Dementia in Convolutional Neural Networks: Using Deep Learning Models to Simulate Neurodegeneration of the Visual System.

IF 2.7 4区 医学 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS
Jasmine A Moore, Anup Tuladhar, Zahinoor Ismail, Pauline Mouches, Matthias Wilms, Nils D Forkert
{"title":"Dementia in Convolutional Neural Networks: Using Deep Learning Models to Simulate Neurodegeneration of the Visual System.","authors":"Jasmine A Moore,&nbsp;Anup Tuladhar,&nbsp;Zahinoor Ismail,&nbsp;Pauline Mouches,&nbsp;Matthias Wilms,&nbsp;Nils D Forkert","doi":"10.1007/s12021-022-09602-6","DOIUrl":null,"url":null,"abstract":"<p><p>Although current research aims to improve deep learning networks by applying knowledge about the healthy human brain and vice versa, the potential of using such networks to model and study neurodegenerative diseases remains largely unexplored. In this work, we present an in-depth feasibility study modeling progressive dementia in silico with deep convolutional neural networks. Therefore, networks were trained to perform visual object recognition and then progressively injured by applying neuronal as well as synaptic injury. After each iteration of injury, network object recognition accuracy, saliency map similarity between the intact and injured networks, and internal activations of the degenerating models were evaluated. The evaluation revealed that cognitive function of the network progressively decreased with increasing injury load whereas this effect was much more pronounced for synaptic damage. The effects of neurodegeneration found for the in silico model are especially similar to the loss of visual cognition seen in patients with posterior cortical atrophy.</p>","PeriodicalId":49761,"journal":{"name":"Neuroinformatics","volume":"21 1","pages":"45-55"},"PeriodicalIF":2.7000,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Neuroinformatics","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1007/s12021-022-09602-6","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS","Score":null,"Total":0}
引用次数: 1

Abstract

Although current research aims to improve deep learning networks by applying knowledge about the healthy human brain and vice versa, the potential of using such networks to model and study neurodegenerative diseases remains largely unexplored. In this work, we present an in-depth feasibility study modeling progressive dementia in silico with deep convolutional neural networks. Therefore, networks were trained to perform visual object recognition and then progressively injured by applying neuronal as well as synaptic injury. After each iteration of injury, network object recognition accuracy, saliency map similarity between the intact and injured networks, and internal activations of the degenerating models were evaluated. The evaluation revealed that cognitive function of the network progressively decreased with increasing injury load whereas this effect was much more pronounced for synaptic damage. The effects of neurodegeneration found for the in silico model are especially similar to the loss of visual cognition seen in patients with posterior cortical atrophy.

Abstract Image

卷积神经网络中的痴呆:使用深度学习模型模拟视觉系统的神经变性。
尽管目前的研究旨在通过应用关于健康人脑的知识来改进深度学习网络,反之亦然,但使用这种网络来建模和研究神经退行性疾病的潜力在很大程度上仍未被探索。在这项工作中,我们提出了一项深入的可行性研究,用深度卷积神经网络在计算机上模拟进行性痴呆。因此,神经网络被训练来进行视觉物体识别,然后通过神经元和突触损伤来逐步损伤。在每次损伤迭代后,评估网络目标识别精度、完整和损伤网络之间的显著性图相似性以及退化模型的内部激活情况。结果表明,随着损伤负荷的增加,神经网络的认知功能逐渐下降,而突触损伤的认知功能下降更为明显。在计算机模型中发现的神经退行性变的影响与后皮层萎缩患者的视觉认知丧失特别相似。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Neuroinformatics
Neuroinformatics 医学-计算机:跨学科应用
CiteScore
6.00
自引率
6.70%
发文量
54
审稿时长
3 months
期刊介绍: Neuroinformatics publishes original articles and reviews with an emphasis on data structure and software tools related to analysis, modeling, integration, and sharing in all areas of neuroscience research. The editors particularly invite contributions on: (1) Theory and methodology, including discussions on ontologies, modeling approaches, database design, and meta-analyses; (2) Descriptions of developed databases and software tools, and of the methods for their distribution; (3) Relevant experimental results, such as reports accompanie by the release of massive data sets; (4) Computational simulations of models integrating and organizing complex data; and (5) Neuroengineering approaches, including hardware, robotics, and information theory studies.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信