Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Toward Robust Early Detection of Alzheimer's Disease via an Integrated Multimodal Learning Approach

Yifei Chen, Shenghao Zhu, Zhaojie Fang, Chang Liu, Binfeng Zou, Yuhe Wang, Shuo Chang, Fan Jia, Feiwei Qin, Jin Fan, Yong Peng, Changmiao Wang

TL;DR

An advanced multimodal classification model that integrates clinical, cognitive, neuroimaging, and EEG data to enhance diagnostic accuracy is introduced, significantly improving the distinction between AD, Mild Cognitive Impairment, and Normal Cognition.

Abstract

Alzheimer's Disease (AD) is a complex neurodegenerative disorder marked by memory loss, executive dysfunction, and personality changes. Early diagnosis is challenging due to subtle symptoms and varied presentations, often leading to misdiagnosis with traditional unimodal diagnostic methods due to their limited scope. This study introduces an advanced multimodal classification model that integrates clinical, cognitive, neuroimaging, and EEG data to enhance diagnostic accuracy. The model incorporates a feature tagger with a tabular data coding architecture and utilizes the TimesBlock module to capture intricate temporal patterns in Electroencephalograms (EEG) data. By employing Cross-modal Attention Aggregation module, the model effectively fuses Magnetic Resonance Imaging (MRI) spatial information with EEG temporal data, significantly improving the distinction between AD, Mild Cognitive Impairment, and Normal Cognition. Simultaneously, we have constructed the first AD classification dataset that includes three modalities: EEG, MRI, and tabular data. Our innovative approach aims to facilitate early diagnosis and intervention, potentially slowing the progression of AD. The source code and our private ADMC dataset are available at https://github.com/JustlfC03/MSTNet.

Toward Robust Early Detection of Alzheimer's Disease via an Integrated Multimodal Learning Approach

TL;DR

An advanced multimodal classification model that integrates clinical, cognitive, neuroimaging, and EEG data to enhance diagnostic accuracy is introduced, significantly improving the distinction between AD, Mild Cognitive Impairment, and Normal Cognition.

Abstract

Alzheimer's Disease (AD) is a complex neurodegenerative disorder marked by memory loss, executive dysfunction, and personality changes. Early diagnosis is challenging due to subtle symptoms and varied presentations, often leading to misdiagnosis with traditional unimodal diagnostic methods due to their limited scope. This study introduces an advanced multimodal classification model that integrates clinical, cognitive, neuroimaging, and EEG data to enhance diagnostic accuracy. The model incorporates a feature tagger with a tabular data coding architecture and utilizes the TimesBlock module to capture intricate temporal patterns in Electroencephalograms (EEG) data. By employing Cross-modal Attention Aggregation module, the model effectively fuses Magnetic Resonance Imaging (MRI) spatial information with EEG temporal data, significantly improving the distinction between AD, Mild Cognitive Impairment, and Normal Cognition. Simultaneously, we have constructed the first AD classification dataset that includes three modalities: EEG, MRI, and tabular data. Our innovative approach aims to facilitate early diagnosis and intervention, potentially slowing the progression of AD. The source code and our private ADMC dataset are available at https://github.com/JustlfC03/MSTNet.
Paper Structure (14 sections, 7 equations, 2 figures, 1 table)

This paper contains 14 sections, 7 equations, 2 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related work
  3. Method
  4. Tabular Feature Encoder
  5. Feature Tokenizer
  6. Tabular Encoder Architecture
  7. Temporal Feature Encoder
  8. Cross-modal Attention Aggregation Module
  9. Experiment
  10. Dataset and Experimental Details
  11. Comparison Experiment
  12. Ablation Study
  13. Conclusion
  14. Acknowledgment

Figures (2)

  • Figure 1: Overall framework of the proposed MSTNet. The MSTNet model primarily comprises three parts: Tabular Feature Encoder, Temporal Feature Encoder and Cross-modal Aggregation Encoder.
  • Figure 2: (a) The Feature Tokenizer converts numerical categorical features into embedding vectors. (b) The TimesBlock module performs a 2D transformation on the multi-periodic features of the time-series data.