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

Precisely identifying sulcal features in brain MRI is made challenging by thevariability of brain folding. This research introduces an innovative 3Dexplainability frame-work that validates outputs from deep learning networks intheir ability to detect the paracingulate sulcus, an anatomical feature thatmay or may not be present on the frontal medial surface of the human brain.This study trained and tested two networks, amalgamating local explainabilitytechniques GradCam and SHAP with a dimensionality reduction method. Theexplainability framework provided both localized and global explanations, alongwith accuracy of classification results, revealing pertinent sub-regionscontributing to the decision process through a post-fusion transformation ofexplanatory and statistical features. Leveraging the TOP-OSLO dataset of MRIacquired from patients with schizophrenia, greater accuracies of paracingulatesulcus detection (presence or absence) were found in the left compared to righthemispheres with distinct, but extensive sub-regions contributing to eachclassification outcome. The study also inadvertently highlighted the criticalrole of an unbiased annotation protocol in maintaining network performancefairness. Our proposed method not only offers automated, impartial annotationsof a variable sulcus but also provides insights into the broader anatomicalvariations associated with its presence throughout the brain. The adoption ofthis methodology holds promise for instigating further explorations andinquiries in the field of neuroscience.

A 3D explainability framework to uncover learning patterns and crucial sub-regions in variable sulci recognition