Modeling Neurodegeneration in silico With Deep Learning

Anup Tuladhar; Jasmine A Moore; Zahinoor Ismail; Nils D Forkert

doi:10.3389/fninf.2021.748370

Modeling Neurodegeneration in silico With Deep Learning

Front Neuroinform. 2021 Nov 19:15:748370. doi: 10.3389/fninf.2021.748370. eCollection 2021.

Authors

Anup Tuladhar^{1

2}, Jasmine A Moore^{1

2

3}, Zahinoor Ismail^{2

4

5

6

7}, Nils D Forkert^{1

2

4

8}

Affiliations

¹ Department of Radiology, University of Calgary, Calgary, AB, Canada.
² Hotchkiss Brain Institute, University of Calgary, Calgary, AB, Canada.
³ Biomedical Engineering Program, University of Calgary, Calgary, AB, Canada.
⁴ Department of Clinical Neurosciences, University of Calgary, Calgary, AB, Canada.
⁵ Department of Community Health Sciences, University of Calgary, Calgary, AB, Canada.
⁶ Department of Psychiatry, University of Calgary, Calgary, AB, Canada.
⁷ O'Brien Institute for Public Health, University of Calgary, Calgary, AB, Canada.
⁸ Alberta Children's Hospital Research Institute, University of Calgary, Calgary, AB, Canada.

Abstract

Deep neural networks, inspired by information processing in the brain, can achieve human-like performance for various tasks. However, research efforts to use these networks as models of the brain have primarily focused on modeling healthy brain function so far. In this work, we propose a paradigm for modeling neural diseases in silico with deep learning and demonstrate its use in modeling posterior cortical atrophy (PCA), an atypical form of Alzheimer's disease affecting the visual cortex. We simulated PCA in deep convolutional neural networks (DCNNs) trained for visual object recognition by randomly injuring connections between artificial neurons. Results showed that injured networks progressively lost their object recognition capability. Simulated PCA impacted learned representations hierarchically, as networks lost object-level representations before category-level representations. Incorporating this paradigm in computational neuroscience will be essential for developing in silico models of the brain and neurological diseases. The paradigm can be expanded to incorporate elements of neural plasticity and to other cognitive domains such as motor control, auditory cognition, language processing, and decision making.

Keywords: Alzheimer’s disease; cognitive computational neuroscience; deep neural networks (DNN); in silico simulation; neurodegenerative diseases; posterior cortical atrophy (PCA); visual object agnosia; visual object recognition.