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

In this work, we exploit the task of joint classification and weaklysupervised localization of thoracic diseases from chest radiographs, with onlyimage-level disease labels coupled with disease severity-level (DSL)information of a subset. A convolutional neural network (CNN) basedattention-guided curriculum learning (AGCL) framework is presented, whichleverages the severity-level attributes mined from radiology reports. Images inorder of difficulty (grouped by different severity-levels) are fed to CNN toboost the learning gradually. In addition, highly confident samples (measuredby classification probabilities) and their corresponding class-conditionalheatmaps (generated by the CNN) are extracted and further fed into the AGCLframework to guide the learning of more distinctive convolutional features inthe next iteration. A two-path network architecture is designed to regress theheatmaps from selected seed samples in addition to the original classificationtask. The joint learning scheme can improve the classification and localizationperformance along with more seed samples for the next iteration. We demonstratethe effectiveness of this iterative refinement framework via extensiveexperimental evaluations on the publicly available ChestXray14 dataset. AGCLachieves over 5.7\% (averaged over 14 diseases) increase in classification AUCand 7%/11% increases in Recall/Precision for the localization task compared tothe state of the art.

Attention-Guided Curriculum Learning for Weakly Supervised Classification and Localization of Thoracic Diseases on Chest Radiographs