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

In recent years, deep neural networks have achieved state-of-the-artperformance in a variety of recognition and segmentation tasks in medicalimaging including brain tumor segmentation. We investigate that segmenting abrain tumor is facing to the imbalanced data problem where the number of pixelsbelonging to the background class (non tumor pixel) is much larger than thenumber of pixels belonging to the foreground class (tumor pixel). To addressthis problem, we propose a multi-task network which is formed as a cascadedstructure. Our model consists of two targets, i.e., (i) effectivelydifferentiate the brain tumor regions and (ii) estimate the brain tumor mask.The first objective is performed by our proposed contextual brain tumordetection network, which plays a role of an attention gate and focuses on theregion around brain tumor only while ignoring the far neighbor background whichis less correlated to the tumor. The second objective is built upon a 3D atrousresidual network and under an encode-decode network in order to effectivelysegment both large and small objects (brain tumor). Our 3D atrous residualnetwork is designed with a skip connection to enables the gradient from thedeep layers to be directly propagated to shallow layers, thus, features ofdifferent depths are preserved and used for refining each other. In order toincorporate larger contextual information from volume MRI data, our networkutilizes the 3D atrous convolution with various kernel sizes, which enlargesthe receptive field of filters. Our proposed network has been evaluated onvarious datasets including BRATS2015, BRATS2017 and BRATS2018 datasets withboth validation set and testing set. Our performance has been benchmarked byboth region-based metrics and surface-based metrics. We also have conductedcomparisons against state-of-the-art approaches.

A Multi-task Contextual Atrous Residual Network for Brain Tumor Detection & Segmentation