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

Deep learning-based Computer-Aided Diagnosis (CAD) has attracted appealingattention in academic researches and clinical applications. Nevertheless, theConvolutional Neural Networks (CNNs) diagnosis system heavily relies on thewell-labeled lesion dataset, and the sensitivity to the variation of datadistribution also restricts the potential application of CNNs in CAD.Unsupervised Domain Adaptation (UDA) methods are developed to solve theexpensive annotation and domain gaps problem and have achieved remarkablesuccess in medical image analysis. Yet existing UDA approaches only adaptknowledge learned from the source lesion domain to a single target lesiondomain, which is against the clinical scenario: the new unlabeled targetdomains to be diagnosed always arrive in an online and continual manner.Moreover, the performance of existing approaches degrades dramatically onpreviously learned target lesion domains, due to the newly learned knowledgeoverwriting the previously learned knowledge (i.e., catastrophic forgetting).To deal with the above issues, we develop a meta-adaptation framework namedConsecutive Lesion Knowledge Meta-Adaptation (CLKM), which mainly consists ofSemantic Adaptation Phase (SAP) and Representation Adaptation Phase (RAP) tolearn the diagnosis model in an online and continual manner. In the SAP, thesemantic knowledge learned from the source lesion domain is transferred toconsecutive target lesion domains. In the RAP, the feature-extractor isoptimized to align the transferable representation knowledge across the sourceand multiple target lesion domains.

Consecutive Knowledge Meta-Adaptation Learning for Unsupervised Medical Diagnosis