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

Deep learning has quickly become the weapon of choice for brain lesionsegmentation. However, few existing algorithms pre-configure any biologicalcontext of their chosen segmentation tissues, and instead rely on the neuralnetwork's optimizer to develop such associations de novo. We present a novelmethod for applying deep neural networks to the problem of glioma tissuesegmentation that takes into account the structured nature of gliomas -edematous tissue surrounding mutually-exclusive regions of enhancing andnon-enhancing tumor. We trained multiple deep neural networks with a 3D U-Netarchitecture in a tree structure to create segmentations for edema,non-enhancing tumor, and enhancing tumor regions. Specifically, training wasconfigured such that the whole tumor region including edema was predictedfirst, and its output segmentation was fed as input into separate models topredict enhancing and non-enhancing tumor. Our method was trained and evaluatedon the publicly available BraTS dataset, achieving Dice scores of 0.882, 0.732,and 0.730 for whole tumor, enhancing tumor and tumor core respectively.

Sequential 3D U-Nets for Biologically-Informed Brain Tumor Segmentation