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
. 2022 Nov 17;22(22):8887.
doi: 10.3390/s22228887.

Zoom-In Neural Network Deep-Learning Model for Alzheimer's Disease Assessments

Bohyun Wang  1 , Joon S Lim  1
Affiliations

Zoom-In Neural Network Deep-Learning Model for Alzheimer's Disease Assessments

Bohyun Wang et al. Sensors (Basel). .

Abstract

Deep neural networks have been successfully applied to generate predictive patterns from medical and diagnostic data. This paper presents an approach for assessing persons with Alzheimer's disease (AD) mild cognitive impairment (MCI), compared with normal control (NC) persons, using the zoom-in neural network (ZNN) deep-learning algorithm. ZNN stacks a set of zoom-in learning units (ZLUs) in a feedforward hierarchy without backpropagation. The resting-state fMRI (rs-fMRI) dataset for AD assessments was obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI). The Automated Anatomical Labeling (AAL-90) atlas, which provides 90 neuroanatomical functional regions, was used to assess and detect the implicated regions in the course of AD. The features of the ZNN are extracted from the 140-time series rs-fMRI voxel values in a region of the brain. ZNN yields the three classification accuracies of AD versus MCI and NC, NC versus AD and MCI, and MCI versus AD and NC of 97.7%, 84.8%, and 72.7%, respectively, with the seven discriminative regions of interest (ROIs) in the AAL-90.

Keywords: AAL functional regions; Alzheimer’s disease; deep neural networks; discriminative regions of interest of Alzheimer’s disease; metacognitive learning; resting-state fMRI.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Structure of the Zoom-in Neural Network (ZNN).
Figure 2
Figure 2
Structure of the Zoom-in Learning Unit (ZLU) (solid lines denote training and dotted lines denote tests).
Figure 3
Figure 3
Schematic diagram for Alzheimer’s disease assessments.
Figure 4
Figure 4
ZNN model for Alzheimer’s disease classification.
Figure 5
Figure 5
Performance improvements by stacking layers of the ZNN for three AD assessments (%).
Figure 6
Figure 6
7 Overlapped discriminative ROI specifications in the AAL-90 from the three AD classifications.
See this image and copyright information in PMC

References

    1. Sutskever I., Martens J. On the importance of initialization and momentum in deep learning; Proceedings of the 30th International Conference on Machine Learning; JMLR Atlanta, GA, USA. June 2013; pp. 16–21.
    1. Crick F. The recent excitement about neural networks. Nature. 1989;337:129–132. doi: 10.1038/337129a0. - DOI - PubMed
    1. Rumelhart D.E., Hinton G.E., Williams R.J. Learning representations by back-propagating errors. Nature. 1986;323:533–536. doi: 10.1038/323533a0. - DOI
    1. Schiess M., Urbanczik R., Senn W. Somato-dendritic Synaptic Plasticity and Error-backpropagation in Active Dendrites. PLoS Comput. Biol. 2016;12:e1004638. doi: 10.1371/journal.pcbi.1004638. - DOI - PMC - PubMed
    1. Bengio Y. Learning deep architectures for AI. Found. Trends Mach. Learn. 2009;2:1–127. doi: 10.1561/2200000006. - DOI

MeSH terms