Evidence-aware multi-modal data fusion and its application to total knee replacement prediction

TL;DR

This paper introduces an evidence-aware multi-modal data fusion framework using Dempster-Shafer theory to improve total knee replacement prediction by accounting for the reliability of different data sources.

Contribution

It proposes a novel fusion method that incorporates evidence scores to handle conflicting information from multiple modalities in medical prediction tasks.

Findings

Outperforms baseline models on the OAI dataset

Effectively manages conflicting modality information

Enhances prediction accuracy with evidence-based fusion

Abstract

Deep neural networks have been widely studied for predicting a medical condition, such as total knee replacement (TKR). It has shown that data of different modalities, such as imaging data, clinical variables and demographic information, provide complementary information and thus can improve the prediction accuracy together. However, the data sources of various modalities may not always be of high quality, and each modality may have only partial information of medical condition. Thus, predictions from different modalities can be opposite, and the final prediction may fail in the presence of such a conflict. Therefore, it is important to consider the reliability of each source data and the prediction output when making a final decision. In this paper, we propose an evidence-aware multi-modal data fusion framework based on the Dempster-Shafer theory (DST). The backbone models contain an image branch, a non-image branch and a fusion branch. For each branch, there is an evidence network that takes the extracted features as input and outputs an evidence score, which is designed to represent the reliability of the output from the current branch. The output probabilities along with the evidence scores from multiple branches are combined with the Dempster's combination rule to make a final prediction. Experimental results on the public OA initiative (OAI) dataset for the TKR prediction task show the superiority of the proposed fusion strategy on various backbone models.