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

Knowledge Graph (KG) plays a crucial role in Medical Report Generation (MRG)because it reveals the relations among diseases and thus can be utilized toguide the generation process. However, constructing a comprehensive KG islabor-intensive and its applications on the MRG process are under-explored. Inthis study, we establish a complete KG on chest X-ray imaging that includes 137types of diseases and abnormalities. Based on this KG, we find that the currentMRG data sets exhibit a long-tailed problem in disease distribution. Tomitigate this problem, we introduce a novel augmentation strategy that enhancesthe representation of disease types in the tail-end of the distribution. Wefurther design a two-stage MRG approach, where a classifier is first trained todetect whether the input images exhibit any abnormalities. The classifiedimages are then independently fed into two transformer-based generators,namely, ``disease-specific generator" and ``disease-free generator" to generatethe corresponding reports. To enhance the clinical evaluation of whether thegenerated reports correctly describe the diseases appearing in the input image,we propose diverse sensitivity (DS), a new metric that checks whether generateddiseases match ground truth and measures the diversity of all generateddiseases. Results show that the proposed two-stage generation framework andaugmentation strategies improve DS by a considerable margin, indicating anotable reduction in the long-tailed problem associated with under-representeddiseases.

Rethinking Medical Report Generation: Disease Revealing Enhancement with Knowledge Graph