{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T16:59:57Z","timestamp":1788454797064,"version":"build-2803163510"},"reference-count":50,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T00:00:00Z","timestamp":1768348800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"School of Medicine, University of Phayao","award":["MD68-22"],"award-info":[{"award-number":["MD68-22"]}]},{"name":"Thailand Science Research and Innovation Fund","award":["2253\/2568"],"award-info":[{"award-number":["2253\/2568"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diseases"],"abstract":"<jats:p>Background\/Objectives: Accurate and reproducible grading of lumbar spinal stenosis (LSS) is clinically critical for guiding treatment decisions and patient management, yet manual assessment remains challenging due to imaging variability and inter-observer subjectivity. To address these limitations, this study aimed to evaluate the generalizability of deep learning\u2013based feature extraction methods\u2014VGG19, ConvNeXt-Tiny, and DINOv2\u2014combined with classical machine learning classifiers for automated multi-grade LSS assessment. Automated grading enables objective, reproducible, and scalable assessment of lumbar spinal stenosis severity, addressing key limitations of manual interpretation. Methods: Axial MRI images were processed using pretrained VGG19, ConvNeXt-Tiny, and DINOv2 models to extract deep features. Logistic Regression, Support Vector Machine (SVM), and LightGBM were trained on internal datasets and externally validated using MRI data from the University of Phayao Hospital. Performance was assessed using accuracy, precision, recall, F1-score, confusion matrices, and multi-class ROC curves. Results: VGG19-based features yielded the strongest external performance, with Logistic Regression achieving the highest accuracy (0.9556) and F1-score (0.9558). External validation further demonstrated excellent discrimination, with AUC values ranging from 0.994 to 1.000 across all severity grades. SVM (0.9333 accuracy) and LightGBM (0.9222 accuracy) also performed well. ConvNeXt-Tiny showed stable cross-model performance, while DINOv2 features exhibited reduced generalizability, especially with LightGBM (accuracy 0.6222). Most classification errors occurred between adjacent grades. Conclusions: Deep convolutional features\u2014particularly VGG19\u2014combined with classical machine learning classifiers provide robust and generalizable LSS grading across external MRI data. Despite advances in modern architectures, CNN-based feature extraction remains highly effective for spinal imaging and represents a practical pathway for clinical decision support.<\/jats:p>","DOI":"10.3390\/diseases14010032","type":"journal-article","created":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T11:01:14Z","timestamp":1768388474000},"page":"32","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Multi-Task Deep Learning Model for Automated Detection and Severity Grading of Lumbar Spinal Stenosis on MRI: Multi-Center External Validation"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1115-936X","authenticated-orcid":false,"given":"Phatcharapon","family":"Udomluck","sequence":"first","affiliation":[{"name":"School of Medicine, University of Phayao, Phayao 56000, Thailand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8563-017X","authenticated-orcid":false,"given":"Watcharaporn","family":"Cholamjiak","sequence":"additional","affiliation":[{"name":"School of Science, University of Phayao, Phayao 56000, Thailand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1031-1324","authenticated-orcid":false,"given":"Jakkaphong","family":"Inpun","sequence":"additional","affiliation":[{"name":"School of Information and Communication Technology, University of Phayao, Phayao 56000, Thailand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Waragunt","family":"Waratamrongpatai","sequence":"additional","affiliation":[{"name":"School of Medicine, University of Phayao, Phayao 56000, Thailand"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,1,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"818","DOI":"10.1056\/NEJMcp0708097","article-title":"Lumbar Spinal Stenosis","volume":"358","author":"Katz","year":"2008","journal-title":"N. Engl. J. Med."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"545","DOI":"10.1016\/j.spinee.2009.03.005","article-title":"Spinal Stenosis Prevalence and Association with Symptoms: The Framingham Study","volume":"9","author":"Kalichman","year":"2009","journal-title":"Spine J."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1103","DOI":"10.1016\/j.joca.2012.06.018","article-title":"Prevalence of Symptomatic Lumbar Spinal Stenosis and Its Association with Physical Performance in a Population-Based Cohort in Japan: The Wakayama Spine Study","volume":"20","author":"Ishimoto","year":"2012","journal-title":"Osteoarthr. Cartil."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1239","DOI":"10.1097\/BRS.0000000000001476","article-title":"ISSLS Prize Winner: Consensus on the Clinical Diagnosis of Lumbar Spinal Stenosis: Results of an International Delphi Study","volume":"41","author":"Melloh","year":"2016","journal-title":"Spine"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1016\/j.berh.2009.11.001","article-title":"Lumbar Spinal Stenosis","volume":"24","author":"Genevay","year":"2010","journal-title":"Best Pract. Res. Clin. Rheumatol."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"h6234","DOI":"10.1136\/bmj.h6234","article-title":"Management of Lumbar Spinal Stenosis","volume":"352","author":"Lurie","year":"2016","journal-title":"BMJ"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"2029","DOI":"10.3174\/ajnr.A4108","article-title":"Lumbar Disc Nomenclature: Version 2.0","volume":"35","author":"Williams","year":"2014","journal-title":"Am. J. Neuroradiol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2394","DOI":"10.3174\/ajnr.A4498","article-title":"MRI Findings of Disc Degeneration Are More Prevalent in Adults with Low Back Pain than in Asymptomatic Controls: A Systematic Review and Meta-Analysis","volume":"36","author":"Brinjikji","year":"2015","journal-title":"Am. J. Neuroradiol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1056\/NEJM199407143310201","article-title":"Magnetic Resonance Imaging of the Lumbar Spine in People without Back Pain","volume":"331","author":"Jensen","year":"1994","journal-title":"N. Engl. J. Med."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Acquah, G., Sule, D.S., Fesi, L., Kyei, K.A., Ago, J.L., Agala, D., and Antwi, W.K. (2025). Magnetic Resonance Imaging Findings in Ghanaian Patients Presenting with Low Back Pain: A Single Centre Study. BMC Med. Imaging, 25.","DOI":"10.1186\/s12880-025-01680-7"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1016\/j.mric.2025.01.007","article-title":"Role of MR Imaging in Spine Infection","volume":"33","author":"Duarte","year":"2025","journal-title":"Magn. Reson. Imaging Clin."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Mienye, I.D., Swart, T.G., Obaido, G., Jordan, M., and Ilono, P. (2025). Deep Convolutional Neural Networks in Medical Image Analysis: A Review. Information, 16.","DOI":"10.3390\/info16030195"},{"key":"ref_13","first-page":"65","article-title":"An Overview of Deep Learning in Medical Imaging","volume":"12","author":"Lundervold","year":"2019","journal-title":"Front. Neurosci."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"e2082","DOI":"10.7717\/peerj-cs.2082","article-title":"Enhancing Early Breast Cancer Diagnosis through Automated Microcalcification Detection Using an Optimized Ensemble Deep Learning Framework","volume":"10","author":"Teoh","year":"2024","journal-title":"PeerJ Comput. Sci."},{"key":"ref_15","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv."},{"key":"ref_16","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2021, January 3\u20137). An Image Is Worth 16 \u00d7 16 Words: Transformers for Image Recognition at Scale. Proceedings of the International Conference on Learning Representations (ICLR 2021), Virtual Conference."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1038\/nature21056","article-title":"Dermatologist-Level Classification of Skin Cancer with Deep Neural Networks","volume":"542","author":"Esteva","year":"2017","journal-title":"Nature"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1146\/annurev-bioeng-071516-044442","article-title":"Deep Learning in Medical Image Analysis","volume":"19","author":"Shen","year":"2017","journal-title":"Annu. Rev. Biomed. Eng."},{"key":"ref_19","unstructured":"Oquab, M., Darcet, T., Moutakanni, T., Vo, H., Szafraniec, M., Khalidov, V., Fernandez, P., Haziza, D., Massa, F., and El-Nouby, A. (2023). DINOv2: Learning Robust Visual Features without Supervision. arXiv."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Lim, B.Y., Lai, K.W., Haiskin, K., Kulathilake, K.S.H., Ong, Z.C., Hum, Y.C., and Zuo, X. (2022). Deep Learning Model for Prediction of Progressive Mild Cognitive Impairment to Alzheimer\u2019s Disease Using Structural MRI. Front. Aging Neurosci., 14.","DOI":"10.3389\/fnagi.2022.876202"},{"key":"ref_21","first-page":"2196","article-title":"SpineNet: Automated Classification and Evidence Visualization of Lumbar Spine MRI","volume":"36","author":"Jamaludin","year":"2017","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"124286","DOI":"10.1016\/j.wneu.2025.124286","article-title":"A Novel Lumbar Disc Herniation Classification Based on Endplate Destruction","volume":"201","author":"Tang","year":"2025","journal-title":"World Neurosurg."},{"key":"ref_23","unstructured":"Raja\u2019S, A. (2010). Computer Aided Diagnosis of Intervertebral Disc Pathology in Lumbar Spine. [Ph.D. Thesis, State University of New York at Buffalo]."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1097\/RLI.0000000000000709","article-title":"A Deep Learning Model for the Accurate and Reliable Classification of Disc Degeneration Based on MRI Data","volume":"56","author":"Niemeyer","year":"2021","journal-title":"Investig. Radiol."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"24587","DOI":"10.1007\/s10489-023-04829-5","article-title":"Exploring Gait Analysis and Deep Feature Contributions to the Screening of Cervical Spondylotic Myelopathy","volume":"53","author":"Ji","year":"2023","journal-title":"Appl. Intell."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Kelly, C.J., Karthikesalingam, A., Suleyman, M., Corrado, G., and King, D. (2019). Key Challenges for Delivering Clinical Impact with Artificial Intelligence. BMC Med., 17.","DOI":"10.1186\/s12916-019-1426-2"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Bohr, A., and Memarzadeh, K. (2020). Ethical and Legal Challenges of Artificial Intelligence-Driven Healthcare. Artificial Intelligence in Healthcare, Academic Press.","DOI":"10.1016\/B978-0-12-818438-7.00002-2"},{"key":"ref_28","unstructured":"(2025, September 05). RSNA 2024 Lumbar Spine Degenerative Classification Dataset. Kaggle, Available online: https:\/\/www.kaggle.com\/."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1016\/j.canlet.2016.05.033","article-title":"Big Data and Machine Learning in Radiation Oncology: State of the Art and Future Prospects","volume":"382","author":"Bibault","year":"2016","journal-title":"Cancer Lett."},{"key":"ref_30","unstructured":"Glocker, B., Robinson, R., Castro, D.C., Dou, Q., and Konukoglu, E. (2019). Machine Learning with Multi-Site Imaging Data: An Empirical Study on the Impact of Scanner Effects. arXiv."},{"key":"ref_31","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_32","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1038\/s41746-019-0105-1","article-title":"Deep Learning Predicts Hip Fracture Using Confounding Patient and Healthcare Variables","volume":"2","author":"Badgeley","year":"2019","journal-title":"NPJ Digit. Med."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1016\/j.jclinepi.2014.06.018","article-title":"A New Framework to Enhance the Interpretation of External Validation Studies of Clinical Prediction Models","volume":"68","author":"Debray","year":"2015","journal-title":"J. Clin. Epidemiol."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"71","DOI":"10.21037\/atm.2019.11.121","article-title":"Overview of Clinical Prediction Models","volume":"8","author":"Chen","year":"2020","journal-title":"Ann. Transl. Med."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Riley, R.D., van der Windt, D., Croft, P., and Moons, K.G. (2019). Prognosis Research in Healthcare: Concepts, Methods, and Impact, Oxford University Press.","DOI":"10.1093\/med\/9780198796619.001.0001"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1136\/svn-2017-000101","article-title":"Artificial Intelligence in Healthcare: Past, Present and Future","volume":"2","author":"Jiang","year":"2017","journal-title":"Stroke Vasc. Neurol."},{"key":"ref_37","first-page":"2.1","article-title":"The Enemies of Reliable and Useful Clinical Prediction Models: A Review of Statistical and Scientific Challenges","volume":"13","author":"Coemans","year":"2025","journal-title":"Annu. Rev. Stat. Its Appl."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"4831","DOI":"10.1093\/eurheartj\/ehad727","article-title":"Five Critical Quality Criteria for Artificial Intelligence-Based Prediction Models","volume":"44","author":"Asselbergs","year":"2023","journal-title":"Eur. Heart J."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"e2431493","DOI":"10.2214\/AJR.24.31493","article-title":"Pitfalls in Interpretive Applications of Artificial Intelligence in Radiology","volume":"223","author":"Behzad","year":"2024","journal-title":"Am. J. Roentgenol."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1055\/s-0039-1692626","article-title":"Genetic Influence in Disc Degeneration\u2014Systematic Review of the Literature","volume":"55","author":"Filho","year":"2020","journal-title":"Rev. Bras. Ortop."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1007\/s00701-024-05924-3","article-title":"Factors Influencing Slippage after Microsurgical Single Level Lumbar Spinal Decompression Surgery\u2014Are the Psoas and Multifidus Muscles Involved?","volume":"166","author":"Ikeda","year":"2024","journal-title":"Acta Neurochir."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1007\/s00586-018-5710-1","article-title":"The Prevalence and Impact of Frailty in Patients with Symptomatic Lumbar Spinal Stenosis","volume":"28","author":"Kim","year":"2019","journal-title":"Eur. Spine J."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1038\/s41591-018-0300-7","article-title":"High-Performance Medicine: The Convergence of Human and Artificial Intelligence","volume":"25","author":"Topol","year":"2019","journal-title":"Nat. Med."},{"key":"ref_44","unstructured":"World Health Organization, and ITU (2021). Guidance on Ethics and Artificial Intelligence for Health, WHO Publications."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image Quality Assessment: From Error Visibility to Structural Similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans. Image Process."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1186\/s40537-019-0197-0","article-title":"A Survey on Image Data Augmentation for Deep Learning","volume":"6","author":"Shorten","year":"2019","journal-title":"J. Big Data"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C., Feichtenhofer, C., Darrell, T., and Xie, S. (2022, January 18\u201324). A ConvNet for the 2020s. Proceedings of the 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"2395","DOI":"10.1161\/CIRCULATIONAHA.106.682658","article-title":"Logistic Regression","volume":"117","author":"LaValley","year":"2008","journal-title":"Circulation"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1023\/A:1022627411411","article-title":"Support-Vector Networks","volume":"20","author":"Cortes","year":"1995","journal-title":"Mach. Learn."},{"key":"ref_50","unstructured":"Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., and Liu, T.-Y. (2017, January 4\u20139). LightGBM: A Highly Efficient Gradient Boosting Decision Tree. Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA."}],"container-title":["Diseases"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2079-9721\/14\/1\/32\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T09:55:07Z","timestamp":1768470907000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2079-9721\/14\/1\/32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,14]]},"references-count":50,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["diseases14010032"],"URL":"https:\/\/doi.org\/10.3390\/diseases14010032","relation":{},"ISSN":["2079-9721"],"issn-type":[{"value":"2079-9721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,14]]}}}