{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,19]],"date-time":"2026-11-19T22:43:27Z","timestamp":1795128207552,"version":"4.10.3"},"reference-count":32,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2022,6,6]],"date-time":"2022-06-06T00:00:00Z","timestamp":1654473600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Endocrinol."],"abstract":"<jats:sec>\n                    <jats:title>Aim<\/jats:title>\n                    <jats:p>Accurate severity grading of lumbar spine disease by magnetic resonance images (MRIs) plays an important role in selecting appropriate treatment for the disease. However, interpreting these complex MRIs is a repetitive and time-consuming workload for clinicians, especially radiologists. Here, we aim to develop a multi-task classification model based on artificial intelligence for automated grading of lumbar disc herniation (LDH), lumbar central canal stenosis (LCCS) and lumbar nerve roots compression (LNRC) at lumbar axial MRIs.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Total 15254 lumbar axial T2W MRIs as the internal dataset obtained from the Fifth Affiliated Hospital of Sun Yat-sen University from January 2015 to May 2019 and 1273 axial T2W MRIs as the external test dataset obtained from the Third Affiliated Hospital of Southern Medical University from June 2016 to December 2017 were analyzed in this retrospective study. Two clinicians annotated and graded all MRIs using the three international classification systems. In agreement, these results served as the reference standard; In disagreement, outcomes were adjudicated by an expert surgeon to establish the reference standard. The internal dataset was randomly split into an internal training set (70%), validation set (15%) and test set (15%). The multi-task classification model based on ResNet-50 consists of a backbone network for feature extraction and three fully-connected (FC) networks for classification and performs the classification tasks of LDH, LCCS, and LNRC at lumbar MRIs. Precision, accuracy, sensitivity, specificity, F1 scores, confusion matrices, receiver-operating characteristics and interrater agreement (Gwet k) were utilized to assess the model\u2019s performance on the internal test dataset and external test datasets.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>A total of 1115 patients, including 1015 patients from the internal dataset and 100 patients from the external test dataset [mean age, 49 years \u00b1 15 (standard deviation); 543 women], were evaluated in this study. The overall accuracies of grading for LDH, LCCS and LNRC were 84.17% (74.16%), 86.99% (79.65%) and 81.21% (74.16%) respectively on the internal (external) test dataset. Internal and external testing of three spinal diseases showed substantial to the almost perfect agreement (k, 0.67 - 0.85) for the multi-task classification model.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The multi-task classification model has achieved promising performance in the automated grading of LDH, LCCS and LNRC at lumbar axial T2W MRIs.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fendo.2022.890371","type":"journal-article","created":{"date-parts":[[2022,6,6]],"date-time":"2022-06-06T02:48:01Z","timestamp":1654483681000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":57,"title":["Automatic Grading of Disc Herniation, Central Canal Stenosis and Nerve Roots Compression in Lumbar Magnetic Resonance Image Diagnosis"],"prefix":"10.3389","volume":"13","author":[{"given":"Zhi-Hai","family":"Su","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min-Sheng","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zi-Yang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ke","family":"You","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng-Jie","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qing-Hao","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"En-Qing","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qian-Jin","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shu-Mao","family":"Pang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shao-Lin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hai","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2022,6,6]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1016\/s0140-6736(21)00733-9","article-title":"Low Back Pain","volume":"398","author":"Knezevic","year":"2021","journal-title":"Lancet"},{"key":"B2","doi-asserted-by":"publisher","first-page":"743","DOI":"10.1016\/s0140-6736(15)60692-4","article-title":"Global, Regional, and National Incidence, Prevalence, and Years Lived With Disability for 301 Acute and Chronic Diseases and Injuries in 188 Countries, 1990-2013: A Systematic Analysis for the Global Burden of Disease Study 2013","volume":"386","year":"2015","journal-title":"Lancet (London England)"},{"key":"B3","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1097\/00007632-198401000-00004","article-title":"Pathoanatomy and Pathophysiology of Nerve Root Compression","volume":"9","author":"Rydevik","year":"1984","journal-title":"Spine (Phila Pa 1976)"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.7326\/m16-2367","article-title":"Noninvasive Treatments for Acute, Subacute, and Chronic Low Back Pain: A Clinical Practice Guideline From the American College of Physicians","volume":"166","author":"Qaseem","year":"2017","journal-title":"Ann Intern Med"},{"key":"B5","doi-asserted-by":"publisher","first-page":"Cd010264","DOI":"10.1002\/14651858.CD010264.pub2","article-title":"Surgical Versus non-Surgical Treatment for Lumbar Spinal Stenosis","volume":"2016","author":"Zaina","year":"2016","journal-title":"Cochrane Database Syst Rev"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1483","DOI":"10.3390\/ijms21041483","article-title":"Lumbar Degenerative Disease Part 1: Anatomy and Pathophysiology of Intervertebral Discogenic Pain and Radiofrequency Ablation of Basivertebral and Sinuvertebral Nerve Treatment for Chronic Discogenic Back Pain: A Prospective Case Series and Review of Literature","volume":"21","author":"Kim","year":"2020","journal-title":"Int J Mol Sci"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1007\/s00586-009-1274-4","article-title":"MSU Classification for Herniated Lumbar Discs on MRI: Toward Developing Objective Criteria for Surgical Selection","volume":"19","author":"Mysliwiec","year":"2010","journal-title":"Eur Spine J"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1590\/1413-785220182606201444","article-title":"Reliability of the Michigan State University (MSU) Classification of Lumbar Disc Herniation","volume":"26","author":"Kaliya-Perumal","year":"2018","journal-title":"Acta Ortop Bras"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1007\/s00256-011-1102-x","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":"Skeletal Radiol"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2302021289","article-title":"MR Image-Based Grading of Lumbar Nerve Root Compromise Due to Disk Herniation: Reliability Study With Surgical Correlation","volume":"230","author":"Pfirrmann","year":"2004","journal-title":"Radiology"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.3348\/kjr.2017.18.1.249","article-title":"Diagnosis of Nerve Root Compromise of the Lumbar Spine: Evaluation of the Performance of Three-Dimensional Isotropic T2-Weighted Turbo Spin-Echo SPACE Sequence at 3T","volume":"18","author":"Sung","year":"2017","journal-title":"Korean J Radiol"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1016\/j.acra.2015.05.007","article-title":"The Effects of Changes in Utilization and Technological Advancements of Cross-Sectional Imaging on Radiologist Workload","volume":"22","author":"McDonald","year":"2015","journal-title":"Acad Radiol"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1038\/s41568-018-0016-5","article-title":"Artificial Intelligence in Radiology","volume":"18","author":"Hosny","year":"2018","journal-title":"Nat Rev Cancer"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1097\/brs.0000000000003377","article-title":"Spinal Stenosis Grading in Magnetic Resonance Imaging Using Deep Convolutional Neural Networks","volume":"45","author":"Won","year":"2020","journal-title":"Spine (Phila Pa 1976)"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1016\/j.spinee.2021.03.006","article-title":"Using Artificial Intelligence to Diagnose Fresh Osteoporotic Vertebral Fractures on Magnetic Resonance Images","volume":"21","author":"Yabu","year":"2021","journal-title":"Spine J"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.3389\/fbioe.2021.708137","article-title":"Lumbar Disc Herniation Automatic Detection in Magnetic Resonance Imaging Based on Deep Learning","volume":"9","author":"Tsai","year":"2021","journal-title":"Front Bioeng Biotechnol"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1007\/s12021-018-9365-1","article-title":"Automated Pathogenesis-Based Diagnosis of Lumbar Neural Foraminal Stenosis via Deep Multiscale Multitask Learning","volume":"16","author":"Han","year":"2018","journal-title":"Neuroinformatics"},{"key":"B18","article-title":"Deep Spine: Automated Lumbar Vertebral Segmentation, Disc-Level Designation, and Spinal Stenosis Grading Using Deep Learning","volume":"85","author":"Lu","year":"2018","journal-title":"Proceedings of Machine Learning Research. PMLR 2018: Proceedings of the 3rd Machine Learning for Healthcare Conference."},{"key":"B19","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1186\/s12891-020-3070-6","article-title":"Association Between Lumbar Disc Herniation and Facet Joint Osteoarthritis","volume":"21","author":"Zhu","year":"2020","journal-title":"BMC Musculoskelet Disord"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1259\/bjr.20120180","article-title":"Clinical Correlation of a New Practical MRI Method for Assessing Central Lumbar Spinal Stenosis","volume":"86","author":"Park","year":"2013","journal-title":"Br J Radiol"},{"key":"B21","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1348\/000711006x126600","article-title":"Computing Inter-Rater Reliability and its Variance in the Presence of High Agreement","volume":"61","author":"Gwet","year":"2008","journal-title":"Br J Math Stat Psychol"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2288-13-61","article-title":"A Comparison of Cohen's Kappa and Gwet's AC1 When Calculating Inter-Rater Reliability Coefficients: A Study Conducted With Personality Disorder Samples","volume":"13","author":"Wongpakaran","year":"2013","journal-title":"BMC Med Res Methodol"},{"key":"B23","article-title":"IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2016","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition","author":"S","year":"2016"},{"key":"B24","first-page":"1013443","article-title":"International Society for Optics andPhotonics","volume-title":"SPIE 2017: Proceedings Volume 10134, Medical Imaging: Computer-Aided Diagnosis","author":"He","year":"2017"},{"key":"B25","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1016\/j.media.2017.07.002","article-title":"SpineNet: Automated Classification and Evidence Visualization in Spinal MRIs","volume":"41","author":"Jamaludin","year":"2017","journal-title":"Med Image Anal"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1097\/00007632-200109010-00011","article-title":"Magnetic Resonance Classification of Lumbar Intervertebral Disc Degeneration","volume":"26","author":"Pfirrmann","year":"2001","journal-title":"Spine (Phila Pa 1976)"},{"key":"B27","doi-asserted-by":"publisher","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":"B28","doi-asserted-by":"publisher","first-page":"902","DOI":"10.3390\/diagnostics11050902","article-title":"Detection of Degenerative Changes on MR Images of the Lumbar Spine With a Convolutional Neural Network: A Feasibility Study","volume":"11","author":"Lehnen","year":"2021","journal-title":"Diagn (Basel)"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.14444\/8068","article-title":"Prognostic Value of Michigan State University (MSU) Classification for Lumbar Disc Herniation: Is It Suitable for Surgical Selection","volume":"15","author":"d'Ercole","year":"2021","journal-title":"Int J Spine Surg"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1111\/papr.12878","article-title":"A Novel Combination Technique: Three Points of Epiduroscopic Laser Neural Decompression and Percutaneous Laser Disc Decompression With the Ho:YAG Laser in an MSU Classification 3ab Herniated Disc","volume":"20","author":"Beyaz","year":"2020","journal-title":"Pain Pract"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0233633","article-title":"Clinical Validity of Two Different Grading Systems for Lumbar Central Canal Stenosis: Schizas and Lee Classification Systems","volume":"15","author":"Ko","year":"2020","journal-title":"PloS One"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1007\/s11999-014-3674-y","article-title":"How Should We Grade Lumbar Disc Herniation and Nerve Root Compression","volume":"473","author":"Li","year":"2015","journal-title":"A Systematic Rev Clin Orthop Relat Res"}],"container-title":["Frontiers in Endocrinology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2022.890371\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,6]],"date-time":"2022-06-06T02:48:05Z","timestamp":1654483685000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2022.890371\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,6]]},"references-count":32,"alternative-id":["10.3389\/fendo.2022.890371"],"URL":"https:\/\/doi.org\/10.3389\/fendo.2022.890371","relation":{"has-part":[{"id-type":"doi","id":"https:\/\/doi.org\/10.3389\/fendo.2022.890371.s001","asserted-by":"subject"}]},"ISSN":["1664-2392"],"issn-type":[{"value":"1664-2392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,6,6]]},"article-number":"890371"}}