Reliable Multimodality Eye Disease Screening via Mixture of Student's t Distributions

TL;DR

This paper introduces EyeMoSt, a multimodality eye disease screening model that uses a mixture of Student's t distributions to improve reliability and robustness by assessing uncertainties and adaptively fusing modalities.

Contribution

The paper proposes a novel evidential fusion pipeline using a mixture of Student's t distributions to enhance reliability and uncertainty estimation in multimodality eye disease screening.

Findings

Outperforms existing methods in reliability on public and in-house datasets.

Provides effective local and global uncertainty measures.

Can serve as a data quality discriminator.

Abstract

Multimodality eye disease screening is crucial in ophthalmology as it integrates information from diverse sources to complement their respective performances. However, the existing methods are weak in assessing the reliability of each unimodality, and directly fusing an unreliable modality may cause screening errors. To address this issue, we introduce a novel multimodality evidential fusion pipeline for eye disease screening, EyeMoSt, which provides a measure of confidence for unimodality and elegantly integrates the multimodality information from a multi-distribution fusion perspective. Specifically, our model estimates both local uncertainty for unimodality and global uncertainty for the fusion modality to produce reliable classification results. More importantly, the proposed mixture of Student's $t$ distributions adaptively integrates different modalities to endow the model with heavy-tailed properties, increasing robustness and reliability. Our experimental findings on both public and in-house datasets show that our model is more reliable than current methods. Additionally, EyeMost has the potential ability to serve as a data quality discriminator, enabling reliable decision-making for multimodality eye disease screening.