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

We explore several oversampling techniques for an imbalanced multi-labelclassification problem, a setting often encountered when developing models forComputer-Aided Diagnosis (CADx) systems. While most CADx systems aim tooptimize classifiers for overall accuracy without considering the relativedistribution of each class, we look into using synthetic sampling to increaseper-class performance when predicting the degree of malignancy. Using low-levelimage features and a random forest classifier, we show that using syntheticoversampling techniques increases the sensitivity of the minority classes by anaverage of 7.22% points, with as much as a 19.88% point increase in sensitivityfor a particular minority class. Furthermore, the analysis of low-level imagefeature distributions for the synthetic nodules reveals that these nodules canprovide insights on how to preprocess image data for better classificationperformance or how to supplement the original datasets when more dataacquisition is feasible.

Synthetic Sampling for Multi-Class Malignancy Prediction