Search research articles

关于 JoVE

概览领导团队博客 JoVE 帮助中心

作者

出版流程编辑委员会范围与政策同行评审常见问题投稿

图书馆员

用户评价订阅访问资源图书馆顾问委员会常见问题

研究

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序

Same author

Tier-specific location of Lewy body pathology and related neuromelanin levels drive dopaminergic cell vulnerability in pigmented non-human primates.

Neurobiology of disease·2026

Same author

Exploring the spatial covariance of cerebral vascular density and amyloid burden in Alzheimer's disease.

Alzheimer's & dementia (Amsterdam, Netherlands)·2026

Same author

Safety and efficacy of staged, bilateral magnetic resonance-guided focused ultrasound pallidothalamic tractotomy for motor complications of Parkinson's disease: a prospective, multicentre, single-arm trial.

The Lancet. Neurology·2026

Same author

Glymphatic clearance as revealed by diffusion tensor imaging along the perivascular space (DTI-ALPS) is associated with Alzheimer's disease neuropathology and periodic rsEEG alpha rhythms in mild cognitive impairment participants.

Alzheimer's & dementia (Amsterdam, Netherlands)·2026

Same author

MRI mapping of nigrostriatal pathway degeneration in early-stage Parkinson's disease.

Neurobiology of disease·2026

Same author

Network based statistics associates increased connectivity to REM sleep disorder and hallucinations in early DLB.

NPJ Parkinson's disease·2026

Search research articles

相关实验视频

Updated: Jul 1, 2025

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

亚空间校正相关性学习与神经成像中的应用.

Rick van Veen¹, Neha Rajendra Bari Tamboli¹, Sofie Lövdal²

¹Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, The Netherlands.

Artificial intelligence in medicine

|March 10, 2024

概括

这项研究引入了一种新的机器学习方法,以减少多中心神经成像数据中的中心特定变异,用于疾病分类. 这种方法提高了在诊断神经退行性疾病,如帕金森氏症时的模型概括性和解释性.

关键词:

一般化矩阵学习向量量化 (GMLVQ)学习向量的量化学习向量的量化.多个来源的数据数据.神经成像是一种神经成像.相关性学习就是学习.

更多相关视频

Modeling the Functional Network for Spatial Navigation in the Human Brain

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

Real-time Video Projection in an MRI for Characterization of Neural Correlates Associated with Mirror Therapy for Phantom Limb Pain

Real-time Video Projection in an MRI for Characterization of Neural Correlates Associated with Mirror Therapy for Phantom Limb Pain

Published on: April 20, 2019

相关实验视频

Last Updated: Jul 1, 2025

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

Modeling the Functional Network for Spatial Navigation in the Human Brain

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

Real-time Video Projection in an MRI for Characterization of Neural Correlates Associated with Mirror Therapy for Phantom Limb Pain

Real-time Video Projection in an MRI for Characterization of Neural Correlates Associated with Mirror Therapy for Phantom Limb Pain

Published on: April 20, 2019

科学领域:

机器学习机器学习
神经成像分析分析神经成像分析
医学数据科学医学数据科学

背景情况:

在机器学习中结合来自多个来源的数据可以引入不必要的变化.
多中心神经成像数据,例如神经退行性疾病的FDG-PET扫描,由于设备和协议的差异,通常会表现出中心依赖的变化.

研究的目的:

开发一种方法来减轻多中心数据集中的中心依赖变化.
提高机器学习模型的概括性和可解释性,用于分类神经退行性疾病,特别是帕金森病阶段.

主要方法:

建议使用通用矩阵学习向量量化 (GMLVQ) 的两步方法.
步骤1:训练GMLVQ在健康控制数据上,以确定区分数据收集中心的"相关性空间".
步骤2:从相关性空间构建一个校正矩阵,为诊断任务改进第二个GMLVQ系统.

主要成果:

拟议的方法成功地减少了机器学习系统的偏差,通过在训练过程中消除中心特定信息.
这种方法产生了更具信息性的相关性概况,可以由医学专家解释.
在现实世界多中心数据集和模拟数据上验证了有效性.

结论:

开发的方法有效地解决了多中心数据的异常变化,以提高机器学习模型的性能.
这种技术提高了神经退行性疾病分类的特异性和可解释性.
该方法可适应其他领域,需要识别相关空间来构建校正矩阵.