{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,2]],"date-time":"2026-11-02T01:05:47Z","timestamp":1793581547859,"version":"4.5.0"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T00:00:00Z","timestamp":1742774400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T00:00:00Z","timestamp":1742774400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"the Macao Young Scholars Programme","award":["AM2023022"],"award-info":[{"award-number":["AM2023022"]}]},{"name":"the Natural Science Foundation of Shandong Province","award":["ZR2023QH033"],"award-info":[{"award-number":["ZR2023QH033"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Radiol med"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:sec>\n            <jats:title>Purpose<\/jats:title>\n            <jats:p>Application of a deep learning model visualization plugin for rapid and accurate automatic quantification and classification of lumbar disc herniation (LDH) types on axial T2-weighted MRIs.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Methods<\/jats:title>\n            <jats:p>Retrospective analysis of 2500 patients, with the training set comprising data from 2120 patients (25,554 images), an internal test set covering data from 80 patients (784 images), and an external test set including data from 300 patients (3285 images). To enhance implementation, this study categorized normal and bulging discs as a grade without significant abnormalities, defining the region and severity grades of LDH based on the relationship between the disc and the spinal canal. The automated detection training and validation process employed the YOLOv8 object detection model for target area localization, the YOLOv8-seg segmentation model for disc recognition, and the YOLOv8-pose keypoint detection model for positioning. Finally, the stability of the detection results was verified using metrics such as Intersection over Union (IoU), mean error (ME), precision (P), F1 score (F1), Kappa coefficient (kappa), and 95% confidence interval (95%CI).<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Results<\/jats:title>\n            <jats:p>The segmentation model achieved an mAP50:95 of 98.12% and an IoU of 98.36% in the training set, while the keypoint detection model achieved an mAP50:95 of 93.58% with a mean error (ME) of 0.208\u00a0mm. For the internal and external test sets, the segmentation model\u2019s IoU was 97.58 and 97.49%, respectively, while the keypoint model\u2019s ME was 0.219\u00a0mm and 0.221\u00a0mm, respectively. In the quantification validation of the extent of LDH, P, F1, and kappa were measured. For LDH classification (18 categories), the internal and external test sets showed <jats:italic>P<\/jats:italic>\u2009=\u200981.21% and 74.50%, F1\u2009=\u200981.26% and 74.42%, and kappa\u2009=\u20090.75 (95%CI 0.68, 0.82, <jats:italic>p<\/jats:italic>\u2009=\u20090.00) and 0.69 (95%CI 0.65, 0.73, <jats:italic>p<\/jats:italic>\u2009=\u20090.00), respectively. For the severity grades of LDH (four categories), the internal and external test sets showed <jats:italic>P<\/jats:italic>\u2009=\u200992.51% and 90.07%, F1\u2009=\u200992.36% and 89.66%, and kappa\u2009=\u20090.88 (95%CI 0.80, 0.96, <jats:italic>p<\/jats:italic>\u2009=\u20090.00) and 0.85 (95%CI 0.81, 0.89, <jats:italic>p<\/jats:italic>\u2009=\u20090.00), respectively. For the regions of LDH (eight categories), the internal and external test sets showed <jats:italic>P<\/jats:italic>\u2009=\u200983.34% and 77.87%, F1\u2009=\u200983.85% and 78.21%, and kappa\u2009=\u20090.77 (95%CI 0.70, 0.85, <jats:italic>p<\/jats:italic>\u2009=\u20090.00) and 0.71 (95%CI 0.67, 0.75, <jats:italic>p<\/jats:italic>\u2009=\u20090.00), respectively.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Conclusion<\/jats:title>\n            <jats:p>The automated aided diagnostic model achieved high performance in detecting and classifying LDH and demonstrated substantial consistency with expert classification.<\/jats:p>\n          <\/jats:sec>","DOI":"10.1007\/s11547-025-01996-y","type":"journal-article","created":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T02:56:21Z","timestamp":1742871381000},"page":"795-804","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Quantification and classification of lumbar disc herniation on axial magnetic resonance images using deep learning models"],"prefix":"10.1007","volume":"130","author":[{"given":"Elzat Elham-Yilizati","family":"Yilihamu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Shang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhi-Hai","family":"Su","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin-Tao","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kun","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hai","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1388-6302","authenticated-orcid":false,"given":"Shi-Qing","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,3,24]]},"reference":[{"key":"1996_CR1","doi-asserted-by":"publisher","first-page":"299","DOI":"10.21037\/atm.2020.02.175","volume":"8","author":"A Wu","year":"2020","unstructured":"Wu A, March L, Zheng X et al (2020) Global low back pain prevalence and years lived with disability from 1990 to 2017: estimates from the Global Burden of Disease Study 2017. Ann Transl Med 8:299. https:\/\/doi.org\/10.21037\/atm.2020.02.175","journal-title":"Ann Transl Med"},{"key":"1996_CR2","doi-asserted-by":"publisher","first-page":"2302","DOI":"10.1016\/S0140-6736(18)30725-6","volume":"391","author":"S Clark","year":"2018","unstructured":"Clark S, Horton R (2018) Low back pain: a major global challenge. Lancet 391:2302. https:\/\/doi.org\/10.1016\/S0140-6736(18)30725-6","journal-title":"Lancet"},{"key":"1996_CR3","doi-asserted-by":"publisher","first-page":"e1066","DOI":"10.1002\/jsp2.1066","volume":"3","author":"I Ogon","year":"2020","unstructured":"Ogon I, Takebayashi T, Takashima H et al (2020) Imaging diagnosis for intervertebral disc. JOR Spine 3:e1066. https:\/\/doi.org\/10.1002\/jsp2.1066","journal-title":"JOR Spine"},{"key":"1996_CR4","doi-asserted-by":"publisher","first-page":"2525","DOI":"10.1016\/j.spinee.2014.04.022","volume":"14","author":"DF Fardon","year":"2014","unstructured":"Fardon DF, Williams AL, Dohring EJ et al (2014) Lumbar disc nomenclature: version 2.0: recommendations of the combined task forces of the North American Spine Society, the American Society of Spine Radiology and the American Society of Neuroradiology. Spine J 14:2525\u20132545. https:\/\/doi.org\/10.1016\/j.spinee.2014.04.022","journal-title":"Spine J"},{"key":"1996_CR5","doi-asserted-by":"publisher","first-page":"811","DOI":"10.3174\/ajnr.A4173","volume":"36","author":"W Brinjikji","year":"2015","unstructured":"Brinjikji W, Luetmer PH, Comstock B et al (2015) Systematic literature review of imaging features of spinal degeneration in asymptomatic populations. Am J Neuroradiol 36:811\u2013816. https:\/\/doi.org\/10.3174\/ajnr.A4173","journal-title":"Am J Neuroradiol"},{"key":"1996_CR6","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1148\/radiol.2021204289","volume":"300","author":"JTPD Hallinan","year":"2021","unstructured":"Hallinan JTPD, Zhu L, Yang K et al (2021) Deep learning model for automated detection and classification of central canal, lateral recess, and neural foraminal stenosis at lumbar spine MRI. Radiology 300:130\u2013138. https:\/\/doi.org\/10.1148\/radiol.2021204289","journal-title":"Radiology"},{"key":"1996_CR7","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1148\/radiol.220076","volume":"305","author":"DSW Lim","year":"2022","unstructured":"Lim DSW, Makmur A, Zhu L et al (2022) Improved productivity using deep learning-assisted reporting for lumbar spine MRI. Radiology 305:160\u2013166. https:\/\/doi.org\/10.1148\/radiol.220076","journal-title":"Radiology"},{"key":"1996_CR8","doi-asserted-by":"publisher","first-page":"e1276","DOI":"10.1002\/jsp2.1276","volume":"6","author":"W Zhang","year":"2023","unstructured":"Zhang W, Chen Z, Su Z et al (2023) Deep learning-based detection and classification of lumbar disc herniation on magnetic resonance images. JOR Spine 6:e1276. https:\/\/doi.org\/10.1002\/jsp2.1276","journal-title":"JOR Spine"},{"key":"1996_CR9","doi-asserted-by":"publisher","first-page":"1087","DOI":"10.1007\/s00586-009-1274-4","volume":"19","author":"LW Mysliwiec","year":"2010","unstructured":"Mysliwiec LW, Cholewicki J, Winkelpleck MD, Eis GP (2010) MSU classification for herniated lumbar discs on MRI: toward developing objective criteria for surgical selection. Eur Spine J 19:1087\u20131093. https:\/\/doi.org\/10.1007\/s00586-009-1274-4","journal-title":"Eur Spine J"},{"key":"1996_CR10","doi-asserted-by":"publisher","DOI":"10.7860\/JCDR\/2022\/52935.15871","author":"QT Alshammari","year":"2022","unstructured":"Alshammari QT, Soundararajan LRA, Thankappan SM, Alshammari MT (2022) Correlation between pain, disability and levels of disc herniation in michigan state university grade-3 disc prolapsed patients using magnetic resonance imaging: a cross-sectional study. JCDR. https:\/\/doi.org\/10.7860\/JCDR\/2022\/52935.15871","journal-title":"JCDR"},{"key":"1996_CR11","doi-asserted-by":"publisher","first-page":"3590","DOI":"10.1109\/TMI.2023.3294248","volume":"42","author":"S Lu","year":"2023","unstructured":"Lu S, Liu J, Wang X, Zhou Y (2023) Collaborative multi-metadata fusion to improve the classification of lumbar disc herniation. IEEE Trans Med Imaging 42:3590\u20133601. https:\/\/doi.org\/10.1109\/TMI.2023.3294248","journal-title":"IEEE Trans Med Imaging"},{"key":"1996_CR12","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1038\/s41586-023-06291-2","volume":"620","author":"K Singhal","year":"2023","unstructured":"Singhal K, Azizi S, Tu T et al (2023) Large language models encode clinical knowledge. Nature 620:172\u2013180. https:\/\/doi.org\/10.1038\/s41586-023-06291-2","journal-title":"Nature"},{"key":"1996_CR13","doi-asserted-by":"publisher","first-page":"1044525","DOI":"10.3389\/fpubh.2023.1044525","volume":"11","author":"J Xuan","year":"2023","unstructured":"Xuan J, Ke B, Ma W et al (2023) Spinal disease diagnosis assistant based on MRI images using deep transfer learning methods. Front Public Health 11:1044525. https:\/\/doi.org\/10.3389\/fpubh.2023.1044525","journal-title":"Front Public Health"},{"key":"1996_CR14","doi-asserted-by":"publisher","first-page":"105278","DOI":"10.1016\/j.bspc.2023.105278","volume":"86","author":"H Li","year":"2023","unstructured":"Li H, Wang Z, Shen W et al (2023) SSCK-Net: Spine segmentation in MRI based on cross attention and key-points recognition-assisted learner. Biomed Signal Process Control 86:105278. https:\/\/doi.org\/10.1016\/j.bspc.2023.105278","journal-title":"Biomed Signal Process Control"},{"key":"1996_CR15","doi-asserted-by":"publisher","first-page":"e135","DOI":"10.1016\/j.wneu.2023.07.009","volume":"178","author":"AN Laiwalla","year":"2023","unstructured":"Laiwalla AN, Ratnaparkhi A, Zarrin D et al (2023) Lumbar spinal canal segmentation in cases with lumbar stenosis using deep-U-net ensembles. World Neurosurg 178:e135\u2013e140. https:\/\/doi.org\/10.1016\/j.wneu.2023.07.009","journal-title":"World Neurosurg"},{"key":"1996_CR16","doi-asserted-by":"publisher","first-page":"841","DOI":"10.1038\/s41467-022-28387-5","volume":"13","author":"H-D Zheng","year":"2022","unstructured":"Zheng H-D, Sun Y-L, Kong D-W et al (2022) Deep learning-based high-accuracy quantitation for lumbar intervertebral disc degeneration from MRI. Nat Commun 13:841. https:\/\/doi.org\/10.1038\/s41467-022-28387-5","journal-title":"Nat Commun"},{"key":"1996_CR17","doi-asserted-by":"publisher","first-page":"9687591","DOI":"10.1155\/2021\/9687591","volume":"2021","author":"F Gao","year":"2021","unstructured":"Gao F, Wu M (2021) Deep learning-based denoised MRI images for correlation analysis between lumbar facet joint and lumbar disc herniation in spine surgery. J Healthc Eng 2021:9687591. https:\/\/doi.org\/10.1155\/2021\/9687591","journal-title":"J Healthc Eng"},{"key":"1996_CR18","doi-asserted-by":"publisher","first-page":"799","DOI":"10.1002\/jmri.27400","volume":"53","author":"F Gao","year":"2021","unstructured":"Gao F, Liu S, Zhang X et al (2021) Automated grading of lumbar disc degeneration using a push-pull regularization network based on MRI. J Magn Reson Imaging 53:799\u2013806. https:\/\/doi.org\/10.1002\/jmri.27400","journal-title":"J Magn Reson Imaging"},{"key":"1996_CR19","unstructured":"mmyolo\/configs\/yolov8 at main open-mmlab\/mmyolo \u00b7 GitHub. https:\/\/github.com\/open-mmlab\/mmyolo\/tree\/main\/configs\/yolov8. Accessed 28 Aug 2023"},{"key":"1996_CR20","doi-asserted-by":"publisher","first-page":"224","DOI":"10.3348\/kjr.2022.0351","volume":"24","author":"J Seo","year":"2023","unstructured":"Seo J, Lee JW (2023) Magnetic resonance imaging grading systems for central canal and neural foraminal stenoses of the lumbar and cervical spines with a focus on the lee grading system. Korean J Radiol 24:224\u2013234. https:\/\/doi.org\/10.3348\/kjr.2022.0351","journal-title":"Korean J Radiol"},{"key":"1996_CR21","doi-asserted-by":"publisher","first-page":"1896","DOI":"10.1007\/s11999-014-3674-y","volume":"473","author":"Y Li","year":"2015","unstructured":"Li Y, Fredrickson V, Resnick DK (2015) How should we grade lumbar disc herniation and nerve root compression? A systematic review. Clin Orthop Relat Res 473:1896\u20131902. https:\/\/doi.org\/10.1007\/s11999-014-3674-y","journal-title":"Clin Orthop Relat Res"},{"key":"1996_CR22","doi-asserted-by":"publisher","DOI":"10.3389\/fbioe.2021.708137","author":"J-Y Tsai","year":"2021","unstructured":"Tsai J-Y, Hung IY-J, Guo YL et al (2021) Lumbar disc herniation automatic detection in magnetic resonance imaging based on deep learning. Front Bioeng Biotechnol. https:\/\/doi.org\/10.3389\/fbioe.2021.708137","journal-title":"Front Bioeng Biotechnol"},{"key":"1996_CR23","doi-asserted-by":"publisher","first-page":"1534","DOI":"10.1097\/00007632-199707010-00023","volume":"22","author":"LL Wiltse","year":"1997","unstructured":"Wiltse LL, Berger PE, McCulloch JA (1997) A system for reporting the size and location of lesions in the spine. Spine 22:1534\u20131537. https:\/\/doi.org\/10.1097\/00007632-199707010-00023","journal-title":"Spine"},{"key":"1996_CR24","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1007\/978-3-319-07269-2_8","volume-title":"Computational methods and clinical applications for spine imaging","author":"RS Alomari","year":"2014","unstructured":"Alomari RS, Corso JJ, Chaudhary V, Dhillon G (2014) Lumbar spine disc herniation diagnosis with a joint shape model. In: Yao J, Klinder T, Li S (eds) Computational methods and clinical applications for spine imaging. Springer International Publishing, Cham, pp 87\u201398"},{"key":"1996_CR25","doi-asserted-by":"publisher","first-page":"262","DOI":"10.1109\/TMI.2020.3025087","volume":"40","author":"S Pang","year":"2021","unstructured":"Pang S, Pang C, Zhao L et al (2021) SpineParseNet: spine parsing for volumetric MR image by a two-stage segmentation framework with semantic image representation. IEEE Trans Med Imaging 40:262\u2013273. https:\/\/doi.org\/10.1109\/TMI.2020.3025087","journal-title":"IEEE Trans Med Imaging"},{"key":"1996_CR26","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics11050902","author":"NC Lehnen","year":"2021","unstructured":"Lehnen NC, Haase R, Faber J et al (2021) Detection of degenerative changes on MR images of the lumbar spine with a convolutional neural network: a feasibility study. Diagnostics. https:\/\/doi.org\/10.3390\/diagnostics11050902","journal-title":"Diagnostics"},{"key":"1996_CR27","doi-asserted-by":"publisher","first-page":"e210015","DOI":"10.1148\/ryai.2021210015","volume":"4","author":"A Suri","year":"2022","unstructured":"Suri A, Jones BC, Ng G et al (2022) Vertebral deformity measurements at MRI, CT, and radiography using deep learning. Radiol Artif Intell 4:e210015. https:\/\/doi.org\/10.1148\/ryai.2021210015","journal-title":"Radiol Artif Intell"},{"key":"1996_CR28","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-89102-w","author":"A Cina","year":"2021","unstructured":"Cina A, Bassani T, Panico M et al (2021) 2-step deep learning model for landmarks localization in spine radiographs. Sci Rep. https:\/\/doi.org\/10.1038\/s41598-021-89102-w","journal-title":"Sci Rep"}],"container-title":["La radiologia medica"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11547-025-01996-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11547-025-01996-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11547-025-01996-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T09:53:22Z","timestamp":1750672402000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11547-025-01996-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,24]]},"references-count":28,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,6]]}},"alternative-id":["1996"],"URL":"https:\/\/doi.org\/10.1007\/s11547-025-01996-y","relation":{},"ISSN":["1826-6983"],"issn-type":[{"value":"1826-6983","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,24]]},"assertion":[{"value":"6 June 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 March 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 March 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no relevant financial or non-financial interests to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interests"}},{"value":"This study was approved by the Ethics Committee of Tianjin Medical University General Hospital (IRB2022-YX-213-01), the Second Hospital of Shandong University (KYLL-2023-324), Fifth Affiliated Hospital of Sun Yat-sen University (K53-1).","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"All the authors in this paper consent to publication of the work.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to publish"}}]}}