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

One of the biggest challenges for deep learning algorithms in medical imageanalysis is the indiscriminate mixing of image properties, e.g. artifacts andanatomy. These entangled image properties lead to a semantically redundantfeature encoding for the relevant task and thus lead to poor generalization ofdeep learning algorithms. In this paper we propose a novel representationdisentanglement method to extract semantically meaningful and generalizablefeatures for different tasks within a multi-task learning framework. Deepneural networks are utilized to ensure that the encoded features are maximallyinformative with respect to relevant tasks, while an adversarial regularizationencourages these features to be disentangled and minimally informative aboutirrelevant tasks. We aim to use the disentangled representations to generalizethe applicability of deep neural networks. We demonstrate the advantages of theproposed method on synthetic data as well as fetal ultrasound images. Ourexperiments illustrate that our method is capable of learning disentangledinternal representations. It outperforms baseline methods in multiple tasks,especially on images with new properties, e.g. previously unseen artifacts infetal ultrasound.

Representation Disentanglement for Multi-task Learning with application to Fetal Ultrasound