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

Obtaining semantic labels on a large scale radiology image database (215,786key images from 61,845 unique patients) is a prerequisite yet bottleneck totrain highly effective deep convolutional neural network (CNN) models for imagerecognition. Nevertheless, conventional methods for collecting image labels(e.g., Google search followed by crowd-sourcing) are not applicable due to theformidable difficulties of medical annotation tasks for those who are notclinically trained. This type of image labeling task remains non-trivial evenfor radiologists due to uncertainty and possible drastic inter-observervariation or inconsistency.  In this paper, we present a looped deep pseudo-task optimization procedurefor automatic category discovery of visually coherent and clinically semantic(concept) clusters. Our system can be initialized by domain-specific (CNNtrained on radiology images and text report derived labels) or generic(ImageNet based) CNN models. Afterwards, a sequence of pseudo-tasks areexploited by the looped deep image feature clustering (to refine image labels)and deep CNN training/classification using new labels (to obtain more taskrepresentative deep features). Our method is conceptually simple and based onthe hypothesized "convergence" of better labels leading to better trained CNNmodels which in turn feed more effective deep image features to facilitate moremeaningful clustering/labels. We have empirically validated the convergence anddemonstrated promising quantitative and qualitative results. Category labels ofsignificantly higher quality than those in previous work are discovered. Thisallows for further investigation of the hierarchical semantic nature of thegiven large-scale radiology image database.

Unsupervised Category Discovery via Looped Deep Pseudo-Task Optimization Using a Large Scale Radiology Image Database