Differential Diagnosis of Frontotemporal Dementia, Alzheimer's Disease, and Normal Aging Using a Multi-Scale Multi-Type Feature Generative Adversarial Deep Neural Network on Structural Magnetic Resonance Images

Peer reviewed: 
Yes, item is peer reviewed.
Scholarly level: 
Faculty/Staff
Final version published as: 

Ma, D., Lu, D., Popuri, K., Wang, L., Beg, M. F., & Alzheimer’s Disease Neuroimaging Initiative. (2020). Differential Diagnosis of Frontotemporal Dementia, Alzheimer’s Disease, and Normal Aging Using a Multi-Scale Multi-Type Feature Generative Adversarial Deep Neural Network on Structural Magnetic Resonance Images. Frontiers in Neuroscience, 14, 853. https://doi.org/10.3389/fnins.2020.00853

Date created: 
2020-10-22
Identifier: 
DOI: 10.3389/fnins.2020.00853
Keywords: 
Differential diagnosis
Magnetic resonance imaging
Generative adversarial network
Frontotemporal dementia (FTD)
Alzheimer's disease
Abstract: 

Methods: Alzheimer's disease and Frontotemporal dementia are the first and third most common forms of dementia. Due to their similar clinical symptoms, they are easily misdiagnosed as each other even with sophisticated clinical guidelines. For disease-specific intervention and treatment, it is essential to develop a computer-aided system to improve the accuracy of their differential diagnosis. Recent advances in deep learning have delivered some of the best performance for medical image recognition tasks. However, its application to the differential diagnosis of AD and FTD pathology has not been explored.

Approach: In this study, we proposed a novel deep learning based framework to distinguish between brain images of normal aging individuals and subjects with AD and FTD. Specifically, we combined the multi-scale and multi-type MRI-base image features with Generative Adversarial Network data augmentation technique to improve the differential diagnosis accuracy.

Results: Each of the multi-scale, multitype, and data augmentation methods improved the ability for differential diagnosis for both AD and FTD. A 10-fold cross validation experiment performed on a large sample of 1,954 images using the proposed framework achieved a high overall accuracy of 88.28%.

Conclusions: The salient contributions of this study are three-fold: (1) our experiments demonstrate that the combination of multiple structural features extracted at different scales with our proposed deep neural network yields superior performance than individual features; (2) we show that the use of Generative Adversarial Network for data augmentation could further improve the discriminant ability of the network regarding challenging tasks such as differentiating dementia sub-types; (3) and finally, we show that ensemble classifier strategy could make the network more robust and stable.

Language: 
English
Document type: 
Article
File(s): 
Sponsor(s): 
Natural Sciences and Engineering Research Council of Canada (NSERC)
Canadian Institutes of Health Research (CIHR)
Michael Smith Foundation for Health Research (MSFHR)
Brain Canada
Pacific Alzheimer Research Foundation (PARF)
Alzheimer Society of Canada (Alzheimer Society Research Program)
National Institutes of Health
National Science Foundation
Statistics: