{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T20:05:44Z","timestamp":1778702744476,"version":"3.51.4"},"reference-count":31,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Research Foundation of Korea funded by the Ministry of Science and ICT","award":["RS-2024-00338438"],"award-info":[{"award-number":["RS-2024-00338438"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Bioengineering"],"abstract":"<jats:p>While magnetic resonance imaging (MRI) is effective for detecting early-stage osteonecrosis of the femoral head (ONFH), it is often expensive and less accessible; conversely, radiography is more widely accessible but has limited sensitivity for early-stage diagnosis. We developed a deep learning approach using radiographic images to effectively classify ONFH stages, providing a more accessible method for early diagnosis and disease stage differentiation. The dataset consisted of 909 hip radiographs, yielding 1818 femoral head images (grade 0:1495; grade 1:80; grade 2:114; grade 3:93; grade 4:36). A U-Net model was used to segment the femoral heads, achieving a Dice similarity coefficient (DSC) of 0.977 on the test set, allowing precise localization of the region of interest. A variational autoencoder (VAE) was then trained using 1270 grade-0 images for training and 112 for validation to construct a normative latent distribution representing healthy femoral heads. When ONFH data from all grades were projected into the latent space, significant differences in Mahalanobis distance distributions were observed across most ONFH stages. No significant difference was found between grades 0 and 1 (p = 0.06), consistent with known radiographic subtlety. However, grades 2\u20134 showed significant deviation from grade 0, and significant differences were also observed among mid- and late-stage grades. These findings demonstrate that the proposed method effectively separates healthy and diseased femoral heads and captures gradewise structural progression within the latent space. This radiograph-based normative modeling approach offers an accessible alternative to MRI for ONFH stage differentiation, particularly in resource-limited clinical environments. Although early-stage differentiation remains challenging, the results highlight the potential of radiograph-based deep learning systems to improve diagnostic efficiency and support future automated ONFH staging workflows.<\/jats:p>","DOI":"10.3390\/bioengineering12121319","type":"journal-article","created":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T10:34:01Z","timestamp":1764758041000},"page":"1319","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Classification of Osteonecrosis of the Femoral Head Stage on Radiographic Images Using Deep Learning Techniques"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0065-3605","authenticated-orcid":false,"given":"Hyun Hee","family":"Lee","sequence":"first","affiliation":[{"name":"Department of Orthopedic Surgery, International St. Mary\u2019s Hospital, Catholic Kwandong University College of Medicine, Incheon 22711, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joeun","family":"Jeong","sequence":"additional","affiliation":[{"name":"Department of Mechanical and Biomedical Engineering, Ewha Womans University, Seoul 03760, Republic of Korea"},{"name":"Graduate Program in Smart Factory, Ewha Womans University, Seoul 03760, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Taehoon","family":"Shin","sequence":"additional","affiliation":[{"name":"Department of Mechanical and Biomedical Engineering, Ewha Womans University, Seoul 03760, Republic of Korea"},{"name":"Graduate Program in Smart Factory, Ewha Womans University, Seoul 03760, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7936-088X","authenticated-orcid":false,"given":"Dong-Sik","family":"Chae","sequence":"additional","affiliation":[{"name":"Department of Orthopedic Surgery, International St. Mary\u2019s Hospital, Catholic Kwandong University College of Medicine, Incheon 22711, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,3]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1517\/17530059.2013.757592","article-title":"Accuracy and limitations of diagnostic methods for avascular necrosis of the hip","volume":"7","author":"Karantanas","year":"2013","journal-title":"Expert Opin. Med. Diagn."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"e082342","DOI":"10.1136\/bmjopen-2023-082342","article-title":"Time elapsed from definitive diagnosis to surgery for osteonecrosis of the femoral head: A nationwide observational study in Japan","volume":"14","author":"Nakamura","year":"2024","journal-title":"BMJ Open"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Banerjee, S., Kapadia, B.H., Jauregui, J.J., Cherian, J.J., and Mont, M.A. (2014). Natural history of osteonecrosis. Osteonecrosis, Springer.","DOI":"10.1007\/978-3-642-35767-1_20"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"641","DOI":"10.2106\/00004623-198971050-00002","article-title":"The diagnostic value of magnetic resonance imaging in non-traumatic osteonecrosis of the femoral head","volume":"71","author":"Hauzeur","year":"1989","journal-title":"J. Bone Jt. Surg."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"875","DOI":"10.1302\/0301-620X.77B6.7593098","article-title":"Quantifying the extent of osteonecrosis of the femoral head. A new method using MRI","volume":"77","author":"Koo","year":"1995","journal-title":"J. Bone Jt. Surg."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"637","DOI":"10.2214\/AJR.10.4322","article-title":"Relationship of idiopathic osteonecrosis of the femoral head to perfusion changes in the proximal femur by dynamic contrast-enhanced MRI","volume":"196","author":"Chan","year":"2011","journal-title":"Am. J. Roentgenol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"155","DOI":"10.2214\/AJR.18.20817","article-title":"Performance of a Deep Learning Algorithm in Detecting Osteonecrosis of the Femoral Head on Digital Radiography: A Comparison With Assessments by Radiologists","volume":"213","author":"Chee","year":"2019","journal-title":"Am. J. Roentgenol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2093","DOI":"10.1109\/JBHI.2020.3037079","article-title":"Deep Learning-Based End-to-End Diagnosis System for Avascular Necrosis of Femoral Head","volume":"25","author":"Li","year":"2021","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"2044","DOI":"10.1016\/j.arth.2022.10.003","article-title":"Deep learning approach for diagnosing early osteonecrosis of the femoral head based on magnetic resonance imaging","volume":"38","author":"Shen","year":"2023","journal-title":"J. Arthroplast."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Lawry Aguila, A., Chapman, J., and Altmann, A. (2023, January 8\u201312). Multi-modal variational autoencoders for normative modelling across multiple imaging modalities. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Vancouver, BC, Canada.","DOI":"10.1007\/978-3-031-43907-0_41"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. Medical Image Computing and Computer-Assisted Intervention\u2014MICCAI 2015, Proceedings of the 18th International Conference, Munich, Germany, 5\u20139 October 2015, Springer. Proceedings, Part III.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Rahman Siddiquee, M.M., Tajbakhsh, N., and Liang, J. (2018, January 20). Unet++: A nested u-net architecture for medical image segmentation. Proceedings of the International Workshop on Deep Learning in Medical Image Analysis, Granada, Spain.","DOI":"10.1007\/978-3-030-00889-5_1"},{"key":"ref_13","unstructured":"Kingma, D.P. (2013). Auto-encoding variational bayes. arXiv."},{"key":"ref_14","first-page":"44318","article-title":"Deep learning advancements in anomaly detection: A comprehensive survey","volume":"12","author":"Huang","year":"2025","journal-title":"IEEE Internet Things J."},{"key":"ref_15","unstructured":"Cabiscol, J.A. (2019). Understanding Uncertainty in Bayesian Neural Networks. [Master\u2019s Thesis, University of Cambridge]."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1116","DOI":"10.1016\/j.neuroimage.2006.01.015","article-title":"User-guided 3D active contour segmentation of anatomical structures: Significantly improved efficiency and reliability","volume":"31","author":"Yushkevich","year":"2006","journal-title":"NeuroImage"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"57613","DOI":"10.1109\/ACCESS.2024.3389669","article-title":"Applications of deep learning models on the medical images of osteonecrosis of the femoral head (ONFH): A comprehensive review","volume":"12","author":"Wang","year":"2024","journal-title":"IEEE Access"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"2235","DOI":"10.1007\/s00264-023-05813-x","article-title":"Automatic detection of early osteonecrosis of the femoral head from various hip pathologies using deep convolutional neural network: A multi-centre study","volume":"47","author":"Shen","year":"2023","journal-title":"Int. Orthop."},{"key":"ref_19","first-page":"327","article-title":"Deep residual learning","volume":"7","author":"He","year":"2015","journal-title":"Image Recognit."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Cao, L., Li, R., Zhou, D., Zhao, M., and Huang, W. (2025, January 28\u201330). Deep Learning-Based Diagnosis and Classification of Femoral Head Necrosis. Proceedings of the 2025 5th International Conference on Artificial Intelligence and Industrial Technology Applications (AIITA), Xi\u2019an, China.","DOI":"10.1109\/AIITA65135.2025.11047864"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Pham, D.D., Dovletov, G., Serong, S., Landgraeber, S., J\u00e4ger, M., and Pauli, J. (2020, January 15\u201317). Multitask-learning for the extraction of avascular necrosis of the femoral head in mri. Proceedings of the Bildverarbeitung f\u00fcr die Medizin 2020: Algorithmen\u2013Systeme\u2013Anwendungen, Berlin, Germany.","DOI":"10.1007\/978-3-658-29267-6_31"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., and Adam, H. (2018, January 8\u201314). Encoder-decoder with atrous separable convolution for semantic image segmentation. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1711","DOI":"10.1038\/s41596-022-00696-5","article-title":"The normative modeling framework for computational psychiatry","volume":"17","author":"Rutherford","year":"2022","journal-title":"Nat. Protoc."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1186\/s13195-025-01753-3","article-title":"Deep normative modelling reveals insights into early-stage Alzheimer\u2019s disease using multi-modal neuroimaging data","volume":"17","author":"Lorenzini","year":"2025","journal-title":"Alzheimer\u2019s Res. Ther."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"817","DOI":"10.1007\/s11517-017-1736-5","article-title":"Novel Mahalanobis-based feature selection improves one-class classification of early hepatocellular carcinoma","volume":"56","author":"Thomaz","year":"2018","journal-title":"Med. Biol. Eng. Comput."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1007\/BF02834632","article-title":"Mahalanobis distance","volume":"4","author":"McLachlan","year":"1999","journal-title":"Resonance"},{"key":"ref_27","first-page":"583","article-title":"Mahalanobis distance and its application for detecting multivariate outliers","volume":"34","author":"Ghorbani","year":"2019","journal-title":"Facta Univ. Ser. Math. Inform."},{"key":"ref_28","unstructured":"Higgins, I., Matthey, L., Pal, A., Burgess, C.P., Glorot, X., Botvinick, M.M., Mohamed, S., and Lerchner, A. (2017, January 24\u201326). \u03b2-VAE: Learning basic visual concepts with a constrained variational framework. Proceedings of the 5th ICLR, Toulon, France."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Zech, J.R., Badgeley, M.A., Liu, M., Costa, A.B., Titano, J.J., and Oermann, E.K. (2018). Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: A cross-sectional study. PLoS Med., 15.","DOI":"10.1371\/journal.pmed.1002683"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"836","DOI":"10.1016\/j.jacr.2023.06.015","article-title":"Understanding biases and disparities in radiology AI datasets: A review","volume":"20","author":"Tripathi","year":"2023","journal-title":"J. Am. Coll. Radiol."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"e230067","DOI":"10.1148\/rg.230067","article-title":"Understanding and mitigating bias in imaging artificial intelligence","volume":"44","author":"Tejani","year":"2024","journal-title":"Radiographics"}],"container-title":["Bioengineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2306-5354\/12\/12\/1319\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T11:13:45Z","timestamp":1764760425000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2306-5354\/12\/12\/1319"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,3]]},"references-count":31,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["bioengineering12121319"],"URL":"https:\/\/doi.org\/10.3390\/bioengineering12121319","relation":{},"ISSN":["2306-5354"],"issn-type":[{"value":"2306-5354","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,3]]}}}