Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
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 JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

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

Correction: Multimodal contrastive learning on rs-fMRI to quantify whole-brain network recovery after hypothalamic hamartoma surgery.

Biomedical engineering online·2025
Same author

Precision connectivity in osteoarthritis pain with permutation and network analysis: a key step toward clinical application.

BMC medical imaging·2025
Same author

Reliability of artificial intelligence algorithms in automated age estimation using orthopantomograms: A scoping review.

Digital health·2025
Same author

A multimodal deep learning framework for functional brain network classification in rs-fMRI.

Cognitive neurodynamics·2025
Same author

Multimodal contrastive learning on rs-fMRI to quantify whole-brain network recovery after hypothalamic hamartoma surgery.

Biomedical engineering online·2025
Same author

Precision Connectivity in Arthritis Pain with Permutation and Network Analysis: A Key Step Toward Clinical Application.

Research square·2025

相关实验视频

Updated: Jan 17, 2026

A Multimodal Imaging- and Stimulation-based Method of Evaluating Connectivity-related Brain Excitability in Patients with Epilepsy
08:23

A Multimodal Imaging- and Stimulation-based Method of Evaluating Connectivity-related Brain Excitability in Patients with Epilepsy

Published on: November 13, 2016

11.7K

用于rs-fMRI症分类和生物标志物发现的可解释变压器模型.

Andrew Jeyabose, Varina L Boerwinkle, Belfin Robinson

    medRxiv : the preprint server for health sciences
    |September 15, 2025
    PubMed
    概括

    一种新的规范化变压器模型有效地使用静止状态fMRI (rs-fMRI) 数据对进行分类,识别潜在的网络生物标志物用于诊断. 需要进一步验证临床应用.

    科学领域:

    • 神经成像是一种神经成像.
    • 人工智能的人工智能
    • 医学诊断 医学诊断 医学诊断

    背景情况:

    • 对于的诊断,静止状态fMRI (rs-fMRI) 的自动解释是具有挑战性的.
    • 使用 rs-fMRI 开发强大的分类的方法对于改善患者的治疗结果至关重要.

    研究的目的:

    • 开发和评估一个规范化变压器模型用于使用rs-fMRI的症分类.
    • 为了确定可解释的,网络层面的候选生物标志物.

    主要方法:

    • 使用了用fMRIPrep.预处理的rs-fMRI数据的Schaefer-200小包时间序列.
    • 开发了一种规范化变压器模型,包括注意力机制,学习定位编码和fMRI特定的规范化.
    • 通过对65名参与者 (30名,35名对照) 的队列和独立的外部数据集进行4倍交叉验证,训练并验证了该模型.

    主要成果:

    • 调节变压器在内折分类中实现了高性能 (例如,精度0.77,AUC0.76).
    • 外部验证显示有希望但性能较低 (精度为0.60,AUC为0.64).
    • 以归因为指导的分析确定了边缘,体运动,默认模式和突出网络中的候选生物标志物.

    结论:

    更多相关视频

    Brain Source Imaging in Preclinical Rat Models of Focal Epilepsy using High-Resolution EEG Recordings
    08:20

    Brain Source Imaging in Preclinical Rat Models of Focal Epilepsy using High-Resolution EEG Recordings

    Published on: June 6, 2015

    15.8K
    Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy
    12:09

    Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy

    Published on: August 5, 2014

    18.5K

    相关实验视频

    Last Updated: Jan 17, 2026

    A Multimodal Imaging- and Stimulation-based Method of Evaluating Connectivity-related Brain Excitability in Patients with Epilepsy
    08:23

    A Multimodal Imaging- and Stimulation-based Method of Evaluating Connectivity-related Brain Excitability in Patients with Epilepsy

    Published on: November 13, 2016

    11.7K
    Brain Source Imaging in Preclinical Rat Models of Focal Epilepsy using High-Resolution EEG Recordings
    08:20

    Brain Source Imaging in Preclinical Rat Models of Focal Epilepsy using High-Resolution EEG Recordings

    Published on: June 6, 2015

    15.8K
    Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy
    12:09

    Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy

    Published on: August 5, 2014

    18.5K
    • 一个规范化的变压器模型显示了从rs-fMRI分类的潜力,并产生可解释的生物标志物.
    • 初步结果表明该模型的有效性,但临床转化需要更大的多站点验证和稳定性测试.