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

Planning of radiotherapy involves accurate segmentation of a large number oforgans at risk, i.e. organs for which irradiation doses should be minimized toavoid important side effects of the therapy. We propose a deep learning methodfor segmentation of organs at risk inside the brain region, from MagneticResonance (MR) images. Our system performs segmentation of eight structures:eye, lens, optic nerve, optic chiasm, pituitary gland, hippocampus, brainstemand brain. We propose an efficient algorithm to train neural networks for anend-to-end segmentation of multiple and non-exclusive classes, addressingproblems related to computational costs and missing ground truth segmentationsfor a subset of classes. We enforce anatomical consistency of the result in apostprocessing step, in particular we introduce a graph-based algorithm forsegmentation of the optic nerves, enforcing the connectivity between the eyesand the optic chiasm. We report cross-validated quantitative results on adatabase of 44 contrast-enhanced T1-weighted MRIs with provided segmentationsof the considered organs at risk, which were originally used for radiotherapyplanning. In addition, the segmentations produced by our model on anindependent test set of 50 MRIs are evaluated by an experienced radiotherapistin order to qualitatively assess their accuracy. The mean distances betweenproduced segmentations and the ground truth ranged from 0.1 mm to 0.7 mm acrossdifferent organs. A vast majority (96 %) of the produced segmentations werefound acceptable for radiotherapy planning.

Anatomically Consistent Segmentation of Organs at Risk in MRI with Convolutional Neural Networks