{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,10]],"date-time":"2026-10-10T21:04:09Z","timestamp":1791666249450,"version":"4.3.4"},"reference-count":33,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2021,8,19]],"date-time":"2021-08-19T00:00:00Z","timestamp":1629331200000},"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>\n                    <jats:bold>Background:<\/jats:bold>\n                    Lumbar disc herniation (LDH) is among the most common causes of lower back pain and sciatica. The causes of LDH have not been fully elucidated but most likely involve a complex combination of mechanical and biological processes. Magnetic resonance imaging (MRI) is a tool most frequently used for LDH because it can show abnormal soft tissue areas around the spine. Deep learning models may be trained to recognize images with high speed and accuracy to diagnose LDH. Although the deep learning model requires huge numbers of image datasets to train and establish the best model, this study processed enhanced medical image features for training the small-scale deep learning dataset.\n                  <\/jats:p>\n                  <jats:p>\n                    <jats:bold>Methods:<\/jats:bold>\n                    We propose automatic detection to assist the initial LDH exam for lower back pain. The subjects were between 20 and 65\u00a0years old with at least 6\u00a0months of work experience. The deep learning method employed the YOLOv3 model to train and detect small object changes such as LDH on MRI. The dataset images were processed and combined with labeling and annotation from the radiologist\u2019s diagnosis record.\n                  <\/jats:p>\n                  <jats:p>\n                    <jats:bold>Results:<\/jats:bold>\n                    Our method proves the possibility of using deep learning with a small-scale dataset with limited medical images. The highest mean average precision (mAP) was 92.4% at 550 images with data augmentation (550-aug), and the YOLOv3 LDH training was 100% with the best average precision at 550-aug among all datasets. This study used data augmentation to prevent under- or overfitting in an object detection model that was trained with the small-scale dataset.\n                  <\/jats:p>\n                  <jats:p>\n                    <jats:bold>Conclusions:<\/jats:bold>\n                    The data augmentation technique plays a crucial role in YOLOv3 training and detection results. This method displays a high possibility for rapid initial tests and auto-detection for a limited clinical dataset.\n                  <\/jats:p>","DOI":"10.3389\/fbioe.2021.708137","type":"journal-article","created":{"date-parts":[[2021,8,19]],"date-time":"2021-08-19T02:12:18Z","timestamp":1629339138000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":72,"title":["Lumbar Disc Herniation Automatic Detection in Magnetic Resonance Imaging Based on Deep Learning"],"prefix":"10.3389","volume":"9","author":[{"given":"Jen-Yung","family":"Tsai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Isabella Yu-Ju","family":"Hung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue Leon","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yih-Kuen","family":"Jan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chih-Yang","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tiffany Ting-Fang","family":"Shih","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bang-Bin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chi-Wen","family":"Lung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2021,8,19]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1186\/s12859-019-2823-4","article-title":"Deep Convolutional Neural Networks for Mammography: Advances, Challenges and Applications","volume":"20","author":"Abdelhafiz","year":"2019","journal-title":"BMC Bioinformatics"},{"key":"B2","doi-asserted-by":"publisher","first-page":"507","DOI":"10.1007\/s12178-017-9441-4","article-title":"Lumbar Disc Herniation","volume":"10","author":"Amin","year":"2017","journal-title":"Curr. Rev. Musculoskelet. Med."},{"key":"B3","doi-asserted-by":"publisher","first-page":"543","DOI":"10.31616\/asj.2020.0147","article-title":"A Review on the Use of Artificial Intelligence in Spinal Diseases","volume":"14","author":"Azimi","year":"2020","journal-title":"Asian Spine J."},{"key":"B4","first-page":"318","article-title":"Is that a Bulging Disk, a Small Herniation or a Moderate Protrusion?","volume":"42","author":"Breton","year":"1991","journal-title":"Can. Assoc. Radiol. J."},{"key":"B5","doi-asserted-by":"publisher","first-page":"811","DOI":"10.3174\/ajnr.A4173","article-title":"Systematic Literature Review of Imaging Features of Spinal Degeneration in Asymptomatic Populations","volume":"36","author":"Brinjikji","year":"2015","journal-title":"AJNR Am. J. Neuroradiol"},{"key":"B6","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.compmedimag.2016.02.002","article-title":"Multi-modal Vertebrae Recognition Using Transformed Deep Convolution Network","volume":"51","author":"Cai","year":"2016","journal-title":"Comput. Med. Imaging Graphics"},{"key":"B7","first-page":"1528","article-title":"A Kernel Theory of Modern Data Augmentation","volume":"97","author":"Dao","year":"2019","journal-title":"Proc. Mach Learn. Res."},{"key":"B8","doi-asserted-by":"publisher","first-page":"414","DOI":"10.1186\/s12891-019-2786-7","article-title":"Correlation between Multifidus Fatty Atrophy and Lumbar Disc Degeneration in Low Back Pain","volume":"20","author":"Faur","year":"2019","journal-title":"BMC Musculoskelet. Disord."},{"key":"B9","doi-asserted-by":"publisher","first-page":"406","DOI":"10.1007\/s10278-017-9945-x","article-title":"Detection and Labeling of Vertebrae in MR Images Using Deep Learning with Clinical Annotations as Training Data","volume":"30","author":"Forsberg","year":"2017","journal-title":"J. Digit Imaging"},{"key":"B10","doi-asserted-by":"publisher","first-page":"2521","DOI":"10.3390\/ijerph18052521","article-title":"Prediction of Lumbar Disc Bulging and Protrusion by Anthropometric Factors and Disc Morphology","volume":"18","author":"Hung","year":"2021","journal-title":"Ijerph"},{"key":"B11","doi-asserted-by":"publisher","first-page":"1582","DOI":"10.2522\/ptj.20130095","article-title":"The Dose-Response Relationship between Cumulative Lifting Load and Lumbar Disk Degeneration Based on Magnetic Resonance Imaging Findings","volume":"94","author":"Hung","year":"2014","journal-title":"Phys. Ther."},{"key":"B12","first-page":"979","article-title":"Differential Data Augmentation Techniques for Medical Imaging Classification Tasks","volume":"2017","author":"Hussain","year":"2017","journal-title":"AMIA Annu. Symp. Proc."},{"key":"B13","doi-asserted-by":"publisher","first-page":"979","DOI":"10.1145\/3018896.3066906","article-title":"Differential Data Augmentation Techniques for Medical Imaging Classification Tasks","volume":"16","author":"Hussain","year":"2017","journal-title":"Paper presented AMIA Annu. Symp. Proc."},{"key":"B14","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1056\/nejm199407143310201","article-title":"Magnetic Resonance Imaging of the Lumbar Spine in People without Back Pain","volume":"331","author":"Jensen","year":"1994","journal-title":"N. Engl. J. Med."},{"key":"B15","doi-asserted-by":"publisher","first-page":"4758","DOI":"10.3390\/app11114758","article-title":"Augmented Reality Maintenance Assistant Using YOLOv5","volume":"11","author":"Malta","year":"2021","journal-title":"Appl. Sci."},{"key":"B16","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1097\/brs.0000000000002822","article-title":"Trends in Lumbar Fusion Procedure Rates and Associated Hospital Costs for Degenerative Spinal Diseases in the United States, 2004 to 2015","volume":"44","author":"Martin","year":"2019","journal-title":"Spine (Phila Pa 1976)"},{"key":"B17","doi-asserted-by":"publisher","first-page":"100837","DOI":"10.1016\/j.inat.2020.100837","article-title":"Lumbar Spine Discs Classification Based on Deep Convolutional Neural Networks Using Axial View MRI","volume":"22","author":"Mbarki","year":"2020","journal-title":"Interdiscip. Neurosurg."},{"key":"B18","doi-asserted-by":"publisher","first-page":"103792","DOI":"10.1016\/j.compbiomed.2020.103792","article-title":"Automated Detection of COVID-19 Cases Using Deep Neural Networks with X-ray Images","volume":"121","author":"Ozturk","year":"2020","journal-title":"Comput. Biol. Med."},{"key":"B19","doi-asserted-by":"publisher","first-page":"95","DOI":"10.2147\/jpr.S171729","article-title":"Chronic Low Back Pain and Postural Rehabilitation Exercise: a Literature Review","volume":"12","author":"Paolucci","year":"2019","journal-title":"Jpr"},{"key":"B20","first-page":"303","article-title":"Data Augmentation for Skin Lesion Analysis","author":"Perez","year":"2018"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.91","article-title":"You Only Look once: Unified, Real-Time Object Detection","author":"Redmon","year":"2016","journal-title":"Paper presented Proc. IEEE Conf. Comput. Vis. pattern recognition"},{"key":"B22","article-title":"Yolov3: An Incremental Improvement","author":"Redmon","year":"2018"},{"key":"B23","article-title":"IN-YOLO: Real-Time Detection of Outdoor High Voltage Insulators Using UAV Imaging","author":"Sadykova","year":"2019","journal-title":"IEEE Trans. Power Deliv."},{"key":"B24","doi-asserted-by":"publisher","first-page":"29","DOI":"10.5455\/aim.2020.28.29-36","article-title":"A Comparative Analysis of Data Augmentation Approaches for Magnetic Resonance Imaging (MRI) Scan Images of Brain Tumor","volume":"28","author":"Safdar","year":"2020","journal-title":"Acta Inform. Med."},{"key":"B25","doi-asserted-by":"publisher","first-page":"1975","DOI":"10.1007\/s11548-020-02262-4","article-title":"Unravelling the Effect of Data Augmentation Transformations in Polyp Segmentation","volume":"15","author":"S\u00e1nchez-Peralta","year":"2020","journal-title":"Int. J. CARS"},{"key":"B26","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.1016\/s0003-9993(96)90147-1","article-title":"Randomized Controlled Trials in Industrial Low Back Pain Relating to Return to Work. Part 2. Discogenic Low Back Pain","volume":"77","author":"Scheer","year":"1996","journal-title":"Arch. Phys. Med. Rehabil."},{"key":"B27","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1186\/s40537-019-0197-0","article-title":"A Survey on Image Data Augmentation for Deep Learning","volume":"6","author":"Shorten","year":"2019","journal-title":"J. Big Data"},{"key":"B28","article-title":"A Convolutional Neural Network Model to Classify the Effects of Vibrations on Biceps Muscles","author":"Tsai","year":"2020","journal-title":"Paper presented Int. Conf. Appl. Hum. Factors Ergon."},{"key":"B29","doi-asserted-by":"publisher","first-page":"72","DOI":"10.3390\/diagnostics9030072","article-title":"Skin Lesion Segmentation in Dermoscopic Images with Combination of YOLO and GrabCut Algorithm","volume":"9","author":"\u00dcnver","year":"2019","journal-title":"Diagnostics"},{"key":"B30","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1007\/s10278-020-00402-5","article-title":"End-To-End Computerized Diagnosis of Spondylolisthesis Using Only Lumbar X-Rays","volume":"34","author":"Var\u00e7\u0131n","year":"2021","journal-title":"J. Digital Imaging"},{"key":"B31","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1186\/s12883-020-02036-0","article-title":"A Deep Learning Model for Diagnosing Dystrophinopathies on Thigh Muscle MRI Images","volume":"21","author":"Yang","year":"2021","journal-title":"BMC Neurol."},{"key":"B32","doi-asserted-by":"publisher","first-page":"3212","DOI":"10.1109\/tnnls.2018.2876865","article-title":"Object Detection with Deep Learning: A Review","volume":"30","author":"Zhao","year":"2019","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"B33","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1007\/s10278-018-0130-7","article-title":"Automatic Lumbar MRI Detection and Identification Based on Deep Learning","volume":"32","author":"Zhou","year":"2019","journal-title":"J. Digit Imaging"}],"container-title":["Frontiers in Bioengineering and Biotechnology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbioe.2021.708137\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,19]],"date-time":"2021-08-19T02:12:26Z","timestamp":1629339146000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbioe.2021.708137\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,19]]},"references-count":33,"alternative-id":["10.3389\/fbioe.2021.708137"],"URL":"https:\/\/doi.org\/10.3389\/fbioe.2021.708137","relation":{},"ISSN":["2296-4185"],"issn-type":[{"value":"2296-4185","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,8,19]]},"article-number":"708137"}}