{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T08:55:01Z","timestamp":1781772901200,"version":"3.54.5"},"reference-count":24,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T00:00:00Z","timestamp":1781740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Philips Germany","award":["ukb_spine"],"award-info":[{"award-number":["ukb_spine"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>Treatment of severely injured patients is challenging, and timely reading of whole-body computed tomography (WBCT) images therefore crucial. Artificial intelligence is increasingly used to prioritize and detect acute injuries in this context. Algorithms focusing on the cervical spine and compression fractures have been deployed successfully. However, tools for whole spine assessment and the entirety of fracture morphologies are lacking. We aimed to investigate the capabilities of an algorithm to detect spine fractures on WBCTs and factors contributing to the difficulties in its development. A version 1.0 (v1) of the algorithm was previously trained with 454 cervical spine fractures using a U-Net via four-fold cross-validation to segment spine fractures and the spine via a multi-task loss. Further training expanded towards whole spine assessment with additional annotated fractures (Cohort 1) of the cervical (n = 50), thoracic (n = 30), and lumbar spine (n = 20), resulting in version 2.0 (v2). Baseline was set to reach the highest sensitivity at a maximum of five false positives per case. Version 1.0 was tested on Cohort 1 and both versions were compared on prospectively collected real-world data (Cohort 2, n = 712 WBCTs). An additional systematic review served to compare the algorithmic performance against the state-of-the-art. Version 1.0 showed promising performance not only for the cervical but also the thoracic and lumbar spine due to generalization (sensitivities ranging between 60% and 87%). Version 2.0 also achieved decent sensitivities for Cohort 2 (sensitivities ranging between 77% and 85%) but generated an abundance of false positives. Various reasons led to false positive results; for Version 2.0, the trabecular structure itself provoked false alerts. Variances in training and test data (image quality, dose, reconstructions), heterogeneity of fractures and anatomies, plus the size of training sets explain some difficulties during algorithm development. Only five other groups described their work on whole-spine fracture detection, encountered similar difficulties, and have also failed to develop a clinically deployable tool. Spine fracture detection on WBCT is feasible, but multiple factors hinder the development of commercially available AI tools. Expansion and the improved design of training cohorts are necessary for further development and simulation of real-life conditions.<\/jats:p>","DOI":"10.3390\/jimaging12060265","type":"journal-article","created":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T07:33:54Z","timestamp":1781768034000},"page":"265","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Towards Automated Spine Fracture Detection on Whole-Body CT of Polytraumatized Patients"],"prefix":"10.3390","volume":"12","author":[{"given":"Elena","family":"Stojanovski","sequence":"first","affiliation":[{"name":"Institute of Radiology and Neuroradiology, BG Klinikum Unfallkrankenhaus Berlin, 12683 Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5469-0639","authenticated-orcid":false,"given":"Alexander","family":"H\u00f6nning","sequence":"additional","affiliation":[{"name":"Center for Clinical Research, BG Klinikum Unfallkrankenhaus Berlin, 12683 Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6468-8276","authenticated-orcid":false,"given":"Frederik","family":"Spohn","sequence":"additional","affiliation":[{"name":"Institute of Radiology and Neuroradiology, BG Klinikum Unfallkrankenhaus Berlin, 12683 Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marlene","family":"Ciesla","sequence":"additional","affiliation":[{"name":"Institute of Radiology and Neuroradiology, BG Klinikum Unfallkrankenhaus Berlin, 12683 Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Holger","family":"Arndt","sequence":"additional","affiliation":[{"name":"Institute of Radiology and Neuroradiology, BG Klinikum Unfallkrankenhaus Berlin, 12683 Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sven","family":"Mutze","sequence":"additional","affiliation":[{"name":"Institute of Radiology and Neuroradiology, BG Klinikum Unfallkrankenhaus Berlin, 12683 Berlin, Germany"},{"name":"Institute of Diagnostic Radiology and Neuroradiology, Universit\u00e4tsklinikum Greifswald, 17489 Greifswald, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alena-Kathrin","family":"Golla","sequence":"additional","affiliation":[{"name":"Philips Research Hamburg, Roentgenstrasse 24-26, 22335 Hamburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tobias","family":"Klinder","sequence":"additional","affiliation":[{"name":"Philips Research Hamburg, Roentgenstrasse 24-26, 22335 Hamburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cristian","family":"Lorenz","sequence":"additional","affiliation":[{"name":"Philips Research Hamburg, Roentgenstrasse 24-26, 22335 Hamburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0011-2382","authenticated-orcid":false,"given":"Leonie","family":"Goelz","sequence":"additional","affiliation":[{"name":"Institute of Radiology and Neuroradiology, BG Klinikum Unfallkrankenhaus Berlin, 12683 Berlin, Germany"},{"name":"Institute of Diagnostic Radiology and Neuroradiology, Universit\u00e4tsklinikum Greifswald, 17489 Greifswald, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,6,18]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"603","DOI":"10.1055\/s-0042-124275","article-title":"Polytraumamanagement\u2014Behandlung des Schwerverletzten in Schockraum und OP [Polytrauma Management\u2014Treatment of Severely Injured Patients in ER and OR]","volume":"155","author":"Perl","year":"2017","journal-title":"Z. Orthop. Unfall."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1177\/0846537120914247","article-title":"Emergent Comprehensive Imaging of the Major Trauma Patient: A New Paradigm for Improved Clinical Decision-Making","volume":"72","author":"Qamar","year":"2021","journal-title":"Can. Assoc. Radiol. J."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"2117","DOI":"10.1016\/j.injury.2016.05.046","article-title":"Cambridge Polytrauma Pathway: Are we making appropriately guided decisions?","volume":"47","author":"Guevel","year":"2016","journal-title":"Injury"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"S76","DOI":"10.1016\/j.injury.2014.08.022","article-title":"Effect of the localisation of the CT scanner during trauma resuscitation on survival\u2014A retrospective, multicentre study","volume":"45","author":"Mand","year":"2014","journal-title":"Injury"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"222","DOI":"10.1007\/s11547-023-01596-8","article-title":"Structured reporting of computed tomography in the polytrauma patient assessment: A Delphi consensus proposal","volume":"128","author":"Granata","year":"2023","journal-title":"Radiol. Med."},{"key":"ref_6","first-page":"e45","article-title":"Current Applications, Challenges, and Future Directions of Artificial Intelligence in Emergency Medicine: A Narrative Review","volume":"13","author":"Farrokhi","year":"2025","journal-title":"Arch. Acad. Emerg. Med."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/s10140-023-02135-8","article-title":"The American Society of Emergency Radiology (ASER) AI\/ML expert panel: Inception, mandate, work products, and goals","volume":"30","author":"Dreizin","year":"2023","journal-title":"Emerg. Radiol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"647","DOI":"10.1007\/s10140-023-02154-5","article-title":"AI tools in Emergency Radiology reading room: A new era of Radiology","volume":"30","author":"Dundamadappa","year":"2023","journal-title":"Emerg. Radiol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1016\/j.spinee.2012.10.041","article-title":"Management of thoracolumbar spine fractures","volume":"14","author":"Wood","year":"2014","journal-title":"Spine J."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"324","DOI":"10.1053\/j.sult.2018.04.003","article-title":"Imaging of Spine Fractures with Emphasis on the Craniocervical Junction","volume":"39","author":"Lo","year":"2018","journal-title":"Semin. Ultrasound. CT MRI"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"e2432076","DOI":"10.2214\/AJR.24.32076","article-title":"Machine Learning to Detect Cervical Spine Fractures Missed by Radiologists on CT: Analysis Using Seven Award-Winning Models from the 2022 RSNA Cervical Spine Fracture AI Challenge","volume":"224","author":"Chen","year":"2025","journal-title":"AJR Am. J. Roentgenol."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"106831","DOI":"10.1016\/j.crad.2025.106831","article-title":"Automated vertebral compression fracture detection and quantification on opportunistic CT scans: A performance evaluation","volume":"83","author":"Guenoun","year":"2025","journal-title":"Clin. Radiol."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1007\/s00068-025-02840-8","article-title":"Imaging strategies for patients with multiple and\/or severe injuries in the resuscitation room: A systematic review and clinical practice guideline update","volume":"51","author":"Braunschweig","year":"2025","journal-title":"Eur. J. Trauma Emerg. Surg."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"115010","DOI":"10.1088\/1361-6560\/acd48b","article-title":"Cervical spine fracture detection in computed tomography using convolutional neural networks","volume":"68","author":"Golla","year":"2023","journal-title":"Phys. Med. Biol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"224","DOI":"10.1001\/jamasurg.2019.5468","article-title":"Association of Low-Dose Whole-Body Computed Tomography with Missed Injury Diagnoses and Radiation Exposure in Patients with Blunt Multiple Trauma","volume":"155","author":"Stengel","year":"2020","journal-title":"JAMA Surg."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"n71","DOI":"10.1136\/bmj.n71","article-title":"The PRISMA 2020 statement: An updated guideline for reporting systematic reviews","volume":"372","author":"Page","year":"2021","journal-title":"BMJ"},{"key":"ref_17","unstructured":"Roth, H.R., Wang, Y., Yao, J., Lu, L., Burns, J.E., and Summers, R.M. (March, January 28). Deep convolutional networks for automated detection of posterior-element fractures on spine CT. Proceedings of the SPIE Medical Imaging: Computer-Aided Diagnosis, San Diego, CA, USA."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"14408","DOI":"10.1038\/s41598-025-98518-7","article-title":"Vision transformer and deep learning based weighted ensemble model for automated spine fracture type identification with GAN generated CT images","volume":"15","author":"Sindhura","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"2216","DOI":"10.1007\/s10278-024-01091-0","article-title":"An Automated Multi-scale Feature Fusion Network for Spine Fracture Segmentation Using Computed Tomography Images","volume":"37","author":"Saeed","year":"2024","journal-title":"J. Imaging Inform. Med."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1661","DOI":"10.1007\/s11517-023-02805-2","article-title":"Automatic vertebral fracture and three-column injury diagnosis with fracture visualization by a multi-scale attention-guided network","volume":"61","author":"Zhang","year":"2023","journal-title":"Med. Biol. Eng. Comput."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"012016","DOI":"10.1088\/1742-6596\/1576\/1\/012016","article-title":"Detection of spinal fracture lesions based on Improved Yolov3","volume":"1576","author":"Sha","year":"2020","journal-title":"J. Phys. Conf. Ser."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"e210014","DOI":"10.1148\/ryai.2021210014","article-title":"Training Strategies for Radiology Deep Learning Models in Data-limited Scenarios","volume":"3","author":"Candemir","year":"2021","journal-title":"Radiol. Artif. Intell."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"109834","DOI":"10.1016\/j.compbiomed.2025.109834","article-title":"Generative AI for synthetic data across multiple medical modalities: A systematic review of recent developments and challenges","volume":"189","author":"Ibrahim","year":"2025","journal-title":"Comput. Biol. Med."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"931","DOI":"10.1177\/09287329241291368","article-title":"Assessment of perceived realism in AI-generated synthetic spine fracture CT images","volume":"33","author":"Sindhura","year":"2025","journal-title":"Technol. Health Care"}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/6\/265\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T08:29:07Z","timestamp":1781771347000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/6\/265"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,18]]},"references-count":24,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["jimaging12060265"],"URL":"https:\/\/doi.org\/10.3390\/jimaging12060265","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,18]]}}}