Modeling Neurodegeneration in silico With Deep Learning

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 fo...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Anup Tuladhar, Jasmine A. Moore, Zahinoor Ismail, Nils D. Forkert
Formato: article
Lenguaje:EN
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://doaj.org/article/dc3f4ca0168a451daf3727e49504414c
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:dc3f4ca0168a451daf3727e49504414c
record_format dspace
spelling oai:doaj.org-article:dc3f4ca0168a451daf3727e49504414c2021-11-19T07:54:39ZModeling Neurodegeneration in silico With Deep Learning1662-519610.3389/fninf.2021.748370https://doaj.org/article/dc3f4ca0168a451daf3727e49504414c2021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fninf.2021.748370/fullhttps://doaj.org/toc/1662-5196Deep 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.Anup TuladharAnup TuladharJasmine A. MooreJasmine A. MooreJasmine A. MooreZahinoor IsmailZahinoor IsmailZahinoor IsmailZahinoor IsmailZahinoor IsmailNils D. ForkertNils D. ForkertNils D. ForkertNils D. ForkertFrontiers Media S.A.articledeep neural networks (DNN)posterior cortical atrophy (PCA)neurodegenerative diseasesAlzheimer’s diseasein silico simulationvisual object recognitionNeurosciences. Biological psychiatry. NeuropsychiatryRC321-571ENFrontiers in Neuroinformatics, Vol 15 (2021)
institution DOAJ
collection DOAJ
language EN
topic deep neural networks (DNN)
posterior cortical atrophy (PCA)
neurodegenerative diseases
Alzheimer’s disease
in silico simulation
visual object recognition
Neurosciences. Biological psychiatry. Neuropsychiatry
RC321-571
spellingShingle deep neural networks (DNN)
posterior cortical atrophy (PCA)
neurodegenerative diseases
Alzheimer’s disease
in silico simulation
visual object recognition
Neurosciences. Biological psychiatry. Neuropsychiatry
RC321-571
Anup Tuladhar
Anup Tuladhar
Jasmine A. Moore
Jasmine A. Moore
Jasmine A. Moore
Zahinoor Ismail
Zahinoor Ismail
Zahinoor Ismail
Zahinoor Ismail
Zahinoor Ismail
Nils D. Forkert
Nils D. Forkert
Nils D. Forkert
Nils D. Forkert
Modeling Neurodegeneration in silico With Deep Learning
description 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.
format article
author Anup Tuladhar
Anup Tuladhar
Jasmine A. Moore
Jasmine A. Moore
Jasmine A. Moore
Zahinoor Ismail
Zahinoor Ismail
Zahinoor Ismail
Zahinoor Ismail
Zahinoor Ismail
Nils D. Forkert
Nils D. Forkert
Nils D. Forkert
Nils D. Forkert
author_facet Anup Tuladhar
Anup Tuladhar
Jasmine A. Moore
Jasmine A. Moore
Jasmine A. Moore
Zahinoor Ismail
Zahinoor Ismail
Zahinoor Ismail
Zahinoor Ismail
Zahinoor Ismail
Nils D. Forkert
Nils D. Forkert
Nils D. Forkert
Nils D. Forkert
author_sort Anup Tuladhar
title Modeling Neurodegeneration in silico With Deep Learning
title_short Modeling Neurodegeneration in silico With Deep Learning
title_full Modeling Neurodegeneration in silico With Deep Learning
title_fullStr Modeling Neurodegeneration in silico With Deep Learning
title_full_unstemmed Modeling Neurodegeneration in silico With Deep Learning
title_sort modeling neurodegeneration in silico with deep learning
publisher Frontiers Media S.A.
publishDate 2021
url https://doaj.org/article/dc3f4ca0168a451daf3727e49504414c
work_keys_str_mv AT anuptuladhar modelingneurodegenerationinsilicowithdeeplearning
AT anuptuladhar modelingneurodegenerationinsilicowithdeeplearning
AT jasmineamoore modelingneurodegenerationinsilicowithdeeplearning
AT jasmineamoore modelingneurodegenerationinsilicowithdeeplearning
AT jasmineamoore modelingneurodegenerationinsilicowithdeeplearning
AT zahinoorismail modelingneurodegenerationinsilicowithdeeplearning
AT zahinoorismail modelingneurodegenerationinsilicowithdeeplearning
AT zahinoorismail modelingneurodegenerationinsilicowithdeeplearning
AT zahinoorismail modelingneurodegenerationinsilicowithdeeplearning
AT zahinoorismail modelingneurodegenerationinsilicowithdeeplearning
AT nilsdforkert modelingneurodegenerationinsilicowithdeeplearning
AT nilsdforkert modelingneurodegenerationinsilicowithdeeplearning
AT nilsdforkert modelingneurodegenerationinsilicowithdeeplearning
AT nilsdforkert modelingneurodegenerationinsilicowithdeeplearning
_version_ 1718420289604288512