EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Artificial intelligence as a second reader for screening mammography

Etsuji Nakai, Yumi Miyagi, Kazuhiro Suzuki, Alessandro Scoccia Pappagallo, Hiroki Kayama, Takehito Matsuba, Lin Yang, Shawn Xu, Christopher Kelly, Ryan Najafi, Timo Kohlberger, Daniel Golden und 8 weitere

Radiology Advances · 28.05.2024 · 1 (2)

DOI: 10.1093/radadv/umae011 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Radiology Advances, online erschienen am 08.05.2024. Verfasst von Etsuji Nakai und 19 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Google LLC.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Artificial intelligence (AI) has shown promise in mammography interpretation, and its use as a second reader in breast cancer screening may reduce the burden on health care systems.

Purpose

To evaluate the performance differences between routine double read and an AI as a second reader workflow (AISR), where the second reader is replaced with AI. Materials and Methods A cohort of patients undergoing routine breast cancer screening at a single center with mammography was retrospectively collected between 2005 and 2021. A model developed on US and UK data was fine-tuned on Japanese data. We subsequently performed a reader study with 10 qualified readers with varied experience (5 reader pairs), comparing routine double read to an AISR workflow.

Results

A “test set” of 4,059 women (mean age, 56 ± 14 years; 157 positive, 3,902 negative) was collected, with 278 (mean age 55 ± 13 years; 90 positive, 188 negative) evaluated for the reader study. We demonstrate an area under the curve =.84 (95% confidence interval [CI], 0.805-0.881) on the test set, with no significant difference to decisions made in clinical practice (P = .32). Compared with routine double reading, in the AISR arm, sensitivity improved by 7.6% (95% CI, 3.80-11.4; P = .00004) and specificity decreased 3.4% (1.42-5.43; P = .0016), with 71% (212/298) of scans no longer requiring input from a second reader. Variation in recall decision between reader pairs improved from a Cohen kappa of κ = .65 (96% CI, 0.61-0.68) to κ = .74 (96% CI, 0.71-0.77) in the AISR arm.

Conclusion

AISR improves sensitivity, reduces variability and decreases workload compared to routine dual screening.

Förderung

  • Google LLC

Zitieren

APA

Nakai, E., Miyagi, Y., Suzuki, K., Pappagallo, A. S., Kayama, H., Matsuba, T., Yang, L., Xu, S., Kelly, C., Najafi, R., Kohlberger, T., Golden, D., Uddin, A., Nakamura, Y., Kokubu, Y., Takahashi, Y., Ueno, T., Oguchi, M., Ohno, S., & Ledsam, J. R. (2024). Artificial intelligence as a second reader for screening mammography. Radiology Advances, 1(2). https://doi.org/10.1093/radadv/umae011

Vancouver

Nakai E, Miyagi Y, Suzuki K, Pappagallo AS, Kayama H, Matsuba T, et al. Artificial intelligence as a second reader for screening mammography. Radiology Advances. 2024;1(2). doi:10.1093/radadv/umae011

BibTeX
@article{Nakai2024,
  author = {Nakai, Etsuji and Miyagi, Yumi and Suzuki, Kazuhiro and Pappagallo, Alessandro Scoccia and Kayama, Hiroki and Matsuba, Takehito and Yang, Lin and Xu, Shawn and Kelly, Christopher and Najafi, Ryan and Kohlberger, Timo and Golden, Daniel and Uddin, Akib and Nakamura, Yusuke and Kokubu, Yumi and Takahashi, Yoko and Ueno, Takayuki and Oguchi, Masahiko and Ohno, Shinji and Ledsam, Joseph R},
  title = {Artificial intelligence as a second reader for screening mammography},
  journal = {Radiology Advances},
  year = {2024},
  volume = {1},
  number = {2},
  doi = {10.1093/radadv/umae011}
}
Kostenlos starten →