HIBMatch: Hypergraph Information Bottleneck for Semi-supervised Alzheimer's Progression

TL;DR

HIBMatch is a semi-supervised hypergraph-based framework that leverages information bottleneck and consistency regularisation to improve Alzheimer's progression prediction using multimodal data, especially with limited labeled samples.

Contribution

The paper introduces HIBMatch, a novel semi-supervised hypergraph architecture utilizing information bottleneck and regularisation strategies for better future MCI conversion prediction.

Findings

Outperforms state-of-the-art methods on ADNI dataset

Effectively leverages unlabeled data through contrastive loss

Enhances robustness and generalisation in Alzheimer's prognosis

Abstract

Alzheimer's disease progression prediction is critical for patients with early Mild Cognitive Impairment (MCI) to enable timely intervention and improve their quality of life. While existing progression prediction techniques demonstrate potential with multimodal data, they are highly limited by their reliance on labelled data and fail to account for a key element of future progression prediction: not all features extracted at the current moment may be relevant for predicting progression several years later. To address these limitations in the literature, we design a novel semi-supervised multimodal learning hypergraph architecture, termed HIBMatch, by harnessing hypergraph knowledge based on information bottleneck and consistency regularisation strategies. Firstly, our framework utilises hypergraphs to represent multimodal data, encompassing both imaging and non-imaging modalities. Secondly, to harmonise relevant information from the currently captured data for future MCI conversion prediction, we propose a Hypergraph Information Bottleneck (HIB) that discriminates against irrelevant information, thereby focusing exclusively on harmonising relevant information for future MCI conversion prediction. Thirdly, our method enforces consistency regularisation between the HIB and a discriminative classifier to enhance the robustness and generalisation capabilities of HIBMatch under both topological and feature perturbations. Finally, to fully exploit the unlabeled data, HIBMatch incorporates a cross-modal contrastive loss for data efficiency. Extensive experiments on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset demonstrate that our proposed HIBMatch framework surpasses existing state-of-the-art methods in Alzheimer's disease prognosis.