Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2019 Dec 5;14(12):e0225759.
doi: 10.1371/journal.pone.0225759. eCollection 2019.

Neuroimaging modality fusion in Alzheimer's classification using convolutional neural networks

Arjun Punjabi  1 , Adam Martersteck  2   3 , Yanran Wang  1 , Todd B Parrish  2 , Aggelos K Katsaggelos  1 ; Alzheimer’s Disease Neuroimaging Initiative
Affiliations

Neuroimaging modality fusion in Alzheimer's classification using convolutional neural networks

Arjun Punjabi et al. PLoS One. .

Abstract

Automated methods for Alzheimer's disease (AD) classification have the potential for great clinical benefits and may provide insight for combating the disease. Machine learning, and more specifically deep neural networks, have been shown to have great efficacy in this domain. These algorithms often use neurological imaging data such as MRI and FDG PET, but a comprehensive and balanced comparison of the MRI and amyloid PET modalities has not been performed. In order to accurately determine the relative strength of each imaging variant, this work performs a comparison study in the context of Alzheimer's dementia classification using the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset with identical neural network architectures. Furthermore, this work analyzes the benefits of using both modalities in a fusion setting and discusses how these data types may be leveraged in future AD studies using deep learning.

PubMed Disclaimer

Conflict of interest statement

The authors have declared that no competing interests exist.

Figures

Fig 1
Fig 1. Pre-processing pipeline for a single subject.
A subject has N MRI scanning sessions and M PET scanning sessions; therefore, the pipeline yields N MRI images and M PET images. The pipeline is repeated for each subject in the dataset.
Fig 2
Fig 2. Convolutional neural network for one modality.
A single MRI or PET volume is taken as input, and the output is a binary diagnosis label of either “Healthy” or “AD”.
Fig 3
Fig 3. Convolutional neural network for fusing MRI and PET modalities.
An MRI and PET scan from a single patient is taken as input, and the output is again a binary diagnosis label.
See this image and copyright information in PMC

References

    1. Hebert L, Scherr P, Bienias J, Bennett D, Evans D. State-specific projections through 2025 of Alzheimer disease prevalence. Neurology. 2004;62(9):1645–1645. 10.1212/01.wnl.0000123018.01306.10 - DOI - PubMed
    1. Cuingnet R, Gerardin E, Tessieras J, Auzias G, Lehéricy S, Habert MO, et al. Automatic classification of patients with Alzheimer’s disease from structural MRI: a comparison of ten methods using the ADNI database. NeuroImage. 2011;56(2):766–781. 10.1016/j.neuroimage.2010.06.013 - DOI - PubMed
    1. Ashburner J. A fast diffeomorphic image registration algorithm. NeuroImage. 2007;38(1):95–113. 10.1016/j.neuroimage.2007.07.007 - DOI - PubMed
    1. Klöppel S, Stonnington CM, Chu C, Draganski B, Scahill RI, Rohrer JD, et al. Automatic classification of MR scans in Alzheimer’s disease. Brain. 2008;131(3):681–689. 10.1093/brain/awm319 - DOI - PMC - PubMed
    1. Liu M, Zhang D, Adeli E, Shen D. Inherent Structure-Based Multiview Learning With Multitemplate Feature Representation for Alzheimer’s Disease Diagnosis. IEEE Transactions on Biomedical Engineering. 2016;63(7):1473–1482. 10.1109/TBME.2015.2496233 - DOI - PMC - PubMed

Publication types

LinkOut - more resources