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

Despite the widespread use of deep learning methods for semantic segmentationof images that are acquired from a single source, clinicians often usemulti-domain data for a detailed analysis. For instance, CT and MRI haveadvantages over each other in terms of imaging quality, artifacts, and outputcharacteristics that lead to differential diagnosis. The capacity of currentsegmentation techniques is only allow to work for an individual domain due totheir differences. However, the models that are capable of working on allmodalities are essentially needed for a complete solution. Furthermore,robustness is drastically affected by the number of samples in the trainingstep, especially for deep learning models. Hence, there is a necessity that allavailable data regardless of data domain should be used for reliable methods.For this purpose, this manuscript aims to implement a novel model that canlearn robust representations from cross-domain data by encapsulating distinctand shared patterns from different modalities. Precisely, covariate shiftproperty is retained with structural modification and adversarial loss wheresparse and rich representations are obtained. Hence, a single parameter set isused to perform cross-domain segmentation task. The superiority of the proposedmethod is that no information related to modalities are provided in eithertraining or inference phase. The tests on CT and MRI liver data acquired inroutine clinical workflows show that the proposed model outperforms all otherbaseline with a large margin. Experiments are also conducted on Covid-19dataset that it consists of CT data where significant intra-class visualdifferences are observed. Similarly, the proposed method achieves the bestperformance.

Cross-Domain Segmentation with Adversarial Loss and Covariate Shift for Biomedical Imaging