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

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 (m...

Full description

Saved in:
Bibliographic Details
Published in:Scientific reports Vol. 11; no. 1; pp. 3254 - 13
Main Authors: Venugopalan, Janani, Tong, Li, Hassanzadeh, Hamid Reza, Wang, May D.
Format: Journal Article
Language:English
Published: London Nature Publishing Group UK 05.02.2021
Nature Publishing Group
Nature Portfolio
Subjects:
631/114/2164
631/114/2401
Alzheimer Disease - diagnosis
Alzheimer's disease
Amygdala
Auditory discrimination learning
Cognitive ability
Data interpretation
Data Mining
Deep Learning
Diagnosis, Computer-Assisted
Early Diagnosis
Humanities and Social Sciences
Humans
Magnetic resonance imaging
multidisciplinary
Neural networks
Neurodegenerative diseases
Neuroimaging
Science
Science (multidisciplinary)
Single-nucleotide polymorphism
ISSN:2045-2322, 2045-2322
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2045-2322
2045-2322
DOI:10.1038/s41598-020-74399-w