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 neural networks exhibit limited generalizability across images withdifferent entangled domain features and categorical features. Learninggeneralizable features that can form universal categorical decision boundariesacross domains is an interesting and difficult challenge. This problem occursfrequently in medical imaging applications when attempts are made to deploy andimprove deep learning models across different image acquisition devices, acrossacquisition parameters or if some classes are unavailable in new trainingdatabases. To address this problem, we propose Mutual Information-basedDisentangled Neural Networks (MIDNet), which extract generalizable categoricalfeatures to transfer knowledge to unseen categories in a target domain. Theproposed MIDNet adopts a semi-supervised learning paradigm to alleviate thedependency on labeled data. This is important for real-world applications wheredata annotation is time-consuming, costly and requires training and expertise.We extensively evaluate the proposed method on fetal ultrasound datasets fortwo different image classification tasks where domain features are respectivelydefined by shadow artifacts and image acquisition devices. Experimental resultsshow that the proposed method outperforms the state-of-the-art on theclassification of unseen categories in a target domain with sparsely labeledtraining data.

Mutual Information-based Disentangled Neural Networks for Classifying  Unseen Categories in Different Domains: Application to Fetal Ultrasound  Imaging