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

Despite the potential of weakly supervised learning to automatically annotatemassive amounts of data, little is known about its limitations for use incomputer-aided diagnosis (CAD). For CT specifically, interpreting theperformance of CAD algorithms can be challenging given the large number ofco-occurring diseases. This paper examines the effect of co-occurring diseaseswhen training classification models by weakly supervised learning, specificallyby comparing multi-label and multiple binary classifiers using the sametraining data. Our results demonstrated that the binary model outperformed themulti-label classification in every disease category in terms of AUC. However,this performance was heavily influenced by co-occurring diseases in the binarymodel, suggesting it did not always learn the correct appearance of thespecific disease. For example, binary classification of lung nodules resultedin an AUC of < 0.65 when there were no other co-occurring diseases, but whenlung nodules co-occurred with emphysema, the performance reached AUC > 0.80. Wehope this paper revealed the complexity of interpreting disease classificationperformance in weakly supervised models and will encourage researchers toexamine the effect of co-occurring diseases on classification performance inthe future.

Co-occurring Diseases Heavily Influence the Performance of Weakly Supervised Learning Models for Classification of Chest CT