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

The significant features identified in a representative subset of the datasetduring the learning process of an artificial intelligence model are referred toas a 'global' explanation. 3D global explanations are crucial in neuroimaging,where a complex representational space demands more than basic 2Dinterpretations. However, current studies in the literature often lack theaccuracy, comprehensibility, and 3D global explanations needed in neuroimagingand beyond. To address this gap, we developed an explainable artificialintelligence (XAI) 3D-Framework capable of providing accurate, low-complexityglobal explanations. We evaluated the framework using various 3D deep learningmodels trained on a well-annotated cohort of 596 structural MRIs. The binaryclassification task focused on detecting the presence or absence of theparacingulate sulcus, a highly variable brain structure associated withpsychosis. Our framework integrates statistical features (Shape) and XAImethods (GradCam and SHAP) with dimensionality reduction, ensuring thatexplanations reflect both model learning and cohort-specific variability. Bycombining Shape, GradCam, and SHAP, our framework reduces inter-methodvariability, enhancing the faithfulness and reliability of global explanations.These robust explanations facilitated the identification of criticalsub-regions, including the posterior temporal and internal parietal regions, aswell as the cingulate region and thalamus, suggesting potential genetic ordevelopmental influences.  Our XAI 3D-Framework leverages global explanations to uncover the broaderdevelopmental context of specific cortical features. This approach advances thefields of deep learning and neuroscience by offering insights into normativebrain development and atypical trajectories linked to mental illness, pavingthe way for more reliable and interpretable AI applications in neuroimaging.

An explainable three dimension framework to uncover learning patterns: A unified look in variable sulci recognition