EUVIMEDEUVIMED entdecken
MetaanalyseSystematische Übersicht

Artificial intelligence for triaging of breast cancer screening mammograms and workload reduction: A meta-analysis of a deep learning software

Debora Xavier iD, Isabele Miyawaki, Carlos Alberto Campello Jorge, Gabriela Batalini Freitas Silva, Maxwell Lloyd iD, Fabio Moraes, Bhavika Patel, Felipe Batalini iD

Journal of Medical Screening · 2024

DOI: 10.1177/09691413231219952 ↗

Kurz gefasst

Metaanalyse in der Zeitschrift Journal of Medical Screening, 2024. Verfasst von Debora Xavier und 7 weiteren Autor:innen. Beteiligte Einrichtung: Federal University of Para, Belem, PA, Brazil. Hauptthemen laut MEDLINE: Breast Neoplasms, Deep Learning, Early Detection of Cancer, Mammography. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 30 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

Deep learning (DL) has shown promising results for improving mammographic breast cancer diagnosis. However, the impact of artificial intelligence (AI) on the breast cancer screening process has not yet been fully elucidated in terms of potential workload reduction. We aim to assess if AI-based triaging of breast cancer screening mammograms could reduce the radiologist's workload with non-inferior sensitivity.

Methods

PubMed, EMBASE, Cochrane Central, and Web of Science databases were systematically searched for studies that evaluated AI algorithms on computer-aided triage of breast cancer screening mammograms. We extracted data from homogenous studies and performed a proportion meta-analysis with a random-effects model to examine the radiologist's workload reduction (proportion of low-risk mammograms that could be theoretically ruled out from human's assessment) and the software's sensitivity to breast cancer detection.

Results

Thirteen studies were selected for full review, and three studies that used the same commercially available DL algorithm were included in the meta-analysis. In the 156,852 examinations included, the threshold of 7 was identified as optimal. With these parameters, radiologist workload decreased by 68.3% (95%CI 0.655–0.711, I² = 98.76%, p < 0.001), while achieving a sensitivity of 93.1% (95%CI 0.882–0.979, I² = 83.86%, p = 0.002) and a specificity of 68.7% (95% CI 0.684–0.723, I² = 97.5%, p < 0.01).

Conclusions

The deployment of DL computer-aided triage of breast cancer screening mammograms reduces the radiology workload while maintaining high sensitivity. Although the implementation of AI remains complex and heterogeneous, it is a promising tool to optimize healthcare resources.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Breast NeoplasmsDeep LearningEarly Detection of CancerMammographyTriageWorkloadFemaleHumansSensitivity and SpecificitySoftware

Stichwörter der Autor:innen

Artificial intelligencebreast cancercancer screeningdeep learningmeta-analysis

Autor:innen und Institutionen

  • Federal University of Para, Belem, PA, Brazil.
  • Federal University of Parana, Curitiba, PR, Brazil.
  • Federal University of Mato Grosso, Cuiaba, MT, Brazil.
  • Hospital Municipal Joao de Caires, Prado Ferreira, PR, Brazil.
  • Beth Israel Deaconess Medical Center, Boston, MA, USA.
  • Department of Oncology, Queen's University, Kingston, ON, Canada.

ORCID-Profile: Debora Xavier, Maxwell Lloyd, Felipe Batalini

Zitieren

APA

Xavier, D., Miyawaki, I., Campello Jorge, C. A., Freitas Silva, G. B., Lloyd, M., Moraes, F., Patel, B., & Batalini, F. (2024). Artificial intelligence for triaging of breast cancer screening mammograms and workload reduction: A meta-analysis of a deep learning software. Journal of Medical Screening. https://doi.org/10.1177/09691413231219952

Vancouver

Xavier D, Miyawaki I, Campello Jorge CA, Freitas Silva GB, Lloyd M, Moraes F, et al. Artificial intelligence for triaging of breast cancer screening mammograms and workload reduction: A meta-analysis of a deep learning software. Journal of Medical Screening. 2024. doi:10.1177/09691413231219952

BibTeX
@article{Xavier2024,
  author = {Xavier, Debora and Miyawaki, Isabele and Campello Jorge, Carlos Alberto and Freitas Silva, Gabriela Batalini and Lloyd, Maxwell and Moraes, Fabio and Patel, Bhavika and Batalini, Felipe},
  title = {Artificial intelligence for triaging of breast cancer screening mammograms and workload reduction: A meta-analysis of a deep learning software},
  journal = {Journal of Medical Screening},
  year = {2024},
  doi = {10.1177/09691413231219952}
}
Kostenlos starten →