English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Although deep learning models for abnormality classification can perform wellin screening mammography, the demographic, imaging, and clinicalcharacteristics associated with increased risk of model failure remain unclear.This retrospective study uses the Emory BrEast Imaging Dataset(EMBED)containing mammograms from 115931 patients imaged at Emory Healthcare between2013-2020, with BI-RADS assessment, region of interest coordinates forabnormalities, imaging features, pathologic outcomes, and patient demographics.Multiple deep learning models were trained to distinguish between abnormaltissue patches and randomly selected normal tissue patches from screeningmammograms. We assessed model performance by subgroups defined by age, race,pathologic outcome, tissue density, and imaging characteristics andinvestigated their associations with false negatives (FN) and false positives(FP). We also performed multivariate logistic regression to control forconfounding between subgroups. The top-performing model, ResNet152V2, achievedaccuracy of 92.6%(95%CI=92.0-93.2%), and AUC 0.975(95%CI=0.972-0.978). Beforecontrolling for confounding, nearly all subgroups showed statisticallysignificant differences in model performance. However, after controlling forconfounding, we found lower FN risk associates with Otherrace(RR=0.828;p=.050), biopsy-proven benign lesions(RR=0.927;p=.011), andmass(RR=0.921;p=.010) or asymmetry(RR=0.854;p=.040); higher FN risk associateswith architectural distortion (RR=1.037;p<.001). Higher FP risk associates toBI-RADS density C(RR=1.891;p<.001) and D(RR=2.486;p<.001). Our resultsdemonstrate subgroup analysis is important in mammogram classifier performanceevaluation, and controlling for confounding between subgroups elucidates thetrue associations between variables and model failure. These results can helpguide developing future breast cancer detection models.

Multivariate Analysis on Performance Gaps of Artificial Intelligence Models in Screening Mammography