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

The crossMoDA challenge aims to automatically segment the vestibularschwannoma (VS) tumor and cochlea regions of unlabeled high-resolution T2 scansby leveraging labeled contrast-enhanced T1 scans. The 2022 edition extends thesegmentation task by including multi-institutional scans. In this work, weproposed an unpaired cross-modality segmentation framework using dataaugmentation and hybrid convolutional networks. Considering heterogeneousdistributions and various image sizes for multi-institutional scans, we applythe min-max normalization for scaling the intensities of all scans between -1and 1, and use the voxel size resampling and center cropping to obtainfixed-size sub-volumes for training. We adopt two data augmentation methods foreffectively learning the semantic information and generating realistic targetdomain scans: generative and online data augmentation. For generative dataaugmentation, we use CUT and CycleGAN to generate two groups of realistic T2volumes with different details and appearances for supervised segmentationtraining. For online data augmentation, we design a random tumor signalreducing method for simulating the heterogeneity of VS tumor signals.Furthermore, we utilize an advanced hybrid convolutional network withmulti-dimensional convolutions to adaptively learn sparse inter-sliceinformation and dense intra-slice information for accurate volumetricsegmentation of VS tumor and cochlea regions in anisotropic scans. On thecrossMoDA2022 validation dataset, our method produces promising results andachieves the mean DSC values of 72.47% and 76.48% and ASSD values of 3.42 mmand 0.53 mm for VS tumor and cochlea regions, respectively.

An Unpaired Cross-modality Segmentation Framework Using Data  Augmentation and Hybrid Convolutional Networks for Segmenting Vestibular  Schwannoma and Cochlea