EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An overview of the performance of AI in fracture detection in lumbar and thoracic spine radiographs on a per vertebra basis

Oppenheimer J, Lüken S, Geveshausen S, Hamm B, Niehues S M

Skeletal Radiology · 2024

DOI: 10.1007/s00256-024-04626-2 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Skeletal Radiology, 2024. Verfasst von Oppenheimer J und 4 weiteren Autor:innen. Beteiligte Einrichtung: Charité Universitätsmedizin Berlin, Klinik für Radiologie, Campus Benjamin FranklinHindenburgdamm 30, 12203, Berlin, Germany. jonas.oppenheimer@chari…. Hauptthemen laut MEDLINE: Spinal Fractures, Thoracic Vertebrae, Lumbar Vertebrae, Sensitivity and Specificity. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 16 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Charité - Universitätsmedizin Berlin.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

Subtle spinal compression fractures can easily be missed. AI may help in interpreting these images. We propose to test the performance of an FDA-approved algorithm for fracture detection in radiographs on a per vertebra basis, assessing performance based on grade of compression, presence of foreign material, severity of degenerative changes, and acuity of the fracture.

Methods

Thoracic and lumbar spine radiographs with inquiries for fracture were retrospectively collected and analyzed by the AI. The presence or absence of fracture was defined by the written report or cross-sectional imaging where available. Fractures were classified semi-quantitatively by the Genant classification, by acuity, by the presence of foreign material, and overall degree of degenerative change of the spine. The results of the AI were compared to the gold standard.

Results

A total of 512 exams were included, depicting 4114 vertebra with 495 fractures. Overall sensitivity was 63.2% for the lumbar spine, significantly higher than the thoracic spine with 50.6%. Specificity was 96.7 and 98.3% respectively. Sensitivity increased with fracture grade, without a significant difference between grade 2 and 3 compression fractures (lumbar spine: grade 1, 52.5%; grade 2, 72.3%; grade 3, 75.8%; thoracic spine: grade 1, 42.4%; grade 2, 60.0%; grade 3, 60.0%). The presence of foreign material and a high degree of degenerative changes reduced sensitivity.

Conclusion

Overall performance of the AI on a per vertebra basis was degraded in clinically relevant scenarios such as for low-grade compression fractures.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Spinal FracturesThoracic VertebraeLumbar VertebraeSensitivity and SpecificityHumansRetrospective StudiesMaleFemaleMiddle AgedAlgorithmsAgedRadiographic Image Interpretation, Computer-AssistedAdultArtificial IntelligenceFractures, CompressionAged, 80 and over

Stichwörter der Autor:innen

Artificial intelligenceComputer-aided diagnosisRadiographyTrauma

Autor:innen und Institutionen

  • Charité Universitätsmedizin Berlin, Klinik für Radiologie, Campus Benjamin FranklinHindenburgdamm 30, 12203, Berlin, Germany. jonas.oppenheimer@charite.de.
  • Charité Universitätsmedizin Berlin, Klinik für Radiologie, Campus Benjamin FranklinHindenburgdamm 30, 12203, Berlin, Germany.

Förderung

  • Charité - Universitätsmedizin Berlin

Zitieren

APA

J, O., S, L., S, G., B, H., & S M, N. (2024). An overview of the performance of AI in fracture detection in lumbar and thoracic spine radiographs on a per vertebra basis. Skeletal Radiology. https://doi.org/10.1007/s00256-024-04626-2

Vancouver

J O, S L, S G, B H, S M N. An overview of the performance of AI in fracture detection in lumbar and thoracic spine radiographs on a per vertebra basis. Skeletal Radiology. 2024. doi:10.1007/s00256-024-04626-2

BibTeX
@article{J2024,
  author = {J, Oppenheimer and S, Lüken and S, Geveshausen and B, Hamm and S M, Niehues},
  title = {An overview of the performance of AI in fracture detection in lumbar and thoracic spine radiographs on a per vertebra basis},
  journal = {Skeletal Radiology},
  year = {2024},
  doi = {10.1007/s00256-024-04626-2}
}
Kostenlos starten →