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

Although the segmentation of brain structures in ultrasound helps initializeimage based registration, assist brain shift compensation, and providesinterventional decision support, the task of segmenting grey and white matterin cranial ultrasound is very challenging and has not been addressed yet. Wetrain a multi-scale fully convolutional neural network simultaneously for twoclasses in order to segment real clinical 3D ultrasound data. Parallel pathwaysworking at different levels of resolution account for high frequency specklenoise and global 3D image features. To ensure reproducibility, the publiclyavailable RESECT dataset is utilized for training and cross-validation. Due tothe absence of a ground truth, we train with weakly annotated label. Weimplement label transfer from MRI to US, which is prone to a residual butinevitable registration error. To further improve results, we perform transferlearning using synthetic US data. The resulting method leads to excellent Dicescores of 0.7080, 0.8402 and 0.9315 for grey matter, white matter andbackground. Our proposed methodology sets an unparalleled standard for whiteand grey matter segmentation in 3D intracranial ultrasound.

Weakly-Supervised White and Grey Matter Segmentation in 3D Brain Ultrasound