• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

基于深度学习的阿尔茨海默病神经影像分析方法研究进展。

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

机构信息

Department of Computer Science, Gachon University, Sujeong-gu, Seongnam-si 13557, Gyeonggi-do, Republic of Korea.

出版信息

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

DOI:10.3390/s22228887
PMID:36433486
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC9694235/
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.

摘要

深度神经网络已成功应用于从医学和诊断数据中生成预测模式。本文提出了一种使用 Zoom-in 神经网络（ZNN）深度学习算法评估阿尔茨海默病（AD）轻度认知障碍（MCI）患者与正常对照（NC）个体的方法。ZNN 在无反向传播的前馈层次结构中堆叠了一组 Zoom-in 学习单元（ZLU）。用于 AD 评估的静息态 fMRI（rs-fMRI）数据集来自阿尔茨海默病神经影像学倡议（ADNI）。使用自动解剖标记（AAL-90）图谱，该图谱提供了 90 个神经解剖学功能区域，用于评估和检测 AD 过程中涉及的区域。ZNN 的特征是从大脑中一个区域的 140 个时间序列 rs-fMRI 体素值中提取出来的。ZNN 分别产生了 AD 与 MCI 和 NC、NC 与 AD 和 MCI、MCI 与 AD 和 NC 的三个分类准确率为 97.7%、84.8%和 72.7%，在 AAL-90 中有 7 个有区别的感兴趣区域（ROI）。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4f87/9694235/53329b1216ec/sensors-22-08887-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4f87/9694235/54f016f9135f/sensors-22-08887-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4f87/9694235/1f07ad867ae4/sensors-22-08887-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4f87/9694235/a9d886222837/sensors-22-08887-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4f87/9694235/c0242488603a/sensors-22-08887-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4f87/9694235/8058161a42ec/sensors-22-08887-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4f87/9694235/53329b1216ec/sensors-22-08887-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4f87/9694235/54f016f9135f/sensors-22-08887-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4f87/9694235/1f07ad867ae4/sensors-22-08887-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4f87/9694235/a9d886222837/sensors-22-08887-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4f87/9694235/c0242488603a/sensors-22-08887-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4f87/9694235/8058161a42ec/sensors-22-08887-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4f87/9694235/53329b1216ec/sensors-22-08887-g006.jpg

相似文献

1
Zoom-In Neural Network Deep-Learning Model for Alzheimer's Disease Assessments.基于深度学习的阿尔茨海默病神经影像分析方法研究进展。
Sensors (Basel). 2022 Nov 17;22(22):8887. doi: 10.3390/s22228887.
2
Application of advanced machine learning methods on resting-state fMRI network for identification of mild cognitive impairment and Alzheimer's disease.先进机器学习方法在静息态功能磁共振成像网络上的应用，用于识别轻度认知障碍和阿尔茨海默病。
Brain Imaging Behav. 2016 Sep;10(3):799-817. doi: 10.1007/s11682-015-9448-7.
3
Temporal and Spatial Analysis of Alzheimer's Disease Based on an Improved Convolutional Neural Network and a Resting-State FMRI Brain Functional Network.基于改进的卷积神经网络和静息态 fMRI 脑功能网络的阿尔茨海默病的时空分析。
Int J Environ Res Public Health. 2022 Apr 8;19(8):4508. doi: 10.3390/ijerph19084508.
4
A parameter-efficient deep learning approach to predict conversion from mild cognitive impairment to Alzheimer's disease.一种参数高效的深度学习方法，用于预测轻度认知障碍向阿尔茨海默病的转化。
Neuroimage. 2019 Apr 1;189:276-287. doi: 10.1016/j.neuroimage.2019.01.031. Epub 2019 Jan 14.
5
A Deep Learning Approach for Automated Diagnosis and Multi-Class Classification of Alzheimer's Disease Stages Using Resting-State fMRI and Residual Neural Networks.基于静息态 fMRI 和残差神经网络的深度学习方法对阿尔茨海默病阶段进行自动诊断和多分类。
J Med Syst. 2019 Dec 18;44(2):37. doi: 10.1007/s10916-019-1475-2.
6
Automated MRI-Based Deep Learning Model for Detection of Alzheimer's Disease Process.基于 MRI 的自动化深度学习模型用于阿尔茨海默病进程的检测。
Int J Neural Syst. 2020 Jun;30(6):2050032. doi: 10.1142/S012906572050032X.
7
A multi-model deep convolutional neural network for automatic hippocampus segmentation and classification in Alzheimer's disease.一种用于阿尔茨海默病中海马自动分割和分类的多模态深度卷积神经网络。
Neuroimage. 2020 Mar;208:116459. doi: 10.1016/j.neuroimage.2019.116459. Epub 2019 Dec 16.
8
Ensembles of Deep Learning Architectures for the Early Diagnosis of the Alzheimer's Disease.用于阿尔茨海默病早期诊断的深度学习架构集成
Int J Neural Syst. 2016 Nov;26(7):1650025. doi: 10.1142/S0129065716500258. Epub 2016 Apr 4.
9
Deep Learning for Alzheimer's Disease Classification using Texture Features.使用纹理特征的深度学习用于阿尔茨海默病分类
Curr Med Imaging Rev. 2019;15(7):689-698. doi: 10.2174/1573405615666190404163233.
10
Automated classification of Alzheimer's disease and mild cognitive impairment using a single MRI and deep neural networks.使用单模态 MRI 和深度神经网络对阿尔茨海默病和轻度认知障碍进行自动分类。
Neuroimage Clin. 2019;21:101645. doi: 10.1016/j.nicl.2018.101645. Epub 2018 Dec 18.

引用本文的文献

1
fMRI-based Alzheimer's disease detection via functional connectivity analysis: a systematic review.基于功能磁共振成像的阿尔茨海默病检测：通过功能连接分析的系统综述。
PeerJ Comput Sci. 2024 Oct 16;10:e2302. doi: 10.7717/peerj-cs.2302. eCollection 2024.
2
The application value of Rs-fMRI-based machine learning models for differentiating mild cognitive impairment from Alzheimer's disease: a systematic review and meta-analysis.基于静息态功能磁共振成像的机器学习模型在区分轻度认知障碍与阿尔茨海默病中的应用价值：一项系统评价和荟萃分析
Neurol Sci. 2025 Jan;46(1):45-62. doi: 10.1007/s10072-024-07731-1. Epub 2024 Sep 3.
3
Multivariate pattern analysis of medical imaging-based Alzheimer's disease.

本文引用的文献

1
Deep Learning-Based Diagnosis of Alzheimer's Disease.基于深度学习的阿尔茨海默病诊断
J Pers Med. 2022 May 18;12(5):815. doi: 10.3390/jpm12050815.
2
Searching for optimal machine learning model to classify mild cognitive impairment (MCI) subtypes using multimodal MRI data.利用多模态 MRI 数据搜索最优机器学习模型来分类轻度认知障碍 (MCI) 亚型。
Sci Rep. 2022 Mar 11;12(1):4284. doi: 10.1038/s41598-022-08231-y.
3
Causal Inference in the Multisensory Brain.多感官大脑中的因果推理。
基于医学影像的阿尔茨海默病的多变量模式分析
Front Med (Lausanne). 2024 Jul 19;11:1412592. doi: 10.3389/fmed.2024.1412592. eCollection 2024.
4
Enhancing generalized anxiety disorder diagnosis precision: MSTCNN model utilizing high-frequency EEG signals.提高广泛性焦虑症诊断精度：利用高频脑电信号的MSTCNN模型
Front Psychiatry. 2023 Dec 21;14:1310323. doi: 10.3389/fpsyt.2023.1310323. eCollection 2023.
5
Potential Ocular Biomarkers for Early Detection of Alzheimer's Disease and Their Roles in Artificial Intelligence Studies.用于阿尔茨海默病早期检测的潜在眼部生物标志物及其在人工智能研究中的作用。
Neurol Ther. 2023 Oct;12(5):1517-1532. doi: 10.1007/s40120-023-00526-0. Epub 2023 Jul 20.
Neuron. 2019 Jun 5;102(5):1076-1087.e8. doi: 10.1016/j.neuron.2019.03.043. Epub 2019 Apr 29.
4
The cingulum bundle: Anatomy, function, and dysfunction.扣带束：解剖、功能与功能障碍。
Neurosci Biobehav Rev. 2018 Sep;92:104-127. doi: 10.1016/j.neubiorev.2018.05.008. Epub 2018 May 16.
5
The neural system of metacognition accompanying decision-making in the prefrontal cortex.前额叶皮层伴随决策的元认知的神经系统。
PLoS Biol. 2018 Apr 23;16(4):e2004037. doi: 10.1371/journal.pbio.2004037. eCollection 2018 Apr.
6
Structural and functional connectional fingerprints in mild cognitive impairment and Alzheimer's disease patients.轻度认知障碍和阿尔茨海默病患者的结构和功能连接指纹图谱
PLoS One. 2017 Mar 23;12(3):e0173426. doi: 10.1371/journal.pone.0173426. eCollection 2017.
7
Random synaptic feedback weights support error backpropagation for deep learning.随机突触反馈权重支持深度学习的误差反向传播。
Nat Commun. 2016 Nov 8;7:13276. doi: 10.1038/ncomms13276.
8
Somato-dendritic Synaptic Plasticity and Error-backpropagation in Active Dendrites.主动树突中的体-树突突触可塑性与误差反向传播
PLoS Comput Biol. 2016 Feb 3;12(2):e1004638. doi: 10.1371/journal.pcbi.1004638. eCollection 2016 Feb.
9
Application of advanced machine learning methods on resting-state fMRI network for identification of mild cognitive impairment and Alzheimer's disease.先进机器学习方法在静息态功能磁共振成像网络上的应用，用于识别轻度认知障碍和阿尔茨海默病。
Brain Imaging Behav. 2016 Sep;10(3):799-817. doi: 10.1007/s11682-015-9448-7.
10
Atrophic Patterns of the Frontal-Subcortical Circuits in Patients with Mild Cognitive Impairment and Alzheimer's Disease.轻度认知障碍和阿尔茨海默病患者额叶-皮质下回路的萎缩模式
PLoS One. 2015 Jun 11;10(6):e0130017. doi: 10.1371/journal.pone.0130017. eCollection 2015.