{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,4]],"date-time":"2026-11-04T14:22:14Z","timestamp":1793802134154,"version":"4.6.1"},"reference-count":34,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,3,27]],"date-time":"2023-03-27T00:00:00Z","timestamp":1679875200000},"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>Background<\/jats:title>\n                    <jats:p>Acute vertebral fracture is usually caused by low-energy injury with osteoporosis and high-energy trauma. The AOSpine thoracolumbar spine injury classification system (AO classification) plays an important role in the diagnosis and treatment of the disease. The diagnosis and description of vertebral fractures according to the classification scheme requires a great deal of time and energy for radiologists.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>To design and validate a multistage deep learning system (multistage AO system) for the automatic detection, localization and classification of acute thoracolumbar vertebral body fractures according to AO classification on computed tomography.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and Methods<\/jats:title>\n                    <jats:p>The CT images of 1,217 patients who came to our hospital from January 2015 to December 2019 were collected retrospectively. The fractures were marked and classified by 2 junior radiology residents according to the type A standard in the AO classification. Marked fracture sites included the upper endplate, lower endplate and posterior wall. When there were inconsistent opinions on classification labels, the final result was determined by a director radiologist. We integrated different networks into different stages of the overall framework. U-net and a graph convolutional neural network (U-GCN) are used to realize the location and classification of the thoracolumbar spine. Next, a classification network is used to detect whether the thoracolumbar spine has a fracture. In the third stage, we detect fractures in different parts of the thoracolumbar spine by using a multibranch output network and finally obtain the AO types.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The mean age of the patients was 61.87 years with a standard deviation of 17.04 years, consisting of 760 female patients and 457 male patients. On vertebrae level, sensitivity for fracture detection was 95.23% in test dataset, with an accuracy of 97.93% and a specificity of 98.35%. For the classification of vertebral body fractures, the balanced accuracy was 79.56%, with an AUC of 0.904 for type A1, 0.945 for type A2, 0.878 for type A3 and 0.942 for type A4.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The multistage AO system can automatically detect and classify acute vertebral body fractures in the thoracolumbar spine on CT images according to AO classification with high accuracy.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fendo.2023.1132725","type":"journal-article","created":{"date-parts":[[2023,3,27]],"date-time":"2023-03-27T02:02:34Z","timestamp":1679882554000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":45,"title":["Automated detection and classification of acute vertebral body fractures using a convolutional neural network on computed tomography"],"prefix":"10.3389","volume":"14","author":[{"given":"Jianlun","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingxu","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingqing","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chencui","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yizhou","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huishu","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2023,3,27]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1007\/s00264-015-3025-y","article-title":"Age- and gender-specific clinical characteristics of acute adult spine fractures in China","volume":"40","author":"Tian","year":"2016","journal-title":"Int Orthop"},{"key":"B2","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1186\/s13018-022-03147-9","article-title":"Epidemiologic analysis of 8000 acute vertebral fractures: Evolution of treatment and complications at 10-year follow-up","volume":"17","author":"Bigdon","year":"2022","journal-title":"J Orthop Surg Res"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.14245\/ns.2142650.325","article-title":"Classification and radiological diagnosis of thoracolumbar spine fractures: Wfns spine committee recommendations","volume":"18","author":"Bajamal","year":"2021","journal-title":"Neurospine"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1097\/00007632-198311000-00003","article-title":"The three column spine and its significance in the classification of acute thoracolumbar spinal injuries","volume":"8","author":"Denis","year":"1983","journal-title":"Spine (Phila Pa 1976)"},{"key":"B5","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1007\/bf02221591","article-title":"A comprehensive classification of thoracic and lumbar injuries","volume":"3","author":"Magerl","year":"1994","journal-title":"Eur Spine J"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1097\/01.brs.0000182986.43345.cb","article-title":"A new classification of thoracolumbar injuries: The importance of injury morphology, the integrity of the posterior ligamentous complex, and neurologic status","volume":"30","author":"Vaccaro","year":"2005","journal-title":"Spine (Phila Pa 1976)"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1097\/BRS.0b013e3182a8a381","article-title":"AOspine thoracolumbar spine injury classification system: Fracture description, neurological status, and key modifiers","volume":"38","author":"Vaccaro","year":"2013","journal-title":"Spine (Phila Pa 1976)"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1016\/j.wneu.2021.06.148","article-title":"Retrospective evaluation of thoracolumbar injury classification system and thoracolumbar AO spine injury scores for the decision treatment of thoracolumbar traumatic fractures in 458 consecutive patients","volume":"153","author":"Santander","year":"2021","journal-title":"World Neurosurg"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.5137\/1019-5149.Jtn.19363-16.1","article-title":"Risk factors and compression and kyphosis rates after 1 year in patients with AO type a thoracic, thoracolumbar, and lumbar fractures treated conservatively","volume":"28","author":"Guzey","year":"2018","journal-title":"Turk Neurosurg"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1007\/s00586-015-3982-2","article-title":"The surgical algorithm for the aospine thoracolumbar spine injury classification system","volume":"25","author":"Vaccaro","year":"2016","journal-title":"Eur Spine J"},{"key":"B11","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1097\/bsd.0000000000001038","article-title":"Surgical management of thoracolumbar burst fractures: Surgical decision-making using the aospine thoracolumbar injury classification score and thoracolumbar injury classification and severity score","volume":"34","author":"Morrissey","year":"2021","journal-title":"Clin Spine Surg"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1016\/j.injury.2017.04.057","article-title":"Clinical importance of posterior vertebral height loss on plain radiography when conservatively treating osteoporotic vertebral fractures","volume":"48","author":"Seo","year":"2017","journal-title":"Injury"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1007\/s00586-016-4842-4","article-title":"Reliability and reproducibility analysis of the aospine thoracolumbar spine injury classification system by Chinese spinal surgeons","volume":"26","author":"Cheng","year":"2017","journal-title":"Eur Spine J"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1148\/rg.2016160058","article-title":"Thoracolumbar spine injury at CT: Trauma\/Emergency radiology","volume":"36","author":"Raniga","year":"2016","journal-title":"Radiographics"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.212631","article-title":"Mandating limits on workload, duty, and speed in radiology","volume":"304","author":"Alexander","year":"2022","journal-title":"Radiology"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1093\/neuros\/nyy362","article-title":"Congress of neurological surgeons systematic review and evidence-based guidelines on the evaluation and treatment of patients with thoracolumbar spine trauma: Timing of surgical intervention","volume":"84","author":"Eichholz","year":"2019","journal-title":"Neurosurgery"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2021.102020","article-title":"A survey of deep learning models in medical therapeutic areas","volume":"112","author":"Nogales","year":"2021","journal-title":"Artif Intell Med"},{"key":"B18","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1038\/s41746-021-00438-z","article-title":"Diagnostic accuracy of deep learning in medical imaging: A systematic review and meta-analysis","volume":"4","author":"Aggarwal","year":"2021","journal-title":"NPJ Digit Med"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1016\/j.acra.2022.02.020","article-title":"Deep learning classification of spinal osteoporotic compression fractures on radiographs using an adaptation of the genant semiquantitative criteria","volume":"29","author":"Dong","year":"2022","journal-title":"Acad Radiol"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-021-08247-4","article-title":"A deep-learning model for identifying fresh vertebral compression fractures on digital radiography","volume":"32","author":"Chen","year":"2022","journal-title":"Eur Radiol"},{"key":"B21","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1016\/j.compbiomed.2018.05.011","article-title":"Deep neural networks for automatic detection of osteoporotic vertebral fractures on CT scans","volume":"98","author":"Tomita","year":"2018","journal-title":"Comput Biol Med"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-021-08014-5","article-title":"Differential diagnosis of benign and malignant vertebral fracture on CT using deep learning","volume":"31","author":"Li","year":"2021","journal-title":"Eur Radiol"},{"key":"B23","doi-asserted-by":"publisher","first-page":"22156","DOI":"10.1038\/s41598-021-01296-1","article-title":"Automatic vertebrae localization and segmentation in CT with a two-stage dense-U-Net","volume":"11","author":"Cheng","year":"2021","journal-title":"Sci Rep"},{"key":"B24","doi-asserted-by":"publisher","first-page":"45","DOI":"10.3390\/tomography8010005","article-title":"Verte-box: A novel convolutional neural network for fully automatic segmentation of vertebrae in CT image","volume":"8","author":"Li","year":"2022","journal-title":"Tomography"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/8747487","article-title":"A classification method for thoracolumbar vertebral fractures due to basketball sports injury based on deep learning","volume":"2022","author":"Chen","year":"2022","journal-title":"Comput Math Methods Med"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-020-07418-z","article-title":"Automatic detection and classification of rib fractures based on patients' CT images and clinical information Via convolutional neural network","volume":"31","author":"Zhou","year":"2021","journal-title":"Eur Radiol"},{"key":"B27","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/j.cmpb.2019.02.006","article-title":"Deep learning and surf for automated classification and detection of calcaneus fractures in CT images","volume":"171","author":"Pranata","year":"2019","journal-title":"Comput Methods Programs BioMed"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-013-3089-2","article-title":"Automatic detection of osteoporotic vertebral fractures in routine thoracic and abdominal mdct","volume":"24","author":"Baum","year":"2014","journal-title":"Eur Radiol"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2014.04.001","article-title":"Cortical shell unwrapping for vertebral body abnormality detection on computed tomography","volume":"38","author":"Yao","year":"2014","journal-title":"Comput Med Imaging Graph"},{"key":"B30","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1148\/radiol.2015142346","article-title":"Automated detection, localization, and classification of traumatic vertebral body fractures in the thoracic and lumbar spine at CT","volume":"278","author":"Burns","year":"2016","journal-title":"Radiology"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1016\/j.injury.2020.09.010","article-title":"Sanders classification of calcaneal fractures in CT images with deep learning and differential data augmentation techniques","volume":"52","author":"Aghnia Farda","year":"2021","journal-title":"Injury"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1097\/cm9.0000000000000919","article-title":"Radiological features of traumatic vertebral endplate fracture: An analysis of 194 cases with 263 vertebral fractures","volume":"133","author":"Wang","year":"2020","journal-title":"Chin Med J (Engl)"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1055\/s-0035-1563610","article-title":"The thoracolumbar aospine injury score","volume":"6","author":"Kepler","year":"2016","journal-title":"Global Spine J"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1007\/s00586-016-4663-5","article-title":"Reliability assessment of aospine thoracolumbar spine injury classification system and thoracolumbar injury classification and severity score (Tlics) for thoracolumbar spine injuries: Results of a multicentre study","volume":"26","author":"Kaul","year":"2017","journal-title":"Eur Spine J"}],"container-title":["Frontiers in Endocrinology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2023.1132725\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,27]],"date-time":"2023-03-27T02:02:40Z","timestamp":1679882560000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2023.1132725\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,27]]},"references-count":34,"alternative-id":["10.3389\/fendo.2023.1132725"],"URL":"https:\/\/doi.org\/10.3389\/fendo.2023.1132725","relation":{},"ISSN":["1664-2392"],"issn-type":[{"value":"1664-2392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,27]]},"article-number":"1132725"}}