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

Accuracy validation of cortical thickness measurement is a difficult problemdue to the lack of ground truth data. To address this need, many methods havebeen developed to synthetically induce gray matter (GM) atrophy in an MRI viadeformable registration, creating a set of images with known changes incortical thickness. However, these methods often cause blurring in atrophiedregions, and cannot simulate realistic atrophy within deep sulci wherecerebrospinal fluid (CSF) is obscured or absent. In this paper, we present asolution using a self-supervised inpainting model to generate CSF in theseregions and create images with more plausible GM/CSF boundaries. Specifically,we introduce a novel, 3D GAN model that incorporates patch-based dropouttraining, edge map priors, and sinusoidal positional encoding, all of which areestablished methods previously limited to 2D domains. We show that ourframework significantly improves the quality of the resulting synthetic imagesand is adaptable to unseen data with fine-tuning. We also demonstrate that ourresulting dataset can be employed for accuracy validation of corticalsegmentation and thickness measurement.

Self-Supervised CSF Inpainting with Synthetic Atrophy for Improved Accuracy Validation of Cortical Surface Analyses