Deep Learning Algorithms Versus Radiologists in Digital Breast Tomosynthesis for Breast Cancer Detection: Systematic Review and Meta-Analysis - Takeaways - MDSpire

Deep Learning Algorithms Versus Radiologists in Digital Breast Tomosynthesis for Breast Cancer Detection: Systematic Review and Meta-Analysis

  • By

  • Shewen Lyu

  • Zepeng Wang

  • Yujing Mu

  • Luyao Wang

  • Xiaohua Pei

  • May 6, 2026

  • 0 min

Share

  • 1

    Breast cancer is the most common cancer among women, with 2.3 million new cases and 666,000 deaths globally in 2022.

  • 2

    Digital breast tomosynthesis (DBT) improves cancer detection rates but increases interpretation time and the risk of misdiagnosis.

  • 3

    Deep learning algorithms show promise in enhancing lesion detection in DBT but face challenges with false positives and generalizability.

  • 4

    The systematic review analyzed data from 38,565 patients to compare the diagnostic performance of deep learning and radiologists.

  • 5

    The study adhered to PRISMA-DTA guidelines and utilized the PROBAST+AI tool for quality assessment of included studies.

Original Source(s)

Deep Learning Algorithms Versus Radiologists in Digital Breast Tomosynthesis for Breast Cancer Detection: Systematic Review and Meta-Analysis

  • by Shewen Lyu, Zepeng Wang, Yujing Mu, Luyao Wang, Xiaohua Pei

  • May 6, 2026

Related Content

Chronic psychosocial stress: a role in breast cancer etiology?

Vitamin D-related genetic variants as predictive biomarkers for breast cancer in Jordanian women

Longitudinal predictor analysis of pain in breast cancer survivors on aromatase inhibitors—the PAC-WOMAN trial