EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Improving traumatic fracture detection on radiographs with artificial intelligence support: a multi-reader study

Rikke Bachmann iD, Gozde Gunes iD, Stine Hangaard iD, Andreas Nexmann, Pavel Lisouski, Mikael Boesen iD, Michael Lundemann iD, Scott G Baginski iD

BJR|Open · 12.12.2023 · 6 (1)

DOI: 10.1093/bjro/tzae011 ↗

Kurz gefasst

Fachartikel in der Zeitschrift BJR|Open, online erschienen am 25.04.2024. Verfasst von Rikke Bachmann und 7 weiteren Autor:innen. Beteiligte Einrichtung: Radiobotics ApS, Copenhagen, Denmark. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: AI.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

The aim of this study was to evaluate the diagnostic performance of nonspecialist readers with and without the use of an artificial intelligence (AI) support tool to detect traumatic fractures on radiographs of the appendicular skeleton.

Methods

The design was a retrospective, fully crossed multi-reader, multi-case study on a balanced dataset of patients (≥2 years of age) with an AI tool as a diagnostic intervention. Fifteen readers assessed 340 radiographic exams, with and without the AI tool in 2 different sessions and the time spent was automatically recorded. Reference standard was established by 3 consultant radiologists. Sensitivity, specificity, and false positives per patient were calculated.

Results

Patient-wise sensitivity increased from 72% to 80% (P < .05) and patient-wise specificity increased from 81% to 85% (P < .05) in exams aided by the AI tool compared to the unaided exams. The increase in sensitivity resulted in a relative reduction of missed fractures of 29%. The average rate of false positives per patient decreased from 0.16 to 0.14, corresponding to a relative reduction of 21%. There was no significant difference in average reading time spent per exam. The largest gain in fracture detection performance, with AI support, across all readers, was on nonobvious fractures with a significant increase in sensitivity of 11 percentage points (pp) (60%-71%).

Conclusions

The diagnostic performance for detection of traumatic fractures on radiographs of the appendicular skeleton improved among nonspecialist readers tested AI fracture detection support tool showed an overall reader improvement in sensitivity and specificity when supported by an AI tool. Improvement was seen in both sensitivity and specificity without negatively affecting the interpretation time. Advances in knowledge The division and analysis of obvious and nonobvious fractures are novel in AI reader comparison studies like this.

Schlagwörter

Stichwörter der Autor:innen

artificial intelligencediagnostic performancefracture detectionmulti-reader study

Autor:innen und Institutionen

  • Radiobotics ApS, Copenhagen, Denmark.
  • Private Ortaca Yucelen Hospital, Turkey.
  • Department of Radiology, Herlev and Gentofte, Copenhagen University Hospital, Denmark.
  • Department of Radiology and Radiological AI Testcenter (RAIT) Denmark, Bispebjerg and Frederiksberg, Copenhagen University Hospital, Denmark.
  • Department of Clinical Medicine, Faculty of Health, and Medical Sciences, University of Copenhagen, Denmark.
  • Virtual Radiologic, Eden Prairie, MN, United States.

ORCID-Profile: Rikke Bachmann, Gozde Gunes, Stine Hangaard, Mikael Boesen, Michael Lundemann, Scott G Baginski

Förderung

  • AI

Zitieren

APA

Bachmann, R., Gunes, G., Hangaard, S., Nexmann, A., Lisouski, P., Boesen, M., Lundemann, M., & Baginski, S. G. (2023). Improving traumatic fracture detection on radiographs with artificial intelligence support: a multi-reader study. BJR|Open, 6(1). https://doi.org/10.1093/bjro/tzae011

Vancouver

Bachmann R, Gunes G, Hangaard S, Nexmann A, Lisouski P, Boesen M, et al. Improving traumatic fracture detection on radiographs with artificial intelligence support: a multi-reader study. BJR|Open. 2023;6(1). doi:10.1093/bjro/tzae011

BibTeX
@article{Bachmann2023,
  author = {Bachmann, Rikke and Gunes, Gozde and Hangaard, Stine and Nexmann, Andreas and Lisouski, Pavel and Boesen, Mikael and Lundemann, Michael and Baginski, Scott G},
  title = {Improving traumatic fracture detection on radiographs with artificial intelligence support: a multi-reader study},
  journal = {BJR|Open},
  year = {2023},
  volume = {6},
  number = {1},
  doi = {10.1093/bjro/tzae011}
}
Kostenlos starten →