Breast area affects the performance of a commercial artificial intelligence algorithm assessment of negative digital breast tomosynthesis exams.

Emily C Barre¹, Yinhao Ren², Derek L Nguyen³, Joseph Y Lo³, Lars J Grimm³

¹Duke University School of Medicine, 40 Duke Medicine Circle, 124 Davison Building, Durham, NC 27710, United States. Electronic address: emily.barre.author@gmail.com.

²iCAD, 2 Townsend West, Suite 6, Nashua, NH 03063, United States.

³Department of Radiology, Duke University School of Medicine, 2301 Erwin Road, Durham, NC 27710, United States.

PubMed PMC DOI PDF

Abstract

OBJECTIVE: To understand whether cancer-neutral image attributes (breast area and number of slices) impact an AI algorithm assessment of negative digital breast tomosynthesis (DBT) screening exams. METHODS: This retrospective cohort study included women from a single institution whose screening mammogram was interpreted as negative between 2016 and 2019. All patients had at least 2 years follow-u…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free Account Sign In

Want unlimited research access? See Pro plans

Mentioned Companies

ICAD
affiliation

NIH Funding

Grant #11179197
Dynamic imaging and tissue biomarker models to delineate indolent from aggressive breast calcifications
DUKE UNIVERSITY
$802,303 (FY2025)

Other Funding

NCI NIH HHS(R01 CA271237)
United States

MeSH Terms

Humans0Female0Mammography*Algorithms*Retrospective Studies0Breast Neoplasms*Middle Aged0Artificial Intelligence*Radiographic Image Interpretation, Computer-Assisted*Breast*Aged0

Keywords

AdultsBreastComputer applications-3DMammography

Article Info

PMID: 41990687
PMCID: PMC13156931
DOI: 10.1016/j.ejrad.2026.112864
Received: September 21, 2025
Accepted: April 11, 2026

How to Cite

Barre EC et al. Breast area affects the performance of a commercial artificial intelligence algorithm assessment of negative digital breast tomosynthesis exams. Eur J Radiol2026;200112864. doi:10.1016/j.ejrad.2026.112864

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.