AI-based automated detection and stability analysis of traumatic vertebral body fractures on computed tomography

• Verfasst von: Polzer, Constanze [VerfasserIn]
• Verfasst von: Yilmaz, Eren [VerfasserIn]
• Verfasst von: Meyer, Carsten [VerfasserIn]
• Verfasst von: Jang, Hyungseok [VerfasserIn]
• Verfasst von: Jansen, Olav [VerfasserIn]
• Verfasst von: Lorenz, Cristian [VerfasserIn]
• Verfasst von: Bürger, Christian [VerfasserIn]
• Verfasst von: Glüer, Claus-Christian [VerfasserIn]
• Verfasst von: Sedaghat, Sam [VerfasserIn]
• Titel: AI-based automated detection and stability analysis of traumatic vertebral body fractures on computed tomography
• Verf.angabe: Constanze Polzer, Eren Yilmaz, Carsten Meyer, Hyungseok Jang, Olav Jansen, Cristian Lorenz, Christian Bürger, Claus-Christian Glüer, Sam Sedaghat
• E-Jahr: 2024
• Jahr: April 2024
• Umfang: 7 S.
• Illustrationen: Illustrationen
• Fussnoten: Online verfügbar: 13. Februar 2024, Artikelversion: 16. Februar 2024 ; Gesehen am 21.08.2024
• Titel Quelle: Enthalten in: European journal of radiology
• Ort Quelle: Amsterdam [u.a.] : Elsevier Science, 1990
• Jahr Quelle: 2024
• Band/Heft Quelle: 173(2024) vom: Apr., Artikel-ID 111364, Seite 1-7
• ISSN Quelle: 1872-7727
• DOI: doi:10.1016/j.ejrad.2024.111364
• Datenträger: Online-Ressource
• Sprache: eng
• Sach-SW: Artificial intelligence
• Sach-SW: Computed tomography
• Sach-SW: Deep learning
• Sach-SW: Neural network
• Sach-SW: Trauma
• Sach-SW: Vertebral body fracture
• K10plus-PPN: 1899281479

Abstract

Purpose - We developed and tested a neural network for automated detection and stability analysis of vertebral body fractures on computed tomography (CT). - Materials and Methods - 257 patients who underwent CT were included in this Institutional Review Board (IRB) approved study. 463 fractured and 1883 non-fractured vertebral bodies were included, with 190 fractures unstable. Two readers identified vertebral body fractures and assessed their stability. A combination of a Hierarchical Convolutional Neural Network (hNet) and a fracture Classification Network (fNet) was used to build a neural network for the automated detection and stability analysis of vertebral body fractures on CT. Two final test settings were chosen: one with vertebral body levels C1/2 included and one where they were excluded. - Results - The mean age of the patients was 68 ± 14 years. 140 patients were female. The network showed a slightly higher diagnostic performance when excluding C1/2. Accordingly, the network was able to distinguish fractured and non-fractured vertebral bodies with a sensitivity of 75.8 % and a specificity of 80.3 %. Additionally, the network determined the stability of the vertebral bodies with a sensitivity of 88.4 % and a specificity of 80.3 %. The AUC was 87 % and 91 % for fracture detection and stability analysis, respectively. The sensitivity of our network in indicating the presence of at least one fracture / one unstable fracture within the whole spine achieved values of 78.7 % and 97.2 %, respectively, when excluding C1/2. - Conclusion - The developed neural network can automatically detect vertebral body fractures and evaluate their stability concurrently with a high diagnostic performance.