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

Brain Imaging

Brain Imaging

Brain imaging technologies provide critical insights into both the structure and function of the human brain, enabling medical professionals and researchers to diagnose, study, and treat neurological disorders or psychiatric disorders more effectively.
These technologies include computerized axial tomography (CAT or CT scans), positron-emission tomography (PET scans), magnetic resonance imaging (MRI), functional magnetic resonance imaging (fMRI), and Transcranial Magnetic...

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

Peptidomics profiling identifies endogenous peptides associated with meningeal afferent activation in a chronic migraine mouse model.

The journal of headache and pain·2026

Same author

Surface attachment of fucoidan through electrostatic interaction alleviates chitosan/chitosan oligosaccharide-induced reduction in protein digestion.

Journal of the science of food and agriculture·2026

Same author

FoldDoF: Utilizing the Primary Degrees of Freedom of Protein Backbone for Geometric Modeling and Generation.

Journal of chemical information and modeling·2026

Same author

Thulium fiber laser versus holmium:YAG laser for ureteroscopic lithotripsy: a single-center retrospective cohort study.

Frontiers in surgery·2026

Same author

Bioactive Magnesium Silicate Activating Myocardial Energy Metabolism For Infarcted Myocardium Repair.

Exploration (Beijing, China)·2026

Same author

In Situ Synthesis of Rapid Hemostatic Zeolite/Gauze Composites on Pre-Seeded Gauze.

ACS applied bio materials·2026

Search research articles

相关实验视频

Updated: Jun 11, 2025

Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment

Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment

Published on: July 7, 2023

基于MRI的深度学习,用于区分双相情感障碍和严重抑郁症.

Ruipeng Li¹, Yueqi Huang², Yanbin Wang¹

¹Third People's Hospital of Hangzhou, Hangzhou, 310010, China.

Psychiatry research. Neuroimaging

|October 2, 2024

概括

这项研究介绍了SE-ResNet,一种新的AI框架,使用结构性MRI扫描来区分双相情感障碍 (BD),主要抑郁障碍 (MDD) 和健康个体. 该模型对客观的精神疾病检测有希望.

关键词:

深度神经网络是一种深度神经网络.分析MRI模式的分析.情绪障碍分化情绪障碍分化神经成像诊断的诊断方法模式识别模式识别模式识别

更多相关视频

MRI-guided dmPFC-rTMS as a Treatment for Treatment-resistant Major Depressive Disorder

MRI-guided dmPFC-rTMS as a Treatment for Treatment-resistant Major Depressive Disorder

Published on: August 11, 2015

Individualized rTMS Treatment for Depression using an fMRI-Based Targeting Method

Individualized rTMS Treatment for Depression using an fMRI-Based Targeting Method

Published on: August 2, 2021

相关实验视频

Last Updated: Jun 11, 2025

Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment

Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment

Published on: July 7, 2023

MRI-guided dmPFC-rTMS as a Treatment for Treatment-resistant Major Depressive Disorder

MRI-guided dmPFC-rTMS as a Treatment for Treatment-resistant Major Depressive Disorder

Published on: August 11, 2015

Individualized rTMS Treatment for Depression using an fMRI-Based Targeting Method

Individualized rTMS Treatment for Depression using an fMRI-Based Targeting Method

Published on: August 2, 2021

科学领域:

神经成像是一种神经成像.
人工智能的人工智能
精神疾病精神疾病

背景情况:

情绪障碍,如双相情绪障碍 (BD) 和严重抑郁障碍 (MDD),具有主观的诊断标准,导致潜在的误诊.
了解这些疾病的神经生物学基础仍然是一个挑战.
结构磁共振成像 (MRI) 提供客观数据,但需要先进的分析工具.

研究的目的:

开发和评估SE-ResNet,这是一个深度学习框架,用于使用结构性MRI数据来区分BD,MDD和健康对照 (HC).
通过在剩余网络 (ResNet) 架构中融合通道和空间注意力机制来增强特征歧视.

主要方法:

使用了剩余网络 (ResNet) 架构,结合了增强的挤压刺激 (SE) 层和空间注意力分支.
实施软聚合用于下采样,以保持特征丰富性,与传统的最大聚合不同.
在303个主题的专有数据集上训练并验证了SE-ResNet框架.

主要成果:

该SE-ResNet模型实现了高性能指标:85.8%的准确性,85.7%的回忆,85.9%的精度,85.8%的F1分数.
证明了框架在区分BD,MDD和HC群体方面的能力.
综合道和空间注意力机制有效地增强了特征歧视.

结论:

在SE-ResNet框架显示显著的潜力作为一个客观的工具,用于检测使用结构性MRI的精神疾病.
这种人工智能驱动的方法可以帮助提高诊断准确度和了解情绪障碍的神经成像相关性.
对更大,更多样化的数据集进行进一步验证是有必要的,以确认临床效用.