{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,4]],"date-time":"2026-10-04T14:33:13Z","timestamp":1791124393420,"version":"4.1.0"},"reference-count":25,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T00:00:00Z","timestamp":1777507200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Bioengineering"],"abstract":"<jats:p>Background\/Objectives: Osteonecrosis of the femoral head (ONFH) is difficult to diagnose, particularly in the early stages, because radiological findings may be subtle. Delayed or inaccurate staging may increase the risk of femoral head collapse and functional loss. Although magnetic resonance imaging is highly sensitive for early-stage lesion detection, interpretation may vary depending on observer experience. Therefore, reliable and explainable automated decision support approaches are needed. Methods: In this study, a deep learning-based approach was proposed to classify ONFH into early and late stages according to the Ficat\u2013Arlet staging system. Stage I\u2013II cases were defined as early-stage, whereas Stage III\u2013IV cases were defined as late-stage. Axial and coronal MR images were evaluated separately to investigate plane-dependent classification performance. The images were converted into a three-channel format, resized to a common spatial resolution, normalized, and augmented during training. Feature extraction was performed using transfer learning with modern convolutional neural network architectures. ConvNeXt Tiny was used as the main classification backbone. Weighted loss was applied to reduce the effect of class imbalance, and the decision threshold was optimized on validation data to reduce missed clinically critical late-stage cases. Results: A dataset collected from the Orthopedics and Traumatology Department of Firat University Hospital was used in the experimental evaluation. The dataset was divided into training and test sets using an 80:20 split, and 10-fold cross-validation was additionally performed to assess model stability. In the hold-out test, the axial plane model achieved 94.51% accuracy, 96.80% sensitivity, 93.49% specificity, 0.9162 F1-score, and 0.981 AUC. In the coronal plane model, 92.84% accuracy, 96.13% sensitivity, 90.96% specificity, 0.9072 F1-score, and 0.988 AUC were obtained. The 10-fold cross-validation results provided a more conservative estimate of generalization performance. Conclusions: The findings indicate that deep learning-based plane-wise analysis of MR images can distinguish early- and late-stage ONFH with high performance. Grad-CAM-based visual explanations showed that the model focused mainly on clinically relevant subchondral and weight-bearing regions of the femoral head. The proposed approach may serve as an explainable decision support tool for reducing observer-dependent variability in clinical staging. Future studies should validate the method using external, multicenter datasets and paired patient-level axial\u2013coronal images.<\/jats:p>","DOI":"10.3390\/bioengineering13050529","type":"journal-article","created":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T09:33:17Z","timestamp":1777627997000},"page":"529","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["An Explainable Plane-Wise ConvNet Approach for Detecting Femoral Head Osteonecrosis from Magnetic Resonance Images"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1709-3851","authenticated-orcid":false,"given":"\u015e\u00fckr\u00fc","family":"Demir","sequence":"first","affiliation":[{"name":"Faculty of Medicine, Firat University, 23119 Elazig, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5973-4856","authenticated-orcid":false,"given":"Mehmet","family":"Vural","sequence":"additional","affiliation":[{"name":"Digital Transformation Office, Firat University, 23119 Elazig, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bu\u011fra","family":"Can","sequence":"additional","affiliation":[{"name":"Faculty of Medicine, Firat University, 23119 Elazig, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3210-3664","authenticated-orcid":false,"given":"Fatih","family":"Demir","sequence":"additional","affiliation":[{"name":"INCISOFT Software Information Technologies, F\u0131rat Teknokent, F\u0131rat University, 23000 Elazig, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1614-2639","authenticated-orcid":false,"given":"Abdulkadir","family":"Sengur","sequence":"additional","affiliation":[{"name":"Department of Electrical-Electronic Engineering, Faculty of Technology, Firat University, 23000 Elazig, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,4,30]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"2843","DOI":"10.4103\/0366-6999.168017","article-title":"Prevalence of nontraumatic osteonecrosis of the femoral head and its associated risk factors in the Chinese population: Results from a nationally representative survey","volume":"128","author":"Zhao","year":"2015","journal-title":"Chin. Med. J."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"590","DOI":"10.5312\/wjo.v6.i8.590","article-title":"Current concepts on osteonecrosis of the femoral head","volume":"6","author":"Gianakos","year":"2015","journal-title":"World J. Orthop."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1084","DOI":"10.2106\/JBJS.19.01271","article-title":"Nontraumatic osteonecrosis of the femoral head: Where do we stand today?: A 5-year update","volume":"102","author":"Mont","year":"2020","journal-title":"J. Bone Jt. Surg."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"e177","DOI":"10.3346\/jkms.2021.36.e177","article-title":"Osteonecrosis of the femoral head: An updated review of ARCO on pathogenesis, staging and treatment","volume":"36","author":"Hines","year":"2021","journal-title":"J. Korean Med. Sci."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1302\/2058-5241.4.180036","article-title":"Osteonecrosis of the femoral head: Pathophysiology and current concepts of treatment","volume":"4","author":"Petek","year":"2019","journal-title":"EFORT Open Rev."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"2636","DOI":"10.1007\/s11999-012-2416-2","article-title":"In brief: Ficat classification: Avascular necrosis of the femoral head","volume":"470","author":"Jawad","year":"2012","journal-title":"Clin. Orthop. Relat. Res."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"709","DOI":"10.1148\/radiology.162.3.3809484","article-title":"Femoral head avascular necrosis: Correlation of MR imaging, radiographic staging, radionuclide imaging, and clinical findings","volume":"162","author":"Mitchell","year":"1987","journal-title":"Radiology"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"933","DOI":"10.1016\/j.arth.2019.11.029","article-title":"The 2019 revised version of Association Research Circulation Osseous staging system of osteonecrosis of the femoral head","volume":"35","author":"Yoon","year":"2020","journal-title":"J. Arthroplast."},{"key":"ref_9","first-page":"283","article-title":"Avascular necrosis of the femoral head: Inter- and intraobserver variations of Ficat and ARCO classifications","volume":"32","author":"Kirchhoff","year":"2007","journal-title":"Int. Orthop."},{"key":"ref_10","first-page":"35","article-title":"Prediction of collapse in femoral head osteonecrosis: A modified Kerboul method with use of magnetic resonance images","volume":"88","author":"Ha","year":"2006","journal-title":"J. Bone Jt. Surg."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1007\/s43465-024-01272-7","article-title":"Aiding diagnosis and classifying of early stage osteonecrosis of the femoral head with convolutional neural network based on magnetic resonance imaging","volume":"59","author":"Liang","year":"2024","journal-title":"Indian J. Orthop."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1016\/j.arth.2023.08.018","article-title":"Development and validation of an automated classification system for osteonecrosis of the femoral head using deep learning approach: A multicenter study","volume":"39","author":"Shen","year":"2024","journal-title":"J. Arthroplast."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1179","DOI":"10.1007\/s00330-023-10104-5","article-title":"Deep learning enables the differentiation between early and late stages of hip avascular necrosis","volume":"34","author":"Klontzas","year":"2024","journal-title":"Eur. Radiol."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Yang, M., Hsiang, F., Li, C., Chen, X., Zhang, C., Sun, G., Lou, Q., Zhu, W., Zhao, H., and Liu, F. (2025). Development and evaluation of a 3D ensemble framework for automatic diagnosis of early osteonecrosis of the femoral head based on MRI: A multicenter diagnostic study. Front. Surg., 12.","DOI":"10.3389\/fsurg.2025.1555749"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"S160","DOI":"10.1016\/j.arth.2025.05.126","article-title":"Development of a deep learning model for the volumetric assessment of osteonecrosis of the femoral head on three-dimensional magnetic resonance imaging","volume":"40","author":"Uemura","year":"2025","journal-title":"J. Arthroplast."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Gao, S., Zhu, H., Wen, M., He, W., Wu, Y., Li, Z., and Peng, J. (2024). Prediction of femoral head collapse in osteonecrosis using deep learning segmentation and radiomics texture analysis of MRI. BMC Med. Inform. Decis. Mak., 24.","DOI":"10.1186\/s12911-024-02722-w"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Ruckli, A.C., Nanavati, A.K., Meier, M.K., Lerch, T.D., Steppacher, S.D., Vuilleumier, S., Boschung, A., Vuillemin, N., Tannast, M., and Siebenrock, K.A. (2023). A deep learning method for quantification of femoral head necrosis based on routine hip mri for improved surgical decision making. J. Pers. Med., 13.","DOI":"10.3390\/jpm13010153"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Vezirh\u00fcy\u00fck, M., Celtik, M., \u015eahin, E., T\u00fcremi\u015f, C., \u00d6nal, C., and Aydemir, S. (2025). Comparative analysis of intra- and interobserver reliability and validity of five basic classifications used to determine the stage of avascular necrosis of the femoral head. BMC Musculoskelet. Disord., 26.","DOI":"10.1186\/s12891-025-08398-1"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"60","DOI":"10.21015\/vtse.v14i1.2311","article-title":"An ensemble deep learning framework for automated multi class skin lesion classification using ConvNeXt-Tiny, EfficientNetV2-S, and MobileNetV3","volume":"14","author":"Faris","year":"2026","journal-title":"VFAST Trans. Softw. Eng."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1016\/S1525-1578(10)60455-2","article-title":"Analysis of microarray data using Z score transformation","volume":"5","author":"Cheadle","year":"2003","journal-title":"J. Mol. Diagn."},{"key":"ref_21","first-page":"1","article-title":"SIHENet: Semantic interaction and hierarchical embedding network for 360\u00b0 salient object detection","volume":"74","author":"He","year":"2024","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"5148","DOI":"10.1109\/TGRS.2017.2702596","article-title":"Remote sensing scene classification by unsupervised representation learning","volume":"55","author":"Lu","year":"2017","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_23","first-page":"851","article-title":"Automatic detection of phone-level mispronunciation for language learning","volume":"99","author":"Franco","year":"1999","journal-title":"Proc. Eurospeech"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1016\/0034-4257(80)90011-5","article-title":"The use of prior probabilities in maximum likelihood classification of remotely sensed data","volume":"10","author":"Strahler","year":"1980","journal-title":"Remote Sens. Environ."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Yusufo\u011flu, E., F\u0131rat, H., \u00dczen, H., \u00d6z\u00e7elik, S.T.A., \u00c7i\u00e7ek, \u0130.B., \u015eeng\u00fcr, A., Atila, O., and Guldemir, N.H. (2024). A comprehensive CNN model for age-related macular degeneration classification using OCT: Integrating inception modules, SE blocks, and ConvMixer. Diagnostics, 14.","DOI":"10.3390\/diagnostics14242836"}],"container-title":["Bioengineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2306-5354\/13\/5\/529\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T15:40:08Z","timestamp":1779205208000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2306-5354\/13\/5\/529"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,30]]},"references-count":25,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5]]}},"alternative-id":["bioengineering13050529"],"URL":"https:\/\/doi.org\/10.3390\/bioengineering13050529","relation":{},"ISSN":["2306-5354"],"issn-type":[{"value":"2306-5354","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,30]]}}}