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

Frontotemporal Dementia (FTD) diagnosis has been successfully progress usingdeep learning techniques. However, current FTD identification methods sufferfrom two limitations. Firstly, they do not exploit the potential of multi-viewfunctional magnetic resonance imaging (fMRI) for classifying FTD. Secondly,they do not consider the reliability of the multi-view FTD diagnosis. Toaddress these limitations, we propose a reliable multi-view impartial decisionnetwork (MID-Net) for FTD diagnosis in fMRI. Our MID-Net provides confidencefor each view and generates a reliable prediction without any conflict. Toachieve this, we employ multiple expert models to extract evidence from theabundant neural network information contained in fMRI images. We then introducethe Dirichlet Distribution to characterize the expert class probabilitydistribution from an evidence level. Additionally, a novel Impartial DecisionMaker (IDer) is proposed to combine the different opinions inductively toarrive at an unbiased prediction without additional computation cost. Overall,our MID-Net dynamically integrates the decisions of different experts on FTDdisease, especially when dealing with multi-view high-conflict cases. Extensiveexperiments on a high-quality FTD fMRI dataset demonstrate that our modeloutperforms previous methods and provides high uncertainty for hard-to-classifyexamples. We believe that our approach represents a significant step toward thedeployment of reliable FTD decision-making under multi-expert conditions. Wewill release the codes for reproduction after acceptance.

A Multi-view Impartial Decision Network for Frontotemporal Dementia Diagnosis