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

Automatic segmentation of liver lesions is a fundamental requirement towardsthe creation of computer aided diagnosis (CAD) and decision support systems(CDS). Traditional segmentation approaches depend heavily upon hand-craftedfeatures and a priori knowledge of the user. As such, these methods aredifficult to adopt within a clinical environment. Recently, deep learningmethods based on fully convolutional networks (FCNs) have been successful inmany segmentation problems primarily because they leverage a large labelleddataset to hierarchically learn the features that best correspond to theshallow visual appearance as well as the deep semantics of the areas to besegmented. However, FCNs based on a 16 layer VGGNet architecture have limitedcapacity to add additional layers. Therefore, it is challenging to learn morediscriminative features among different classes for FCNs. In this study, weovercome these limitations using deep residual networks (ResNet) to segmentliver lesions. ResNet contain skip connections between convolutional layers,which solved the problem of the training degradation of training accuracy invery deep networks and thereby enables the use of additional layers forlearning more discriminative features. In addition, we achieve more preciseboundary definitions through a novel cascaded ResNet architecture withmulti-scale fusion to gradually learn and infer the boundaries of both theliver and the liver lesions. Our proposed method achieved 4th place in the ISBI2017 Liver Tumor Segmentation Challenge by the submission deadline.

Automatic Liver Lesion Detection using Cascaded Deep Residual Networks