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/

Zendy Plus

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

Zendy Tools

Zendy Open

Deep learning based methods have achieved state-of-the-art performance forautomated white matter (WM) tract segmentation. In these methods, thesegmentation model needs to be trained with a large number of manuallyannotated scans, which can be accumulated throughout time. When novel WMtracts, i.e., tracts not included in the existing annotated WM tracts, are tobe segmented, additional annotations of these novel WM tracts need to becollected. Since tract annotation is time-consuming and costly, it is desirableto make only a few annotations of novel WM tracts for training the segmentationmodel, and previous work has addressed this problem by transferring theknowledge learned for segmenting existing WM tracts to the segmentation ofnovel WM tracts. However, accurate segmentation of novel WM tracts can still bechallenging in the one-shot setting, where only one scan is annotated for thenovel WM tracts. In this work, we explore the problem of one-shot segmentationof novel WM tracts. Since in the one-shot setting the annotated training datais extremely scarce, based on the existing knowledge transfer framework, wepropose to further perform extensive data augmentation for the single annotatedscan, where synthetic annotated training data is produced. We have designedseveral different strategies that mask out regions in the single annotated scanfor data augmentation. Our method was evaluated on public and in-housedatasets. The experimental results show that our method improves the accuracyof one-shot segmentation of novel WM tracts.

One-Shot Segmentation of Novel White Matter Tracts via Extensive Data Augmentation