{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T05:49:16Z","timestamp":1782452956342,"version":"3.54.5"},"reference-count":38,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T00:00:00Z","timestamp":1782432000000},"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. Med."],"abstract":"<jats:p>Automated lumbar spine MRI analysis has made notable progress in recent years, yet existing methods still suffer from anatomical ambiguity, insufficient use of explicit structural priors, and limited modeling of inter-level degenerative dependency, which restrict their reliability for clinically meaningful burden assessment. To address these limitations, we propose an anatomy-guided, multi-sequence, multi-level deep learning framework for lumbar degenerative disease grading and patient-level risk assessment. First, an anatomical parsing module is pre-trained to segment vertebral bodies, intervertebral discs, and the spinal canal, providing stable level localization and structural priors for downstream analysis. Then, the localized multi-sequence MRI patches and quantitative anatomical biomarkers are jointly encoded and further modeled by a lightweight Transformer to capture contextual dependency across lumbar levels, enabling both segment-level ordinal grading and Clinically Significant Degeneration Score (CSDS)-based patient-level burden assessment. Extensive experiments on public datasets demonstrate that the proposed framework achieves superior performance over representative baselines, reaching a Macro F1-score of 0.783 \u00b1 0.010, a Cohen's Kappa of 0.765 \u00b1 0.012, a weighted log loss of 0.463 \u00b1 0.018, and a patient-level AUC of 0.891 \u00b1 0.009, while supplementary evaluations further verify the robustness of the anatomical parsing stage. The ablation results show that anatomy-guided cropping, quantitative biomarker fusion, spine-context modeling, and consistency regularization each contribute complementary gains, confirming that the effectiveness of the framework arises from their coordinated interaction rather than from any single component alone. Overall, these findings indicate that explicitly integrating anatomical priors, structured biomarkers, and multilevel context can substantially improve both diagnostic accuracy and interpretability, while also supporting more standardized, transparent, and human-centered lumbar MRI assessment in radiological practice.<\/jats:p>","DOI":"10.3389\/fmed.2026.1848548","type":"journal-article","created":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T05:44:05Z","timestamp":1782452645000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Anatomy-guided context-aware deep learning for lumbar degenerative disease grading and burden-aware risk assessment on MRI"],"prefix":"10.3389","volume":"13","author":[{"given":"Zhijin","family":"Chai","sequence":"first","affiliation":[{"name":"Lianyungang Clinical College of Nanjing Medical University","place":["Lianyungang, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Liu","sequence":"additional","affiliation":[{"name":"Lianyungang Clinical College of Nanjing Medical University","place":["Lianyungang, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rujie","family":"Qin","sequence":"additional","affiliation":[{"name":"Lianyungang Clinical College of Nanjing Medical University","place":["Lianyungang, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dexuan","family":"Zhao","sequence":"additional","affiliation":[{"name":"The Affiliated Lianyungang Hospital of Xuzhou Medical University","place":["Lianyungang, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ankang","family":"Shi","sequence":"additional","affiliation":[{"name":"The Affiliated Lianyungang Hospital of Xuzhou Medical University","place":["Lianyungang, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,6,26]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"e54676","DOI":"10.2196\/54676","article-title":"Machine learning and deep learning for diagnosis of lumbar spinal stenosis: systematic review and meta-analysis","volume":"26","author":"Wang","year":"2024","journal-title":"J Med Internet Res"},{"key":"B2","doi-asserted-by":"publisher","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":"B3","doi-asserted-by":"publisher","first-page":"3435","DOI":"10.1007\/s00330-023-09483-6","article-title":"Deep learning for automated, interpretable classification of lumbar spinal stenosis and facet arthropathy from axial MRI","volume":"33","author":"Bharadwaj","year":"2023","journal-title":"Eur Radiol"},{"key":"B4","doi-asserted-by":"publisher","first-page":"2113","DOI":"10.1148\/rg.2017170077","article-title":"Deep learning: a primer for radiologists","volume":"37","author":"Chartrand","year":"2017","journal-title":"RadioGraph"},{"key":"B5","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":"B6","doi-asserted-by":"publisher","first-page":"2137","DOI":"10.1007\/s00586-022-07311-x","article-title":"External validation of the deep learning system \u201cSpineNet\u201d for grading radiological features of degeneration on MRIs of the lumbar spine","volume":"31","author":"Grob","year":"2022","journal-title":"Eur Spine J"},{"key":"B7","doi-asserted-by":"publisher","first-page":"100564","DOI":"10.1016\/j.xnsj.2024.100564","article-title":"External validation of SpineNetV2 on a comprehensive set of radiological features for grading lumbosacral disc pathologies","volume":"20","author":"Nigru","year":"2024","journal-title":"North Am Spine Soc J"},{"key":"B8","doi-asserted-by":"publisher","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":"B9","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1038\/s41597-024-03090-w","article-title":"Lumbar spine segmentation in MR images: a dataset and a public benchmark","volume":"11","author":"van der Graaf","year":"2024","journal-title":"Sci Data"},{"key":"B10","doi-asserted-by":"publisher","first-page":"1178","DOI":"10.1007\/s00330-024-11155-y","article-title":"SPINEPS\u2013automatic whole spine segmentation of T2-weighted MR images using a two-phase approach to multi-class semantic and instance segmentation","volume":"35","author":"M\u00f6ller","year":"2025","journal-title":"Eur Radiol"},{"key":"B11","doi-asserted-by":"publisher","first-page":"e250480","DOI":"10.1148\/ryai.250480","article-title":"The RSNA lumbar degenerative imaging spine classification (LumbarDISC) dataset","volume":"8","author":"Richards","year":"2026","journal-title":"Radiology"},{"key":"B12","unstructured":"RSNA Lumbar Spine Degenerative Classification AI Challenge\n          \n          2024"},{"key":"B13","unstructured":"RSNA 2024 Lumbar Spine Degenerative Classification\n          \n          2024"},{"key":"B14","doi-asserted-by":"publisher","first-page":"1131","DOI":"10.1038\/s41597-024-03919-4","article-title":"An open-access lumbosacral spine MRI dataset with enhanced spinal nerve root structure resolution","volume":"11","author":"Liu","year":"2024","journal-title":"Sci Data"},{"key":"B15","doi-asserted-by":"publisher","first-page":"102166","DOI":"10.1016\/j.media.2021.102166","article-title":"VERSE: a vertebrae labelling and segmentation benchmark for multi-detector CT images","volume":"73","author":"Sekuboyina","year":"2021","journal-title":"Med Image Anal"},{"key":"B16","doi-asserted-by":"publisher","first-page":"500","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":"B17","doi-asserted-by":"publisher","first-page":"1472","DOI":"10.1016\/j.acra.2018.02.018","article-title":"Deep learning in radiology","volume":"25","author":"McBee","year":"2018","journal-title":"Acad Radiol"},{"key":"B18","doi-asserted-by":"publisher","first-page":"939","DOI":"10.1002\/jmri.26534","article-title":"Deep learning in radiology: an overview of the concepts and a survey of the state of the art with focus on MRI","volume":"49","author":"Mazurowski","year":"2019","journal-title":"J Magn Reson Imag"},{"key":"B19","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1038\/s41591-021-01614-0","article-title":"AI in health and medicine","volume":"28","author":"Rajpurkar","year":"2022","journal-title":"Nat Med"},{"key":"B20","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","article-title":"U-Net: convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015","journal-title":"Medical image computing and computer-assisted intervention (MICCAI)"},{"key":"B21","doi-asserted-by":"publisher","first-page":"565","DOI":"10.1109\/3DV.2016.79","article-title":"V-Net: fully convolutional neural networks for volumetric medical image segmentation","author":"Milletari","year":"2016","journal-title":"2016 fourth international conference on 3D vision (3DV)"},{"key":"B22","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","article-title":"nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation","volume":"18","author":"Isensee","year":"2021","journal-title":"Nat Methods"},{"key":"B23","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1109\/CVPR.2016.90","article-title":"Deep residual learning for image recognition","author":"He","year":"2016","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)"},{"key":"B24","doi-asserted-by":"publisher","first-page":"6546","DOI":"10.1109\/CVPR.2018.00685","article-title":"Can spatiotemporal 3D CNNs retrace the history of 2D CNNs and ImageNet?","author":"Hara","year":"2018","journal-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)"},{"key":"B25","first-page":"5998","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"B26","doi-asserted-by":"publisher","first-page":"837","DOI":"10.2307\/2531595","article-title":"Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach","volume":"44","author":"DeLong","year":"1988","journal-title":"Biometrics"},{"key":"B27","first-page":"65","article-title":"A simple sequentially rejective multiple test procedure","volume":"6","author":"Holm","year":"1979","journal-title":"Scandinav J Stat"},{"key":"B28","doi-asserted-by":"publisher","first-page":"1748","DOI":"10.1109\/WACV51458.2022.00181","article-title":"UNETR: transformers for 3D medical image segmentation","author":"Hatamizadeh","year":"2022","journal-title":"Proceedings of the IEEE\/CVF winter conference on applications of computer vision (WACV)"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-08999-2_22","article-title":"Swin UNETR: swin transformers for semantic segmentation of brain tumors in MRI images","author":"Hatamizadeh","year":"2022","journal-title":"arXiv preprint arXiv:2201.01266"},{"key":"B30","doi-asserted-by":"publisher","first-page":"618","DOI":"10.1109\/ICCV.2017.74","article-title":"Grad-CAM: visual explanations from deep networks via gradient-based localization","author":"Selvaraju","year":"2017","journal-title":"Proceedings of the IEEE international conference on computer vision (ICCV)"},{"key":"B31","doi-asserted-by":"publisher","first-page":"124","DOI":"10.5220\/0008975201240133","article-title":"Coarse to fine vertebrae localization and segmentation with SpatialConfiguration-Net and U-Net","author":"Payer","year":"2020","journal-title":"Proceedings of the 15th international joint conference on computer vision, imaging and computer graphics theory and applications (VISAPP)"},{"key":"B32","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","article-title":"A survey on deep learning in medical image analysis","volume":"42","author":"Litjens","year":"2017","journal-title":"Med Image Anal"},{"key":"B33","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1016\/j.zemedi.2018.11.002","article-title":"An overview of deep learning in medical imaging focusing on MRI","volume":"29","author":"Lundervold","year":"2019","journal-title":"Zeitschrift f\u00fcr Medizinische Physik"},{"key":"B34","doi-asserted-by":"publisher","first-page":"1773","DOI":"10.1038\/s41591-022-01981-2","article-title":"Multimodal biomedical AI","volume":"28","author":"Acosta","year":"2022","journal-title":"Nat Med"},{"key":"B35","doi-asserted-by":"publisher","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":"B36","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1038\/s41591-018-0316-z","article-title":"A guide to deep learning in healthcare","volume":"25","author":"Esteva","year":"2019","journal-title":"Nat Med"},{"key":"B37","doi-asserted-by":"publisher","first-page":"4128","DOI":"10.1038\/s41467-022-30695-9","article-title":"The medical segmentation decathlon","volume":"13","author":"Antonelli","year":"2022","journal-title":"Nat Commun"},{"key":"B38","doi-asserted-by":"publisher","first-page":"654","DOI":"10.1038\/s41467-024-44824-z","article-title":"Segment anything in medical images","volume":"15","author":"Ma","year":"2024","journal-title":"Nat Commun"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1848548\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T05:44:09Z","timestamp":1782452649000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1848548\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,26]]},"references-count":38,"alternative-id":["10.3389\/fmed.2026.1848548"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1848548","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,26]]},"article-number":"1848548"}}