A Multi-view Impartial Decision Network for Frontotemporal Dementia Diagnosis

TL;DR

This paper introduces MID-Net, a novel multi-view impartial decision network that leverages expert models and Dirichlet distributions to improve the reliability and accuracy of frontotemporal dementia diagnosis using fMRI data.

Contribution

The paper proposes MID-Net, a new framework that combines multi-view expert opinions with an impartial decision maker to enhance FTD diagnosis reliability and handle conflicting evidence.

Findings

Outperforms previous FTD diagnosis methods on fMRI data

Provides high uncertainty estimates for difficult cases

Effectively integrates multi-view expert opinions

Abstract

Frontotemporal Dementia (FTD) diagnosis has been successfully progress using deep learning techniques. However, current FTD identification methods suffer from two limitations. Firstly, they do not exploit the potential of multi-view functional magnetic resonance imaging (fMRI) for classifying FTD. Secondly, they do not consider the reliability of the multi-view FTD diagnosis. To address these limitations, we propose a reliable multi-view impartial decision network (MID-Net) for FTD diagnosis in fMRI. Our MID-Net provides confidence for each view and generates a reliable prediction without any conflict. To achieve this, we employ multiple expert models to extract evidence from the abundant neural network information contained in fMRI images. We then introduce the Dirichlet Distribution to characterize the expert class probability distribution from an evidence level. Additionally, a novel Impartial Decision Maker (IDer) is proposed to combine the different opinions inductively to arrive at an unbiased prediction without additional computation cost. Overall, our MID-Net dynamically integrates the decisions of different experts on FTD disease, especially when dealing with multi-view high-conflict cases. Extensive experiments on a high-quality FTD fMRI dataset demonstrate that our model outperforms previous methods and provides high uncertainty for hard-to-classify examples. We believe that our approach represents a significant step toward the deployment of reliable FTD decision-making under multi-expert conditions. We will release the codes for reproduction after acceptance.