{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,29]],"date-time":"2026-10-29T22:00:16Z","timestamp":1793311216246,"version":"4.5.0"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2023,8,15]],"date-time":"2023-08-15T00:00:00Z","timestamp":1692057600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,8,15]],"date-time":"2023-08-15T00:00:00Z","timestamp":1692057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100014984","name":"European Society of Musculoskeletal Radiology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100014984","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004429","name":"University of Crete","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100004429","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Eur Radiol"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>To develop a deep learning methodology that distinguishes early from late stages of avascular necrosis of the hip (AVN) to determine treatment decisions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      Three convolutional neural networks (CNNs) VGG-16, Inception ResnetV2, InceptionV3 were trained with transfer learning (ImageNet) and finetuned with a retrospectively collected cohort of (\n                      <jats:italic>n\u00a0<\/jats:italic>\n                      = 104) MRI examinations of AVN patients, to differentiate between early (ARCO 1\u20132) and late (ARCO 3\u20134) stages. A consensus CNN ensemble decision was recorded as the agreement of at least two CNNs. CNN and ensemble performance was benchmarked on an independent cohort of 49 patients from another country and was compared to the performance of two MSK radiologists. CNN performance was expressed with areas under the curve (AUC), the respective 95% confidence intervals (CIs) and precision, and recall and f1-scores. AUCs were compared with DeLong\u2019s test.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      On internal testing, Inception-ResnetV2 achieved the highest individual performance with an AUC of 99.7% (95%CI 99\u2013100%), followed by InceptionV3 and VGG-16 with AUCs of 99.3% (95%CI 98.4\u2013100%) and 97.3% (95%CI 95.5\u201399.2%) respectively. The CNN ensemble the same AUCs Inception ResnetV2. On external validation, model performance dropped with VGG-16 achieving the highest individual AUC of 78.9% (95%CI 51.6\u201379.6%) The best external performance was achieved by the model ensemble with an AUC of 85.5% (95%CI 72.2\u201393.9%). No significant difference was found between the CNN ensemble and expert MSK radiologists (\n                      <jats:italic>p\u00a0<\/jats:italic>\n                      = 0.22 and 0.092 respectively).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>An externally validated CNN ensemble accurately distinguishes between the early and late stages of AVN and has comparable performance to expert MSK radiologists.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Clinical relevance statement<\/jats:title>\n                    <jats:p>This paper introduces the use of deep learning for the differentiation between early and late avascular necrosis of the hip, assisting in a complex clinical decision that can determine the choice between conservative and surgical treatment.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Key Points<\/jats:title>\n                    <jats:p>\n                      <jats:italic>\u2022 A convolutional neural network ensemble achieved excellent performance in distinguishing between early and late avascular necrosis.<\/jats:italic>\n                    <\/jats:p>\n                    <jats:p>\n                      <jats:italic>\u2022 The performance of the deep learning method was similar to the performance of expert readers.<\/jats:italic>\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s00330-023-10104-5","type":"journal-article","created":{"date-parts":[[2023,8,15]],"date-time":"2023-08-15T00:01:31Z","timestamp":1692057691000},"page":"1179-1186","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":23,"title":["Deep learning enables the differentiation between early and late stages of hip avascular necrosis"],"prefix":"10.1007","volume":"34","author":[{"given":"Michail E.","family":"Klontzas","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Evangelia E.","family":"Vassalou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Konstantinos","family":"Spanakis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Felix","family":"Meurer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Klaus","family":"Woertler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aristeidis","family":"Zibis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kostas","family":"Marias","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0927-2403","authenticated-orcid":false,"given":"Apostolos H.","family":"Karantanas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,8,15]]},"reference":[{"key":"10104_CR1","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1055\/s-0031-1278427","volume":"15","author":"AH Karantanas","year":"2011","unstructured":"Karantanas AH, Drakonaki EE (2011) The role of MR imaging in avascular necrosis of the femoral head. Semin Musculoskelet Radiol 15:281\u2013300","journal-title":"Semin Musculoskelet Radiol"},{"key":"10104_CR2","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1302\/2058-5241.4.180036","volume":"4","author":"D Petek","year":"2019","unstructured":"Petek D, Hannouche D, Suva D (2019) Osteonecrosis of the femoral head: pathophysiology and current concepts of treatment. EFORT Open Rev 4:85\u201397","journal-title":"EFORT Open Rev"},{"key":"10104_CR3","doi-asserted-by":"publisher","first-page":"933","DOI":"10.1016\/j.arth.2019.11.029","volume":"35","author":"B Yoon","year":"2020","unstructured":"Yoon B, Mont MA, Koo K et al (2020) The 2019 revised version of Association Research Circulation Osseous staging system of osteonecrosis of the femoral head. J Arthroplasty 35:933\u2013940","journal-title":"J Arthroplasty"},{"key":"10104_CR4","first-page":"100","volume":"21","author":"D Zhao","year":"2020","unstructured":"Zhao D, Zhang F, Wang B et al (2020) Guidelines for clinical diagnosis and treatment of osteonecrosis of the femoral head in adults (2019 version). J Orthop Transl 21:100\u2013110","journal-title":"J Orthop Transl"},{"key":"10104_CR5","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-023-09403-8","author":"J Kim","year":"2023","unstructured":"Kim J, Lee SK, Kim J-Y, Kim J-H (2023) CT and MRI findings beyond the subchondral bone in osteonecrosis of the femoral head to distinguish between ARCO stages 2 and 3A. Eur Radiol. https:\/\/doi.org\/10.1007\/s00330-023-09403-8","journal-title":"Eur Radiol"},{"key":"10104_CR6","doi-asserted-by":"publisher","first-page":"610","DOI":"10.1002\/jmri.27860","volume":"55","author":"S Shi","year":"2022","unstructured":"Shi S, Luo P, Sun L et al (2022) Analysis of MR signs to distinguish between ARCO stages 2 and 3A in osteonecrosis of the femoral head. J Magn Reson Imaging 55:610\u2013617","journal-title":"J Magn Reson Imaging"},{"key":"10104_CR7","doi-asserted-by":"publisher","first-page":"2093","DOI":"10.1109\/JBHI.2020.3037079","volume":"25","author":"Y Li","year":"2021","unstructured":"Li Y, Li Y, Tian H (2021) Deep learning-based end-to-end diagnosis system for avascular necrosis of femoral head. IEEE J Biomed Health Inform 25:2093\u20132102","journal-title":"IEEE J Biomed Health Inform"},{"key":"10104_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.arth.2022.10.003","author":"X Shen","year":"2022","unstructured":"Shen X, Luo J, Tang X et al (2022) Deep learning approach for diagnosing early osteonecrosis of the femoral head based on magnetic resonance imaging. J Arthroplasty. https:\/\/doi.org\/10.1016\/j.arth.2022.10.003","journal-title":"J Arthroplasty"},{"key":"10104_CR9","doi-asserted-by":"publisher","first-page":"677","DOI":"10.1007\/s00264-022-05631-7","volume":"47","author":"P Hernigou","year":"2023","unstructured":"Hernigou P (2023) Revisiting prediction of collapse in hip osteonecrosis with artificial intelligence and machine learning: a new approach for quantifying and ranking the contribution and association of factors for collapse. Int Orthop 47:677\u2013689","journal-title":"Int Orthop"},{"key":"10104_CR10","doi-asserted-by":"publisher","first-page":"1686","DOI":"10.3390\/diagnostics11091686","volume":"11","author":"ME Klontzas","year":"2021","unstructured":"Klontzas ME, Manikis GC, Nikiforaki K et al (2021) Radiomics and machine learning can differentiate transient osteoporosis from avascular necrosis of the hip. Diagnostics 11:1686","journal-title":"Diagnostics"},{"issue":"8","key":"10104_CR11","doi-asserted-by":"publisher","first-page":"1870","DOI":"10.3390\/diagnostics12081870","volume":"12","author":"ME Klontzas","year":"2022","unstructured":"Klontzas ME, Stathis I, Spanakis K et al (2022) Deep learning for the differential diagnosis between transient osteoporosis and avascular necrosis of the hip. Diagnostics 12(8):1870","journal-title":"Diagnostics"},{"issue":"1","key":"10104_CR12","doi-asserted-by":"publisher","first-page":"153","DOI":"10.3390\/jpm13010153","volume":"13","author":"AC Ruckli","year":"2023","unstructured":"Ruckli AC, Nanavati AK, Meier MK et al (2023) A deep learning method for quantification of femoral head necrosis based on routine hip MRI for improved surgical decision making. J Person Med 13(1):153","journal-title":"J Person Med"},{"issue":"6","key":"10104_CR13","doi-asserted-by":"publisher","first-page":"e210014","DOI":"10.1148\/ryai.2021210014","volume":"3","author":"S Candemir","year":"2021","unstructured":"Candemir S, Nguyen XV, Folio LR, Prevedello LM (2021) Training strategies for radiology deep learning models in data-limited scenarios. Radiology: Artif Intell 3(6):e210014","journal-title":"Radiol Artif Intell"},{"key":"10104_CR14","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2020200029","volume":"2","author":"J Mongan","year":"2020","unstructured":"Mongan J, Moy L, Kahn CE (2020) Checklist for Artificial Intelligence and Medical Imaging (CLAIM): a guide for authors and reviewers. Radiol Artif Intell 2:e200029","journal-title":"Radiol Artif Intell"},{"key":"10104_CR15","doi-asserted-by":"publisher","first-page":"826","DOI":"10.1148\/radiol.2015151516","volume":"277","author":"PM Bossuyt","year":"2015","unstructured":"Bossuyt PM, Reitsma JB, Bruns DE et al (2015) STARD 2015: an updated list of essential items for reporting diagnostic accuracy studies. Radiology 277:826\u2013832","journal-title":"Radiology"},{"key":"10104_CR16","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1016\/j.ejrad.2007.03.019","volume":"63","author":"KN Malizos","year":"2007","unstructured":"Malizos KN, Karantanas AH, Varitimidis SE et al (2007) Osteonecrosis of the femoral head: etiology, imaging and treatment. Eur J Radiol 63:16\u201328","journal-title":"Eur J Radiol"},{"key":"10104_CR17","doi-asserted-by":"publisher","first-page":"2271","DOI":"10.1007\/s00330-014-3216-8","volume":"24","author":"R Meier","year":"2014","unstructured":"Meier R, Kraus TM, Schaeffeler C et al (2014) Bone marrow oedema on MR imaging indicates ARCO stage 3 disease in patients with AVN of the femoral head. Eur Radiol 24:2271\u20132278","journal-title":"Eur Radiol"},{"key":"10104_CR18","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1517\/17530059.2013.757592","volume":"7","author":"AH Karantanas","year":"2013","unstructured":"Karantanas AH (2013) Accuracy and limitations of diagnostic methods for avascular necrosis of the hip. Expert Opin Med Diagn 7:179\u2013187","journal-title":"Expert Opin Med Diagn"},{"key":"10104_CR19","doi-asserted-by":"publisher","first-page":"2035","DOI":"10.1016\/j.injury.2022.03.008","volume":"53","author":"ME Klontzas","year":"2022","unstructured":"Klontzas ME, Vassalou EE, Kakkos GA et al (2022) Differentiation between subchondral insufficiency fractures and advanced osteoarthritis of the knee using transfer learning and an ensemble of convolutional neural networks. Injury 53:2035\u20132040","journal-title":"Injury"},{"key":"10104_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12880-022-00793-7","volume":"22","author":"HE Kim","year":"2022","unstructured":"Kim HE, Cosa-Linan A, Santhanam N et al (2022) Transfer learning for medical image classification: a literature review. BMC Med Imaging 22:1\u201313","journal-title":"BMC Med Imaging"},{"key":"10104_CR21","first-page":"12","volume":"8","author":"N Turck","year":"2011","unstructured":"Turck N, Vutskits L, Sanchez-Pena P et al (2011) pROC: an open-source package for R and S+ to analyze and compare ROC curves. BMC Bioinform 8:12\u201377","journal-title":"BMC Bioinform"},{"key":"10104_CR22","doi-asserted-by":"publisher","first-page":"837","DOI":"10.2307\/2531595","volume":"44","author":"ER DeLong","year":"1988","unstructured":"DeLong ER, DeLong DM, Clarke-Pearson DL (1988) Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics 44:837\u2013845","journal-title":"Biometrics"},{"key":"10104_CR23","doi-asserted-by":"publisher","first-page":"1073","DOI":"10.2214\/ajr.150.5.1073","volume":"150","author":"WP Shuman","year":"1988","unstructured":"Shuman WP, Castagno AA, Baron RL, Richardson ML (1988) MR imaging of avascular necrosis of the femoral head: value of small-field-of-view sagittal surface-coil images. AJR Am J Roentgenol 150:1073\u20138","journal-title":"AJR Am J Roentgenol"},{"key":"10104_CR24","doi-asserted-by":"publisher","first-page":"545","DOI":"10.2214\/ajr.181.2.1810545","volume":"181","author":"G-S Huang","year":"2003","unstructured":"Huang G-S, Chan WP, Chang Y-C et al (2003) MR imaging of bone marrow edema and joint effusion in patients with osteonecrosis of the femoral head: relationship to pain. AJR Am J Roentgenol 181:545\u20139","journal-title":"AJR Am J Roentgenol"},{"key":"10104_CR25","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.210064","volume":"4","author":"AC Yu","year":"2022","unstructured":"Yu AC, Mohajer B, Eng J (2022) External validation of deep learning algorithms for radiologic diagnosis: a systematic review. Radiol Artif Intell 4:e210064","journal-title":"Radiol Artif Intell"},{"key":"10104_CR26","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2022.42343","volume":"5","author":"W Hsu","year":"2022","unstructured":"Hsu W, Hippe DS, Nakhaei N et al (2022) External validation of an ensemble model for automated mammography interpretation by artificial intelligence. JAMA Netw Open 5:e2242343","journal-title":"JAMA Netw Open"},{"key":"10104_CR27","doi-asserted-by":"publisher","first-page":"405","DOI":"10.3348\/kjr.2019.0025","volume":"20","author":"DW Kim","year":"2019","unstructured":"Kim DW, Jang HY, Kim KW et al (2019) Design characteristics of studies reporting the performance of artificial intelligence algorithms for diagnostic analysis of medical images: results from recently published papers. Korean J Radiol 20:405\u2013410","journal-title":"Korean J Radiol"}],"container-title":["European Radiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00330-023-10104-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00330-023-10104-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00330-023-10104-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,8]],"date-time":"2024-02-08T06:04:15Z","timestamp":1707372255000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00330-023-10104-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,15]]},"references-count":27,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2024,2]]}},"alternative-id":["10104"],"URL":"https:\/\/doi.org\/10.1007\/s00330-023-10104-5","relation":{},"ISSN":["1432-1084"],"issn-type":[{"value":"1432-1084","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,15]]},"assertion":[{"value":"27 February 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 June 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 July 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 August 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The scientific guarantor of this publication is Prof. Apostolos Karantanas.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Guarantor"}},{"value":"The authors of this manuscript declare no relationships with any companies, whose products or services may be related to the subject matter of the article.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"One of the authors has significant statistical expertise.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Statistics and biometry"}},{"value":"Written informed consent was obtained from all subjects participating to undergo the examination. Informed consent was waived for the retrospective anonymized analysis of patient images.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}},{"value":"Institutional Review Board approval was obtained.","order":6,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"One of the two cohorts (UHH) used for the training of our deep learning models has been previously used to train another deep learning ensemble that distinguishes between avascular necrosis and transient osteoporosis. This work has no overlap with the present paper and has been published at\n                      \n                      . No staging of AVN had been attempted in the previous work and our current work does not attempt any diagnosis but only staging of the patients of the cohort. Therefore the work presented here is completely different without any overlap in aims or results.","order":7,"name":"Ethics","group":{"name":"EthicsHeading","label":"Study subjects or cohorts overlap"}},{"order":8,"name":"Ethics","group":{"name":"EthicsHeading","label":"Methodology"}}]}}