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

Deep-learning-based object detection methods show promise for improvingscreening mammography, but high rates of false positives can hinder theireffectiveness in clinical practice. To reduce false positives, we identifythree challenges: (1) unlike natural images, a malignant mammogram typicallycontains only one malignant finding; (2) mammography exams contain two views ofeach breast, and both views ought to be considered to make a correctassessment; (3) most mammograms are negative and do not contain any findings.In this work, we tackle the three aforementioned challenges by: (1) leveragingSparse R-CNN and showing that sparse detectors are more appropriate than densedetectors for mammography; (2) including a multi-view cross-attention module tosynthesize information from different views; (3) incorporating multi-instancelearning (MIL) to train with unannotated images and perform breast-levelclassification. The resulting model, M&M, is a Multi-view and Multi-instancelearning system that can both localize malignant findings and providebreast-level predictions. We validate M&M's detection and classificationperformance using five mammography datasets. In addition, we demonstrate theeffectiveness of each proposed component through comprehensive ablationstudies.

M&M: Tackling False Positives in Mammography with a Multi-view and Multi-instance Learning Sparse Detector