{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T04:50:17Z","timestamp":1764996617599,"version":"3.44.0"},"reference-count":33,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T00:00:00Z","timestamp":1757462400000},"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. Bioeng. Biotechnol."],"abstract":"<jats:p>This study develops an intelligent diagnostic model for LDD based on a novel YOLOv9-AID detection network and evaluates the impact of multiple innovative strategies on detection performance. A total of 222 adult patients who underwent lumbar MRI for low back pain or radicular leg pain were enrolled, yielding 1110 de-identified sagittal T2-weighted images (five per case). After excluding cases with prior spinal trauma, tumors, postoperative changes, congenital malformations, or severe artefacts, 202 cases (1,010 images) were randomly divided into training, validation, and internal test sets (8:1:1), while 20 cases (100 images) formed an external dataset for generalization assessment. The YOLOv9-AID model introduces three key enhancements to the baseline YOLOv9: a SlideLoss function to rebalance training weights between high- and low-quality samples; spatial-channel collaborative attention modules (SCSA) embedded at layers 5 and 11 to strengthen lesion feature extraction; and an ExtraDW-inspired redesign of the ResNCSPELAN4 module to boost precision and reduce parameter count. In the internal test set, the model achieved an mAP50 of 82.8% and an overall detection precision of 80.3%, with Schmorl\u2019s node detection at 92.9%, Pfirrmann grading accuracy at 93.3%, and disc herniation accuracy at 73.2% (an 8.4% improvement). Recall rates increased by approximately 5% on average, with Schmorl\u2019s node recall up 15.1%, Pfirrmann recall up 1.8%, and herniation recall improvements of up to 12.3%. External validation confirmed robust generalization, and detection rates for small lesions such as high-intensity zones and Schmorl\u2019s nodes significantly outperformed conventional methods. These results demonstrate that the YOLOv9-AID network, through the integration of SlideLoss and spatial-channel attention mechanisms, substantially enhances the accuracy and robustness of LDD detection on MRI and offers a promising tool to support clinical diagnosis efficiency and consistency.<\/jats:p>","DOI":"10.3389\/fbioe.2025.1626299","type":"journal-article","created":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T05:27:36Z","timestamp":1757482056000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Enhancing LDD diagnosis with YOLOv9-AID: simultaneous detection of pfirrmann grading, disc herniation, HIZ, and Schmorl\u2019s nodules"],"prefix":"10.3389","volume":"13","author":[{"given":"Erling","family":"Xiang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongkang","family":"Zou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiale","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunhai","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feiwen","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoping","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shenghua","family":"Qin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyu","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nanyu","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xu","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingzheng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,9,10]]},"reference":[{"key":"B1","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1007\/978-3-319-07269-2_8","article-title":"Lumbar spine disc herniation diagnosis with a joint shape model","volume-title":"Computational methods and clinical applications for spine imaging: proceedings of the workshop held at the 16th international conference on medical image computing and computer assisted intervention, september 22-26, 2013","author":"Alomari","year":"2014"},{"key":"B2","doi-asserted-by":"publisher","first-page":"1164","DOI":"10.1111\/os.12727","article-title":"Significant association between the t2 values of vertebral cartilage endplates and pfirrmann grading","volume":"12","author":"Cao","year":"2020","journal-title":"Orthop. Surg."},{"key":"B3","doi-asserted-by":"publisher","first-page":"E177","DOI":"10.1097\/brs.0000000000004632","article-title":"Why are some intervertebral discs more prone to degeneration?insights into isolated thoracic \u201cdysgeneration\u201d","volume":"48","author":"Cheung","year":"2023","journal-title":"Spine"},{"key":"B4","doi-asserted-by":"crossref","first-page":"3898","DOI":"10.1109\/BigData62323.2024.10825149","article-title":"Leveraging multimodal models for enhanced neuroimaging diagnostics in alzheimer\u2019s disease","volume-title":"2024 IEEE international conference on big data (BigData)","author":"Chiumento","year":"2024"},{"key":"B5","doi-asserted-by":"publisher","first-page":"e40941","DOI":"10.7759\/cureus.40941","article-title":"Non-surgical restoration of l3\/l4 disc herniation","volume":"15","author":"Chu","year":"2023","journal-title":"Cureus"},{"key":"B6","doi-asserted-by":"publisher","first-page":"3764","DOI":"10.1007\/s00586-023-0778-0","article-title":"Are current machine learning applications comparable to radiologist classification of degenerate and herniated discs and modic change? a systematic review and meta-analysis","volume":"32","author":"Compte","year":"2023","journal-title":"Eur. Spine J."},{"key":"B7","doi-asserted-by":"publisher","first-page":"3709","DOI":"10.1007\/s11517-024-03161-5","article-title":"Enhanced deep leaning model for detection and grading of lumbar disc herniation from mri","volume":"62","author":"Duan","year":"2024","journal-title":"Med. and Biol. Eng. and Comput."},{"key":"B8","doi-asserted-by":"publisher","first-page":"e489","DOI":"10.1016\/s2589-7500(20)30186-2","article-title":"The myth of generalisability in clinical research and machine learning in health care","volume":"2","author":"Futoma","year":"2020","journal-title":"Lancet Digital Health"},{"key":"B9","doi-asserted-by":"publisher","first-page":"100055","DOI":"10.1016\/j.cmpbup.2022.100055","article-title":"Automatic semantic segmentation and detection of vertebras and intervertebral discs by neural networks","volume":"2","author":"Guinebert","year":"2022","journal-title":"Comput. Methods Programs Biomed. Update"},{"key":"B10","doi-asserted-by":"publisher","first-page":"99","DOI":"10.22603\/ssrr.2020-0011","article-title":"Imaging in spine surgery: current concepts and future directions","volume":"4","author":"Harada","year":"2020","journal-title":"Spine Surg. Relat. Res."},{"key":"B11","doi-asserted-by":"publisher","first-page":"1762","DOI":"10.1002\/jmri.28735","article-title":"Lsw-net: lightweight deep neural network based on small-world properties for spine mr image segmentation","volume":"58","author":"He","year":"2023","journal-title":"J. Magnetic Reson. Imaging"},{"key":"B12","doi-asserted-by":"publisher","first-page":"123728","DOI":"10.1016\/j.wneu.2025.123728","article-title":"Deep learning for lumbar disc herniation diagnosis and treatment decision-making using magnetic resonance imagings: a retrospective study","volume":"195","author":"He","year":"2025","journal-title":"World Neurosurg."},{"key":"B13","doi-asserted-by":"publisher","first-page":"1424716","DOI":"10.3389\/fsurg.2024.1424716","article-title":"Mri to digital medicine diagnosis: integrating deep learning into clinical decision-making for lumbar degenerative diseases","volume":"11","author":"Ke","year":"2025","journal-title":"Front. Surg."},{"key":"B14","doi-asserted-by":"publisher","first-page":"2531","DOI":"10.1007\/s00586-021-06865-6","article-title":"The association between vertebral endplate structural defects and back pain: a systematic review and meta-analysis","volume":"30","author":"Lawan","year":"2021","journal-title":"Eur. Spine J."},{"key":"B15","doi-asserted-by":"publisher","first-page":"663","DOI":"10.3390\/diagnostics13040663","article-title":"Automatic detection, classification, and grading of lumbar intervertebral disc degeneration using an artificial neural network model","volume":"13","author":"Liawrungrueang","year":"2023","journal-title":"Diagnostics"},{"key":"B16","doi-asserted-by":"publisher","first-page":"1405","DOI":"10.1177\/21925682241274372","article-title":"Artificial intelligence-assisted mri diagnosis in lumbar degenerative disc disease: a systematic review","volume":"15","author":"Liawrungrueang","year":"2025","journal-title":"Glob. Spine J."},{"key":"B17","doi-asserted-by":"publisher","first-page":"e0302067","DOI":"10.1371\/journal.pone.0302067","article-title":"Lumbar spine mri annotation with intervertebral disc height and pfirrmann grade predictions","volume":"19","author":"Natalia","year":"2024","journal-title":"PLoS One"},{"key":"B18","doi-asserted-by":"publisher","first-page":"2088","DOI":"10.1177\/21925682231170612","article-title":"An investigation into the relationship between the sedimentation sign and lumbar disc herniation in upright magnetic resonance images","volume":"14","author":"Patel","year":"2024","journal-title":"Glob. Spine J."},{"key":"B19","doi-asserted-by":"publisher","first-page":"1873","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"},{"key":"B20","doi-asserted-by":"publisher","first-page":"1247112","DOI":"10.3389\/fbioe.2023.1247112","article-title":"An approach to the diagnosis of lumbar disc herniation using deep learning models","volume":"11","author":"Prisilla","year":"2023","journal-title":"Front. Bioeng. Biotechnol."},{"key":"B21","doi-asserted-by":"publisher","first-page":"e0000023","DOI":"10.1371\/journal.pdig.0000023","article-title":"Generalizability challenges of mortality risk prediction models: a retrospective analysis on a multi-center database","volume":"1","author":"Singh","year":"2022","journal-title":"PLOS Digit. Health"},{"key":"B22","doi-asserted-by":"publisher","first-page":"e43340","DOI":"10.7759\/cureus.43340","article-title":"Role of apparent diffusion coefficient in evaluating degeneration of the intervertebral disc: a narrative review","volume":"15","author":"Sood","year":"2023","journal-title":"Cureus"},{"key":"B23","doi-asserted-by":"publisher","first-page":"e1321","DOI":"10.1002\/jsp2.1321","article-title":"Tracing the disc: the novel qualitative morphometric mri based disc degeneration classification system","volume":"7","author":"Soydan","year":"2024","journal-title":"JOR spine"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1025","DOI":"10.1016\/j.spinee.2020.02.015","article-title":"Lumbar high-intensity zones on mri: imaging biomarkers for severe, prolonged low back pain and sciatica in a population-based cohort","volume":"20","author":"Teraguchi","year":"2020","journal-title":"Spine J."},{"key":"B25","doi-asserted-by":"publisher","first-page":"903","DOI":"10.1016\/j.spinee.2024.11.017","article-title":"Quantitative assessment of cervical disc degeneration using disc signal intensity index","volume":"25","author":"Tsuchiya","year":"2024","journal-title":"Spine J."},{"key":"B26","doi-asserted-by":"publisher","first-page":"1526478","DOI":"10.3389\/fbioe.2025.1526478","article-title":"Automated diagnosis and grading of lumbar intervertebral disc degeneration based on a modified yolo framework","volume":"13","author":"Wang","year":"2025","journal-title":"Front. Bioeng. Biotechnol."},{"key":"B27","article-title":"Towards generalist foundation model for radiology by leveraging web-scale 2d&3d medical data","author":"Wu","year":"2023"},{"key":"B28","doi-asserted-by":"publisher","first-page":"e15734056280128","DOI":"10.2174\/0115734056280128240201081830","article-title":"Magnetic resonance images segmentation of multifidus based on dense-unet and superpixel","volume":"20","author":"Xu","year":"2024","journal-title":"Curr. Med. Imaging"},{"key":"B29","doi-asserted-by":"publisher","first-page":"364","DOI":"10.1002\/jmri.29403","article-title":"Deep learning model for grading and localization of lumbar disc herniation on magnetic resonance imaging","volume":"61","author":"Xu","year":"2025","journal-title":"J. Magnetic Reson. Imaging"},{"key":"B30","doi-asserted-by":"publisher","first-page":"758","DOI":"10.1186\/s13018-023-04187-5","article-title":"The correlation between the lumbar disc mri high-intensity zone and discogenic low back pain: a systematic review and meta-analysis","volume":"18","author":"Yang","year":"2023","journal-title":"J. Orthop. Surg. Res."},{"key":"B31","doi-asserted-by":"publisher","first-page":"110714","DOI":"10.1016\/j.patcog.2024.110714","article-title":"Yolo-facev2: a scale and occlusion aware face detector","volume":"155","author":"Yu","year":"2024","journal-title":"Pattern Recognit."},{"key":"B32","doi-asserted-by":"publisher","first-page":"e1342","DOI":"10.1002\/jsp2.1342","article-title":"A fully automatic mri-guided decision support system for lumbar disc herniation using machine learning","volume":"7","author":"Zhang","year":"2024","journal-title":"JOR Spine"},{"key":"B33","doi-asserted-by":"publisher","first-page":"743","DOI":"10.1038\/s41551-023-01045-x","article-title":"A transformer-based representation-learning model with unified processing of multimodal input for clinical diagnostics","volume":"7","author":"Zhou","year":"2023","journal-title":"Nat. Biomed. Eng."}],"container-title":["Frontiers in Bioengineering and Biotechnology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbioe.2025.1626299\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T05:27:38Z","timestamp":1757482058000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbioe.2025.1626299\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,10]]},"references-count":33,"alternative-id":["10.3389\/fbioe.2025.1626299"],"URL":"https:\/\/doi.org\/10.3389\/fbioe.2025.1626299","relation":{},"ISSN":["2296-4185"],"issn-type":[{"value":"2296-4185","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,10]]},"article-number":"1626299"}}