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

Convolutional networks (ConvNets) have achieved promising accuracy forvarious anatomical segmentation tasks. Despite the success, these methods canbe sensitive to data appearance variations. Considering the large variabilityof scans caused by artifacts, pathologies, and scanning setups, robust ConvNetsare vital for clinical applications, while have not been fully explored. Inthis paper, we propose to mitigate the challenge by enabling ConvNets'awareness of the underlying anatomical invariances among imaging scans.Specifically, we introduce a fully convolutional Constraint Adoption Module(CAM) that incorporates probabilistic atlas priors as explicit constraints forpredictions over a locally connected Conditional Random Field (CFR), whicheffectively reinforces the anatomical consistency of the labeling outputs. Wedesign the CAM to be flexible for boosting various ConvNet, and compact forco-optimizing with ConvNets for fusion parameters that leads to the optimalperformance. We show the advantage of such atlas priors fusion is two-fold withtwo brain parcellation tasks. First, our models achieve state-of-the-artaccuracy among ConvNet-based methods on both datasets, by significantlyreducing structural abnormalities of predictions. Second, we can largely boostthe robustness of existing ConvNets, proved by: (i) testing on scans withsynthetic pathologies, and (ii) training and evaluation on scans of differentscanning setups across datasets. Our method is proposing to be easily adoptedto existing ConvNets by fine-tuning with CAM plugged in for accuracy androbustness boosts.

Atlas-aware ConvNetfor Accurate yet Robust Anatomical Segmentation