 97.9% for deputy chief orthopaedic surgeons, respectively.


      The deep learning system showed a comparable performance to that of deputy chief orthopaedic surgeons in identifying early ONFH. The success of deep learning diagnosis of ONFH might be conducive to assisting less-experienced surgeons, especially in large-scale medical imaging screening and community scenarios lacking consulting experts.


      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'


      Subscribe to The Journal of Arthroplasty
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect


        • Koo K.H.
        • Mont M.A.
        • Cui Q.
        • Hines J.T.
        • Yoon B.H.
        • Novicoff W.M.
        • et al.
        The 2021 association research circulation osseous classification for early-stage osteonecrosis of the femoral head-CT based study.
        J Arthroplasty. 2022; 37: 1074-1082
        • Zhao D.
        • Zhang F.
        • Wang B.
        • Liu B.
        • Li L.
        • Kim S.Y.
        • et al.
        Guidelines for clinical diagnosis and treatment of osteonecrosis of the femoral head in adults (2019 version).
        J Orthop Translat. 2020; 21: 100-110
        • Mont M.A.
        • Cherian J.J.
        • Sierra R.J.
        • Jones L.C.
        • Lieberman J.R.
        Nontraumatic osteonecrosis of the femoral head: where do we stand today? A ten-year update.
        J Bone Joint Surg Am. 2015; 97: 1604-1627
        • Ma M.
        • Tan Z.
        • Li W.
        • Zhang H.
        • Liu Y.
        • Yue C.
        Osteoimmunology and osteonecrosis of the femoral head.
        Bone Joint Res. 2022; 11: 26-28
        • Zhao D.W.
        • Yu M.
        • Hu K.
        • Wang W.
        • Yang L.
        • Wang B.J.
        • et al.
        Prevalence of nontraumatic osteonecrosis of the femoral head and its associated risk factors in the Chinese population: results from a nationally representative survey.
        Chin Med J (Engl). 2015; 128: 2843-2850
        • Pedersen M.
        • Grindem H.
        • Johnson J.L.
        • Engebretsen L.
        • Axe M.J.
        • Snyder-Mackler L.
        • et al.
        Clinical, functional, and physical activity outcomes 5 Years following the treatment algorithm of the Delaware-oslo ACL cohort study.
        J Bone Joint Surg Am. 2021; 103: 1473-1481
        • Huang Z.
        • Li T.
        • Lin N.
        • Cui Q.
        • Chen W.
        Evaluation of radiographic outcomes after core decompression for osteonecrosis of the femoral head: the beijing university of Chinese medicine X-ray evaluation method.
        J Bone Joint Surg Am. 2021; 104: 25-32
        • Liang D.
        • Pei J.
        • Zhang L.
        • Ling H.
        • Liu Y.
        • Chen X.
        Treatment of pre-collapse non-traumatic osteonecrosis of the femoral head through Orthopdische Chirurgie München approach combined with autologous bone mixed with β-tricalcium phosphate porous bioceramic bone graft: a retrospective study of mid-term results.
        J Orthop Surg Res. 2021; 16: 492
        • Osawa Y.
        • Seki T.
        • Okura T.
        • Takegami Y.
        • Ishiguro N.
        • Hasegawa Y.
        Long-term outcomes of curved intertrochanteric varus osteotomy combined with bone impaction grafting for non-traumatic osteonecrosis of the femoral head.
        Bone Joint J. 2021; 103-B: 665-671
        • Kim S.C.
        • Lim Y.W.
        • Jo W.L.
        • Park S.B.
        • Kim Y.S.
        • Kwon S.Y.
        Long-Term results of total hip arthroplasty in young patients with osteonecrosis after allogeneic bone marrow transplantation for hematological disease: a multicenter, propensity-matched cohort study with a mean 11-year follow-up.
        J Arthroplasty. 2021; 36: 1049-1054
        • Kim H.S.
        • Park J.W.
        • Ha J.H.
        • Lee Y.K.
        • Ha Y.C.
        • Koo K.H.
        Third-generation ceramic-on-ceramic total hip arthroplasty in patients with osteonecrosis of the femoral head: a 10- to 16-year follow-up study.
        J Bone Joint Surg Am. 2021; 104: 68-75
        • Papakostidis C.
        • Tosounidis T.H.
        • Jones E.
        • Giannoudis P.V.
        The role of “cell therapy” in osteonecrosis of the femoral head. A systematic review of the literature and meta-analysis of 7 studies.
        Acta Orthop. 2016; 87: 72-78
        • Ikemura S.
        • Motomura G.
        • Kawano K.
        • Hamai S.
        • Fujii M.
        • Nakashima Y.
        The discrepancy in the posterior boundary of necrotic lesion between axial and oblique axial slices of MRI in patients with osteonecrosis of the femoral head.
        J Bone Joint Surg Am. 2022; 104: 33-39
        • Li W.L.
        • Tan B.
        • Jia Z.X.
        • Dong B.
        • Huang Z.Q.
        • Zhu R.Z.
        • et al.
        Exploring the risk factors for the misdiagnosis of osteonecrosis of femoral head: a case-control study.
        Orthop Surg. 2020; 12: 1792-1798
        • Mazurowski M.A.
        • Buda M.
        • Saha A.
        • Bashir M.R.
        Deep learning in radiology: an overview of the concepts and a survey of the state of the art with focus on MRI.
        J Magn Reson Imaging. 2019; 49: 939-954
        • Gassenmaier S.
        • Küstner T.
        • Nickel D.
        • Herrmann J.
        • Hoffmann R.
        • Almansour H.
        • et al.
        Deep learning applications in magnetic resonance imaging: has the future become present?.
        Diagnostics (Basel). 2021; 11: 2181
        • Sato Y.
        • Takegami Y.
        • Asamoto T.
        • Ono Y.
        • Hidetoshi T.
        • Goto R.
        • et al.
        Artificial intelligence improves the accuracy of residents in the diagnosis of hip fractures: a multicenter study.
        BMC Musculoskelet Disord. 2021; 22: 407
        • 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: 239-244
        • Lindsey R.
        • Daluiski A.
        • Chopra S.
        • Lachapelle A.
        • Mozer M.
        • Sicular S.
        • et al.
        Deep neural network improves fracture detection by clinicians.
        Proc Natl Acad Sci U S A. 2018; 115: 11591-11596
        • Wang P.
        • Liu X.
        • Xu J.
        • Li T.
        • Sun W.
        • Li Z.
        • et al.
        Deep learning for diagnosing osteonecrosis of the femoral head based on magnetic resonance imaging.
        Comput Methods Programs Biomed. 2021; 208: 106229
        • Yoon B.H.
        • Mont M.A.
        • Koo K.H.
        • Chen C.H.
        • Cheng E.Y.
        • Cui Q.
        • et al.
        The 2019 revised version of association research circulation osseous staging system of osteonecrosis of the femoral head.
        J Arthroplasty. 2020; 35: 933-940
        • Zhang H.
        • Wu C.
        • Zhang Z.
        • Zhu Y.
        • Lin H.
        • Zhang Z.
        • et al.
        Resnest: split-attention networks.
        IEEE Comput Soc Conf Comput Vis Pattern Recogn. 2022; : 2736-2746
        • Kingma D.P.
        • Ba J.
        Adam: A method for stochastic optimization.
        arXiv preprint, 2014 (arXiv:14126980.)
        • Wichmann J.L.
        • Willemink M.J.
        • De Cecco C.N.
        Artificial intelligence and machine learning in radiology: current state and considerations for routine clinical implementation.
        Invest Radiol. 2020; 55: 619-627
        • Karnuta J.M.
        • Haeberle H.S.
        • Luu B.C.
        • Roth A.L.
        • Molloy R.M.
        • Nystrom L.M.
        • et al.
        Artificial intelligence to identify arthroplasty implants from radiographs of the hip.
        J Arthroplasty. 2021; 36: S290-S294
        • Yamada Y.
        • Maki S.
        • Kishida S.
        • Nagai H.
        • Arima J.
        • Yamakawa N.
        • et al.
        Automated classification of hip fractures using deep convolutional neural networks with orthopedic surgeon-level accuracy: ensemble decision-making with antero-posterior and lateral radiographs.
        Acta Orthop. 2020; 91: 699-704
        • Cheng C.T.
        • Wang Y.
        • Chen H.W.
        • Hsiao P.-M.
        • Yeh C.-N.
        • Hsieh C.-H.
        • et al.
        A scalable physician-level deep learning algorithm detects universal trauma on pelvic radiographs.
        Nat Commun. 2021; 12: 1066
        • Zhu L.
        • Han J.
        • Guo R.
        • Wu D.
        • Wei Q.
        • Chai W.
        • et al.
        An automatic classification of the early osteonecrosis of femoral head with deep learning.
        Curr Med Imaging. 2020; 16: 1323-1331
        • Chee C.G.
        • Kim Y.
        • Kang Y.
        • Lee K.J.
        • Chae H.D.
        • Cho J.
        • et al.
        Performance of a deep learning algorithm in detecting osteonecrosis of the femoral head on digital radiography: a comparison with assessments by radiologists.
        AJR Am J Roentgenol. 2019; 213: 155-162
        • Nagendran M.
        • Chen Y.
        • Lovejoy C.A.
        • Gordon A.C.
        • Komorowski M.
        • Harvey H.
        • et al.
        Artificial intelligence versus clinicians: systematic review of design, reporting standards, and claims of deep learning studies.
        BMJ. 2020; 368: m689
        • von Schacky C.E.
        • Sohn J.H.
        • Liu F.
        • Ozhinsky E.
        • Jungmann P.M.
        • Nardo L.
        • et al.
        Development and validation of a multitask deep learning model for severity grading of hip osteoarthritis features on radiographs.
        Radiology. 2020; 295: 136-145
        • Zhang S.C.
        • Sun J.
        • Liu C.B.
        • Fang J.H.
        • Xie H.T.
        • Ning B.
        Clinical application of artificial intelligence-assisted diagnosis using anteroposterior pelvic radiographs in children with developmental dysplasia of the hip.
        Bone Joint J. 2020; 102-B: 1574-1581
        • Mattijssen-Horstink L.
        • Langeraar J.J.
        • Mauritz G.J.
        • van der Stappen W.
        • Baggelaar M.
        • Tan E.
        Radiologic discrepancies in diagnosis of fractures in a Dutch teaching emergency department: a retrospective analysis.
        Scand J Trauma Resusc Emerg Med. 2020; 28: 38