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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

A key promise of AI applications in healthcare is in increasing access toquality medical care in under-served populations and emerging markets. However,deep learning models are often only trained on data from advantaged populationsthat have the infrastructure and resources required for large-scale datacollection. In this paper, we aim to empirically investigate the potentialimpact of such biases on breast cancer detection in mammograms. We specificallyexplore how a deep learning algorithm trained on screening mammograms from theUS and UK generalizes to mammograms collected at a hospital in China, wherescreening is not widely implemented. For the evaluation, we use a top-scoringmodel developed for the Digital Mammography DREAM Challenge. Despite the changein institution and population composition, we find that the model generalizeswell, exhibiting similar performance to that achieved in the DREAM Challenge,even when controlling for tumor size. We also illustrate a simple but effectivemethod for filtering predictions based on model variance, which can beparticularly useful for deployment in new settings. While there are manycomponents in developing a clinically effective system, these results representa promising step towards increasing access to life-saving screening mammographyin populations where screening rates are currently low.

Validation of a deep learning mammography model in a population with low screening rates