Multimodal deep learning models for early detection of Alzheimer’s disease stage

Мультимодальные модели глубокого обучения для раннего выявления стадии болезни Альцгеймера
Tong Li, May Dongmei Wang, Hamid Reza Hassanzadeh, Janani Venugopalan
2021-02-05

3D convolutional neural networksADNI datasetAlzheimer’s disease stagingmultimodal deep learningstacked denoising autoencoders
Most current Alzheimer's disease (AD) and mild cognitive disorders (MCI) studies use single data modality to make predictions such as AD stages. The fusion of multiple data modalities can provide a holistic view of AD staging analysis. Thus, we use deep learning (DL) to integrally analyze imaging (magnetic resonance imaging (MRI)), genetic (single nucleotide polymorphisms (SNPs)), and clinical test data to classify patients into AD, MCI, and controls (CN). We use stacked denoising auto-encoders to extract features from clinical and genetic data, and use 3D-convolutional neural networks (CNNs) for imaging data. We also develop a novel data interpretation method to identify top-performing features learned by the deep-models with clustering and perturbation analysis. Using Alzheimer's disease neuroimaging initiative (ADNI) dataset, we demonstrate that deep models outperform shallow models, including support vector machines, decision trees, random forests, and k-nearest neighbors. In addition, we demonstrate that integrating multi-modality data outperforms single modality models in terms of accuracy, precision, recall, and meanF1 scores. Our models have identified hippocampus, amygdala brain areas, and the Rey Auditory Verbal Learning Test (RAVLT) as top distinguished features, which are consistent with the known AD literature.
1
A multimodal deep-learning framework integrates MRI, SNP, and clinical-test data to classify patients as Alzheimer’s disease, mild cognitive impairment, or cognitively normal.
2
Interpretation analysis identifies the hippocampus, amygdala, and Rey Auditory Verbal Learning Test as top discriminative features, consistent with established Alzheimer’s disease findings.
3
Multimodal data integration outperforms single-modality models in accuracy, precision, recall, and mean F1 score.
4
On the ADNI dataset, deep-learning models outperform shallow methods including support vector machines, decision trees, random forests, and k-nearest neighbors.
5
Stacked denoising autoencoders extract clinical and genetic features, while 3D convolutional neural networks process MRI data.

Alzheimer’s disease, mild cognitive impairment, and cognitively normal individuals characterized by MRI, SNP, and clinical test data

Multimodal deep-learning-based classification of disease stage and identification of distinguishing imaging, genetic, and clinical features

Publication Details
Publication Date
2021-02-05
Journal
Publisher
ISSN
Cited by
745
Access Type
Author Information
Authors
Tong Li
May Dongmei Wang
Hamid Reza Hassanzadeh
Janani Venugopalan
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%