{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T22:39:48Z","timestamp":1789079988175,"version":"build-2803163510"},"reference-count":35,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T00:00:00Z","timestamp":1787097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>Lumbar foraminal stenosis grading contributes to surgical-level selection, but automated four-grade classification remains challenging. Published pipelines for this dataset reach approximately 65% four-class accuracy, and deep classifiers offer no anatomical rationale. We investigated whether interpretable, millimeter-scale morphometry from segmentation masks improves grading beyond a deep image model. We analyzed the LSS-MRI-AISSLab sagittal T2-weighted dataset (469 patients, 2979 expert-graded foramina spanning L1-L2 through L5-S1 bilaterally on a four-grade scale). Ten morphometric descriptors were computed from mid-sagittal polygon segmentations and scaled to millimeters using each patient\u2019s recorded pixel spacing. A dual-branch network combined a fine-tuned ResNet-18 embedding of each foraminal region of interest with the morphometric vector through an ordinal regression head. Foraminal regions were supplied from expert bounding-box annotations; automated localization within the full sagittal examination was not evaluated. Four configurations (nominal softmax, appearance-only, anatomy-only, and fusion) were compared on a locked patient-level test set of 94 patients after five-fold cross-validation, with quadratic weighted kappa (QWK) as the primary endpoint and patient-clustered bootstrap inference. Feature-grade correlations were reported pooled and adjusted for lumbar level. Fusion achieved QWK 0.813 (95% confidence interval [CI] 0.769\u20130.847) and 75.3% four-class accuracy. Appearance-only was statistically indistinguishable (QWK 0.806; delta QWK +0.006, 95% CI \u22120.023 to 0.036, p = 0.68), whereas anatomy-only reached 0.444, and a level-and-side-only reference reached 0.314. Boundary discrimination was strong (area under the curve 0.92\u20130.99), 98.3% of predictions fell within one grade, and performance was consistent across scanner vendors. Morphometric associations were confounded by level: the apparent spondylolisthesis effect (rho \u22120.349) disappeared after adjustment (rho \u22120.000), while disc height, null when pooled (rho +0.021), emerged as a genuine within-level effect (rho \u22120.108). A fine-tuned ordinal image classifier achieved strong agreement for four-grade lumbar foraminal stenosis classification. The evaluated segmentation-derived morphometric features did not improve performance beyond imaging alone, and several apparent anatomic associations reflected confounding by lumbar level. External and prospective validation in complete clinical MRI workflows are needed before implementation.<\/jats:p>","DOI":"10.3390\/jimaging12080388","type":"journal-article","created":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T11:04:12Z","timestamp":1787137452000},"page":"388","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Ordinal Deep Learning for Lumbar Foraminal Stenosis Grading on Sagittal MRI"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8611-6711","authenticated-orcid":false,"given":"Rohan A.","family":"Phadke","sequence":"first","affiliation":[{"name":"School of Medicine, Baylor College of Medicine, Houston, TX 77030, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9897-4071","authenticated-orcid":false,"given":"Samer G.","family":"Salman","sequence":"additional","affiliation":[{"name":"School of Medicine, Baylor College of Medicine, Houston, TX 77030, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2953-1133","authenticated-orcid":false,"given":"Zane G.","family":"Salman","sequence":"additional","affiliation":[{"name":"College of Natural Sciences, The University of Texas at Austin, Austin, TX 78712, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1789-2752","authenticated-orcid":false,"given":"Akhil","family":"Marupudi","sequence":"additional","affiliation":[{"name":"McGovern Medical School, The University of Texas Health Science Center, Houston, TX 77030, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kirtan","family":"Patel","sequence":"additional","affiliation":[{"name":"Edward Via College of Osteopathic Medicine-Louisiana, Monroe, LA 71203, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4860-827X","authenticated-orcid":false,"given":"Joshua","family":"Ong","sequence":"additional","affiliation":[{"name":"Massachusetts Eye and Ear, Harvard Medical School, Boston, MA 02114, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9460-1269","authenticated-orcid":false,"given":"Alireza","family":"Tavakkoli","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Nevada, Reno, NV 89557, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sainyam","family":"Galhotra","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Cornell University, Ithaca, NY 14853, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ajay","family":"Tripuraneni","sequence":"additional","affiliation":[{"name":"School of Medicine, Baylor College of Medicine, Houston, TX 77030, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2835-0371","authenticated-orcid":false,"given":"James","family":"Rizkalla","sequence":"additional","affiliation":[{"name":"Department of Orthopaedic Surgery, Baylor University Medical Center, Dallas, TX 75246, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0496-4977","authenticated-orcid":false,"given":"Nathan J.","family":"Lee","sequence":"additional","affiliation":[{"name":"Midwest Orthopaedics at Rush, Rush University School of Medicine, Chicago, IL 60612, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,19]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1688","DOI":"10.1001\/jama.2022.5921","article-title":"Diagnosis and management of lumbar spinal stenosis","volume":"327","author":"Katz","year":"2022","journal-title":"JAMA"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1329","DOI":"10.1097\/BRS.0b013e3181e0f04d","article-title":"Surgical versus nonoperative treatment for lumbar spinal stenosis: Four-year results of the Spine Patient Outcomes Research Trial","volume":"35","author":"Weinstein","year":"2010","journal-title":"Spine"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1097\/BRS.0000000000000731","article-title":"Long-term outcomes of lumbar spinal stenosis: Eight-year results of the Spine Patient Outcomes Research Trial (SPORT)","volume":"40","author":"Lurie","year":"2015","journal-title":"Spine"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"556","DOI":"10.1097\/00007632-200003010-00005","article-title":"Surgical and nonsurgical management of lumbar spinal stenosis: Four-year outcomes from the Maine Lumbar Spine Study","volume":"25","author":"Atlas","year":"2000","journal-title":"Spine"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"936","DOI":"10.1097\/01.brs.0000158953.57966.c0","article-title":"Long-term outcomes of surgical and nonsurgical management of lumbar spinal stenosis: 8 to 10 year results from the Maine Lumbar Spine Study","volume":"30","author":"Atlas","year":"2005","journal-title":"Spine"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1097\/00003086-199206000-00010","article-title":"The natural course of lumbar spinal stenosis","volume":"279","author":"Johnsson","year":"1992","journal-title":"Clin. Orthop. Relat. Res."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Kang, D.H., Lee, S., Kim, H.J., Park, S.M., and Yeom, J.S. (2022). Probability for surgical treatment in patients with lumbar spinal stenosis according to the stenotic lesion severity: A 5-10-year follow-up study. BMC Musculoskelet. Disord., 23.","DOI":"10.1186\/s12891-022-05510-7"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2121","DOI":"10.1007\/s00701-023-05693-5","article-title":"Is the presence of foraminal stenosis associated with outcome in lumbar spinal stenosis patients treated with posterior microsurgical decompression","volume":"165","author":"Aaen","year":"2023","journal-title":"Acta Neurochir."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"403","DOI":"10.2106\/00004623-199072030-00013","article-title":"Abnormal magnetic-resonance scans of the lumbar spine in asymptomatic subjects: A prospective investigation","volume":"72","author":"Boden","year":"1990","journal-title":"J. Bone Jt. Surg. Am."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1178","DOI":"10.1097\/00007632-199505150-00013","article-title":"Lumbar spinal stenosis: Clinical and radiologic features","volume":"20","author":"Amundsen","year":"1995","journal-title":"Spine"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"679","DOI":"10.1007\/s00586-008-0646-5","article-title":"Degenerative lumbar spinal stenosis: Correlation with Oswestry Disability Index and MR imaging","volume":"17","author":"Sirvanci","year":"2008","journal-title":"Eur. Spine J."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"240","DOI":"10.1007\/s10143-026-04179-z","article-title":"Endoscopic versus open lumbar decompression: A retrospective cohort study of 31,000 patients with 90-day follow-up","volume":"49","author":"Srinivas","year":"2026","journal-title":"Neurosurg. Rev."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Phadke, R., Salman, S., Kumar, R., Paidisetty, V., Matthews, B., Srinivas, R., Vaja, S., and Lee, N.J. (2026). Endoscopic and percutaneous minimally invasive repair of pars interarticularis defects: A systematic review of clinical outcomes. Spine Deform., 1\u201312.","DOI":"10.1007\/s43390-026-01435-6"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Salman, S.G., Phadke, R., Kumar, R., Gill, K., Vaja, S., Lee, N.J., and Bono, C. (2026). Long-term outcomes of lumbar total disc arthroplasty and hybrid constructs: A systematic review. Spine J.","DOI":"10.1016\/j.spinee.2026.06.010"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1095","DOI":"10.2214\/AJR.09.2772","article-title":"A practical MRI grading system for lumbar foraminal stenosis","volume":"194","author":"Lee","year":"2010","journal-title":"AJR Am. J. Roentgenol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1919","DOI":"10.1097\/BRS.0b013e3181d359bd","article-title":"Qualitative grading of severity of lumbar spinal stenosis based on the morphology of the dural sac on magnetic resonance images","volume":"35","author":"Schizas","year":"2010","journal-title":"Spine"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1033","DOI":"10.1007\/s00256-011-1153-z","article-title":"A new grading system of lumbar central canal stenosis on MRI: An easy and reliable method","volume":"40","author":"Lee","year":"2011","journal-title":"Skelet. Radiol."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Ko, Y.-J., Lee, E., Lee, J.W., Park, C.Y., Cho, J., Kang, Y., and Ahn, J.M. (2020). Clinical validity of two different grading systems for lumbar central canal stenosis: Schizas and Lee classification systems. PLoS ONE, 15.","DOI":"10.1371\/journal.pone.0233633"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"869","DOI":"10.1007\/s00586-024-08612-z","article-title":"Inter-observer variability in the classification of lumbar foraminal stenosis in magnetic resonance imaging using different evaluation scales","volume":"34","author":"Pereira","year":"2025","journal-title":"Eur. Spine J."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"174","DOI":"10.1148\/radiol.12111930","article-title":"Radiologic criteria for the diagnosis of spinal stenosis: Results of a Delphi survey","volume":"264","author":"Mamisch","year":"2012","journal-title":"Radiology"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"W735","DOI":"10.2214\/AJR.12.10163","article-title":"A systematic review of semiquantitative and qualitative radiologic criteria for the diagnosis of lumbar spinal stenosis","volume":"201","author":"Andreisek","year":"2013","journal-title":"AJR Am. J. Roentgenol."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Walsh, P.J., Lee, U.J., Lipetz, J.S., and Walz, D.M. (2026). Improving reliability of MRI lumbar spinal stenosis assessment across radiology and spine specialties: Impact of a structured education intervention. Acad. Radiol.","DOI":"10.1016\/j.acra.2026.06.021"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"E179","DOI":"10.1097\/BRS.0000000000005174","article-title":"Performance of artificial intelligence in diagnosing lumbar spinal stenosis: A systematic review and meta-analysis","volume":"50","author":"Yang","year":"2025","journal-title":"Spine"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1148\/radiol.2021204289","article-title":"Deep learning model for automated detection and classification of central canal, lateral recess, and neural foraminal stenosis at lumbar spine MRI","volume":"300","author":"Hallinan","year":"2021","journal-title":"Radiology"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"941","DOI":"10.1007\/s00586-023-08089-2","article-title":"A neural network model for detection and classification of lumbar spinal stenosis on MRI","volume":"33","author":"Tumko","year":"2024","journal-title":"Eur. Spine J."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Phadke, R.A., Salman, S.G., Salman, Z.G., Yedupati, S.M., Ong, J., Tavakkoli, A., Galhotra, S., Tripuraneni, A., and Rizkalla, J. (2026). Deep learning-based multi-class pediatric wrist fracture subtype classification: A pilot study comparing convolutional neural network architectures. J. Imaging, 12.","DOI":"10.3390\/jimaging12070307"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"548","DOI":"10.1007\/s00586-025-09443-2","article-title":"Deep learning models for lumbar spinal stenosis on MRI: Model comparison and clinical benchmarking","volume":"35","author":"Lee","year":"2026","journal-title":"Eur. Spine J."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Kumar, R., Kaur, H., Sporn, K., Salman, S.G., Phadke, R., Sarnala, S., Vaja, S., Lee, N.J., and Lee, N.J. (2026). Advancing spine connectomics and neural integration through machine learning and neuroengineering: A narrative review. Eur. Spine J.","DOI":"10.1007\/s00586-026-10215-9"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"105472","DOI":"10.1016\/j.compbiomed.2022.105472","article-title":"Grading diabetic retinopathy and prostate cancer diagnostic images with deep quantum ordinal regression","volume":"145","author":"Useche","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1016\/j.compmedimag.2019.06.002","article-title":"Fully automatic knee osteoarthritis severity grading using deep neural networks with a novel ordinal loss","volume":"75","author":"Chen","year":"2019","journal-title":"Comput. Med. Imaging Graph."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1605","DOI":"10.1097\/BRS.0b013e3181791af3","article-title":"Reliability of readings of magnetic resonance imaging features of lumbar spinal stenosis","volume":"33","author":"Lurie","year":"2008","journal-title":"Spine"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"3319","DOI":"10.1007\/s00586-021-06944-8","article-title":"Quantitative correlation of lumbar foraminal stenosis with local morphological metrics","volume":"30","author":"Gunasekaran","year":"2021","journal-title":"Eur. Spine J."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Salman, S.G., Phadke, R., Kumar, R., Zaman, N., and Tavakkoli, A. (2026). Digital twins and multimodal artificial intelligence in spine care: A scoping review of concepts, evidence, and translational barriers. Spine Deform.","DOI":"10.1007\/s43390-026-01397-9"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Salman, S., Phadke, R., Kumar, R., Momin, A., and Tavakkoli, A. (2026). Risk prediction in spine surgery: A scoping review of traditional models, artificial intelligence, and the challenge of clinical translation. Spine Deform.","DOI":"10.1007\/s43390-026-01365-3"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"113301","DOI":"10.1016\/j.injury.2026.113301","article-title":"The fracture orthopedic risk of non-home discharge (FORD) score: A novel bedside predictive tool for non-home discharge in orthopedic trauma patients","volume":"57","author":"Salman","year":"2026","journal-title":"Injury"}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/8\/388\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T11:35:02Z","timestamp":1787139302000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/8\/388"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,19]]},"references-count":35,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["jimaging12080388"],"URL":"https:\/\/doi.org\/10.3390\/jimaging12080388","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,19]]}}}