{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T22:43:57Z","timestamp":1768344237220,"version":"3.49.0"},"reference-count":33,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2023,9,18]],"date-time":"2023-09-18T00:00:00Z","timestamp":1694995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>Early diagnosis and initiation of treatment for fresh osteoporotic lumbar vertebral fractures (OLVF) are crucial. Magnetic resonance imaging (MRI) is generally performed to differentiate between fresh and old OLVF. However, MRIs can be intolerable for patients with severe back pain. Furthermore, it is difficult to perform in an emergency. MRI should therefore only be performed in appropriately selected patients with a high suspicion of fresh fractures. As radiography is the first-choice imaging examination for the diagnosis of OLVF, improving screening accuracy with radiographs will optimize the decision of whether an MRI is necessary. This study aimed to develop a method to automatically classify lumbar vertebrae (LV) conditions such as normal, old, or fresh OLVF using deep learning methods with radiography. A total of 3481 LV images for training, validation, and testing and 662 LV images for external validation were collected. Visual evaluation by two radiologists determined the ground truth of LV diagnoses. Three convolutional neural networks were ensembled. The accuracy, sensitivity, and specificity were 0.89, 0.83, and 0.92 in the test and 0.84, 0.76, and 0.89 in the external validation, respectively. The results suggest that the proposed method can contribute to the accurate automatic classification of LV conditions on radiography.<\/jats:p>","DOI":"10.3390\/jimaging9090187","type":"journal-article","created":{"date-parts":[[2023,9,18]],"date-time":"2023-09-18T05:59:06Z","timestamp":1695016746000},"page":"187","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["A Deep Learning-Based Model for Classifying Osteoporotic Lumbar Vertebral Fractures on Radiographs: A Retrospective Model Development and Validation Study"],"prefix":"10.3390","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-4565-0918","authenticated-orcid":false,"given":"Yohei","family":"Ono","sequence":"first","affiliation":[{"name":"Department of Radiology, NTT East Medical Center Sapporo, South-1 West-15, Chuo-Ku, Sapporo 060-0061, Japan"},{"name":"Graduate School of Health Sciences, Hokkaido University, North-12 West-5, Kita-Ku, Sapporo 060-0812, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9435-4919","authenticated-orcid":false,"given":"Nobuaki","family":"Suzuki","sequence":"additional","affiliation":[{"name":"Department of Radiology, NTT East Medical Center Sapporo, South-1 West-15, Chuo-Ku, Sapporo 060-0061, Japan"}]},{"given":"Ryosuke","family":"Sakano","sequence":"additional","affiliation":[{"name":"Department of Radiological Technology, Hokkaido University Hospital, Kita-14 Nishi-5, Kita-Ku, Sapporo 060-8648, Japan"}]},{"given":"Yasuka","family":"Kikuchi","sequence":"additional","affiliation":[{"name":"Department of Radiology, NTT East Medical Center Sapporo, South-1 West-15, Chuo-Ku, Sapporo 060-0061, Japan"},{"name":"Department of Diagnostic Imaging, Faculty of Medicine, Hokkaido University, Kita-15 Nishi-7, Kita-Ku, Sapporo 060-8638, Japan"},{"name":"Department of Diagnostic and Interventional Radiology, Tonan Hospital, Kita 4 Nishi 7, Chuo-Ku, Sapporo 060-0004, Japan"}]},{"given":"Tasuku","family":"Kimura","sequence":"additional","affiliation":[{"name":"Department of Radiology, NTT East Medical Center Sapporo, South-1 West-15, Chuo-Ku, Sapporo 060-0061, Japan"},{"name":"Department of Radiology, Hokkaido Medical Center, Yamanote5-7, Nishi-Ku, Sapporo 063-0005, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3494-5427","authenticated-orcid":false,"given":"Kenneth","family":"Sutherland","sequence":"additional","affiliation":[{"name":"Global Center for Biomedical Science and Engineering, Hokkaido University, North-15 West-7, Kita-Ku, Sapporo 060-8638, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7293-7471","authenticated-orcid":false,"given":"Tamotsu","family":"Kamishima","sequence":"additional","affiliation":[{"name":"Faculty of Health Sciences, Hokkaido University, North-12 West-5, Kita-Ku, Sapporo 060-0812, Japan"}]}],"member":"1968","published-online":{"date-parts":[[2023,9,18]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Xu, W., Wang, S., Chen, C., Li, Y., Ji, Y., Zhu, X., and Li, Z. (2018). Correlation analysis between the magnetic resonance imaging characteristics of osteoporotic vertebral compression fractures and the efficacy of percutaneous vertebroplasty: A prospective cohort study. BMC Musculoskelet. Disord., 19.","DOI":"10.1186\/s12891-018-2040-8"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"21514593221100238","DOI":"10.1177\/21514593221100238","article-title":"The Short-Term Changes of the Sagittal Spinal Alignments After Acute Vertebral Compression Fracture Receiving Vertebroplasty and Their Relationship with the Change of Bathel Index in the Elderly","volume":"13","author":"Su","year":"2022","journal-title":"Geriatr. Orthop. Surg. Rehabil."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.trsl.2016.09.006","article-title":"Advances in imaging approaches to fracture risk evaluation","volume":"181","author":"Manhard","year":"2017","journal-title":"Transl. Res."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"111","DOI":"10.21037\/jss.2016.06.05","article-title":"Effects of cement augmentation on the mechanical stability of multilevel spine after vertebral compression fracture","volume":"2","author":"Tan","year":"2016","journal-title":"J. Spine Surg."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"E13","DOI":"10.36076\/ppj.2017.1.E13","article-title":"Does Percutaneous Vertebroplasty or Balloon Kyphoplasty for Osteoporotic Vertebral Compression Fractures Increase the Incidence of New Vertebral Fractures? A Meta-Analysis","volume":"20","author":"Zhang","year":"2017","journal-title":"Pain Physician"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"50","DOI":"10.12659\/MSM.905729","article-title":"Impact of Magnetic Resonance Imaging on Treatment-Related Decision Making for Osteoporotic Vertebral Compression Fracture: A Prospective Randomized Trial","volume":"24","author":"Jin","year":"2018","journal-title":"Med. Sci. Monit."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"e14793","DOI":"10.1097\/MD.0000000000014793","article-title":"Percutaneous vertebroplasty vs balloon kyphoplasty in the treatment of newly onset osteoporotic vertebral compression fractures: A retrospective cohort study","volume":"98","author":"Cheng","year":"2019","journal-title":"Medicine"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1007\/s00586-008-0847-y","article-title":"The prognosis for pain, disability, activities of daily living and quality of life after an acute osteoporotic vertebral body fracture: Its relation to fracture level, type of fracture and grade of fracture deformation","volume":"18","author":"Suzuki","year":"2009","journal-title":"Eur. Spine J."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"100217","DOI":"10.1016\/j.bonr.2019.100217","article-title":"The efficacy of osteoporotic treatment in patients with new spinal vertebral compression fracture pain, ADL, QOL, bone metabolism and fracture-healing\u2014In comparison with weekly teriparatide with bisphosphonate","volume":"11","author":"Shigenobu","year":"2019","journal-title":"Bone Rep."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1598","DOI":"10.1097\/CORR.0000000000001685","article-title":"Can a Deep-learning Model for the Automated Detection of Vertebral Fractures Approach the Performance Level of Human Subspecialists?","volume":"479","author":"Li","year":"2021","journal-title":"Clin. Orthop. Relat. Res."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1080\/17453674.2016.1273644","article-title":"Concomitant and previous osteoporotic vertebral fractures","volume":"88","author":"Lenski","year":"2017","journal-title":"Acta Orthop."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"227","DOI":"10.14245\/kjs.2012.9.3.227","article-title":"Usefulness of SPAIR Image, Fracture Line and the Adjacent Discs Change on Magnetic Resonance Image in the Acute Osteoporotic Compression Fracture","volume":"9","author":"Choi","year":"2012","journal-title":"Korean J. Spine"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"S26","DOI":"10.1016\/j.injury.2018.10.006","article-title":"The impact of magnetic resonance imaging in the diagnostic and classification process of osteoporotic vertebral fractures","volume":"49","author":"Marongiu","year":"2018","journal-title":"Injury"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"714","DOI":"10.1016\/j.jcma.2015.06.015","article-title":"Determination of the painful level in osteoporotic vertebral fractures\u2014Retrospective comparison between plain film, bone scan, and magnetic resonance imaging","volume":"78","author":"Lin","year":"2015","journal-title":"J. Chin. Med. Assoc."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1308\/003588410X12518836440162","article-title":"Vertebral compression fractures\u2014New clinical signs to aid diagnosis","volume":"92","author":"Langdon","year":"2010","journal-title":"Ann. R. Coll. Surg. Engl."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"485","DOI":"10.1007\/s00256-013-1812-3","article-title":"Dual-energy CT in vertebral compression fractures: Performance of visual and quantitative analysis for bone marrow edema demonstration with comparison to MRI","volume":"43","author":"Bierry","year":"2014","journal-title":"Skeletal Radiol."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"853","DOI":"10.1007\/s10278-021-00471-0","article-title":"Automated Vertebral Segmentation and Measurement of Vertebral Compression Ratio Based on Deep Learning in X-Ray Images","volume":"34","author":"Kim","year":"2021","journal-title":"J. Digit. Imaging"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"105833","DOI":"10.1016\/j.cmpb.2020.105833","article-title":"Automatic detection and segmentation of lumbar vertebrae from X-ray images for compression fracture evaluation","volume":"200","author":"Kim","year":"2021","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1007\/s00330-018-5568-y","article-title":"Single-source dual-energy computed tomography for the assessment of bone marrow oedema in vertebral compression fractures: A prospective diagnostic accuracy study","volume":"29","author":"Diekhoff","year":"2019","journal-title":"Eur. Radiol."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"e229987","DOI":"10.1136\/bcr-2019-229987","article-title":"Importance of screening in physical therapy: Vertebral fracture of thoracolumbar junction in a recreational runner","volume":"12","author":"Maselli","year":"2019","journal-title":"BMJ Case Rep."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"567","DOI":"10.1007\/s00586-009-1162-y","article-title":"Previous vertebral compression fractures add to the deterioration of the disability and quality of life after an acute compression fracture","volume":"19","author":"Suzuki","year":"2010","journal-title":"Eur. Spine J."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"458","DOI":"10.1016\/j.injury.2011.09.014","article-title":"Emergency department visits due to vertebral fractures in the Netherlands, 1986\u20132008: Steep increase in the oldest old, strong association with falls","volume":"43","author":"Oudshoorn","year":"2012","journal-title":"Injury"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"787","DOI":"10.21037\/jgo-22-197","article-title":"Classification of hepatic cavernous hemangioma or hepatocellular carcinoma using a convolutional neural network model","volume":"13","author":"Cao","year":"2022","journal-title":"J. Gastrointest. Oncol."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1186\/s13550-022-00897-9","article-title":"Convolutional neural networks for detection of transthyretin amyloidosis in 2D scintigraphy images","volume":"12","author":"Halme","year":"2022","journal-title":"EJNMMI Res."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"15523","DOI":"10.1038\/s41598-022-19674-8","article-title":"Road damage detection algorithm for improved YOLOv5","volume":"12","author":"Guo","year":"2022","journal-title":"Sci. Rep."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"106120","DOI":"10.1016\/j.compbiomed.2022.106120","article-title":"Automatic detection of stroke lesion from diffusion-weighted imaging via the improved YOLOv5","volume":"150","author":"Chen","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"2575","DOI":"10.1007\/s00521-022-07730-3","article-title":"Automatic detection of indoor occupancy based on improved YOLOv5 model","volume":"35","author":"Wang","year":"2023","journal-title":"Neural Comput. Appl."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Shi, Y., Li, J., Yu, Z., Li, Y., Hu, Y., and Wu, L. (2022). Multi-Barley Seed Detection Using iPhone Images and YOLOv5 Model. Foods, 11.","DOI":"10.3390\/foods11213531"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1496","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":"ref_30","doi-asserted-by":"crossref","first-page":"h5527","DOI":"10.1136\/bmj.h5527","article-title":"STARD 2015: An updated list of essential items for reporting diagnostic accuracy studies","volume":"351","author":"Bossuyt","year":"2015","journal-title":"BMJ"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1002\/jbmr.5650080915","article-title":"Vertebral fracture assessment using a semiquantitative technique","volume":"8","author":"Genant","year":"1993","journal-title":"J. Bone Miner. Res."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"159","DOI":"10.2307\/2529310","article-title":"The measurement of observer agreement for categorical data","volume":"33","author":"Landis","year":"1977","journal-title":"Biometrics"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1007\/s10140-022-02092-8","article-title":"Radiographic assessment of acute vs chronic vertebral compression fractures","volume":"30","author":"Strickland","year":"2023","journal-title":"Emerg. Radiol."}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/9\/9\/187\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T20:52:55Z","timestamp":1760129575000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/9\/9\/187"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,18]]},"references-count":33,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2023,9]]}},"alternative-id":["jimaging9090187"],"URL":"https:\/\/doi.org\/10.3390\/jimaging9090187","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9,18]]}}}