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/

Zendy Plus

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

Zendy Tools

Zendy Open

Chest radiography is the most common medical image examination for screeningand diagnosis in hospitals. Automatic interpretation of chest X-rays at thelevel of an entry-level radiologist can greatly benefit work prioritization andassist in analyzing a larger population. Subsequently, several datasets anddeep learning-based solutions have been proposed to identify diseases based onchest X-ray images. However, these methods are shown to be vulnerable to shiftin the source of data: a deep learning model performing well when tested on thesame dataset as training data, starts to perform poorly when it is tested on adataset from a different source. In this work, we address this challenge ofgeneralization to a new source by forcing the network to learn asource-invariant representation. By employing an adversarial training strategy,we show that a network can be forced to learn a source-invariantrepresentation. Through pneumonia-classification experiments on multi-sourcechest X-ray datasets, we show that this algorithm helps in improvingclassification accuracy on a new source of X-ray dataset.

Learning Invariant Feature Representation to Improve Generalization across Chest X-ray Datasets