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

Over the last few years machine learning has demonstrated groundbreakingresults in many areas of medical image analysis, including segmentation. A keyassumption, however, is that the train- and test distributions match. We studya realistic scenario where this assumption is clearly violated, namelysegmentation with missing input modalities. We describe two neural networkapproaches that can handle a variable number of input modalities. The first ismodality dropout: a simple but surprisingly effective modification of thetraining. The second is the unified representation network: a networkarchitecture that maps a variable number of input modalities into a unifiedrepresentation that can be used for downstream tasks such as segmentation. Wedemonstrate that modality dropout makes a standard segmentation networkreasonably robust to missing modalities, but that the same network works evenbetter if trained on the unified representation.

A unified representation network for segmentation with missing modalities