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

Neural Circuits01:25

Neural Circuits

3.0K
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
3.0K
Visual Agnosia01:12

Visual Agnosia

2.0K
Visual agnosia is a condition characterized by the inability to recognize visually presented objects despite having normal vision. For instance, a person with visual agnosia can describe the shape and color of an object but cannot identify or name it. This impairment does not affect their visual field, acuity, color vision, brightness discrimination, language, or memory. An example of this condition in a social setting is someone at a dinner party asking for "that silver thing with a round...
2.0K

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

On-demand growth of semiconductor heterostructures guided by physics-informed machine learning.

Science advances·2026
Same author

Kappa-opioid receptor activation promotes depression-like behaviors by suppressing Pax6-dependent adult hippocampal neurogenesis.

Translational psychiatry·2026
Same author

Comment on: Exploring the mechanism of ropivacaine in alleviating neuropathic pain via the mTOR-PKM2/STAT3-H4K12 lactylation axis.

International immunopharmacology·2026
Same author

Classification of 24-h movement behaviour patterns among university students and their relationship with physical fitness: a latent profile analysis.

BMC public health·2026
Same author

SAMS-Net: A Smoothness-Anchored Monotone Neural Differential Equation Network for Failure-Only-Supervised Structural Health Indicator Construction.

Sensors (Basel, Switzerland)·2026
Same author

Ligand-mediated suppression of Ostwald ripening enables low-temperature sol-gel ZnO for efficient inverted flexible organic photovoltaics.

Nature communications·2026

相关实验视频

Updated: May 2, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

990

通过突出性一致的对比学习对内微镜脑数据的可解释分类.

Chi Xu1, Alfie Roddan1, Irini Kakaletri2

  • 1The Hamlyn Centre for Robotic Surgery, Imperial College London, London, SW7 2AZ, United Kingdom.

Medical image analysis
|December 28, 2025
PubMed
概括

这项研究引入了一种新的AI框架,用于使用基于探针的聚焦激光内分显微镜 (pCLE) 进行可解释的大脑组织分类. 该方法通过为AI决策提供明确的解释,提高了对外科指导的准确性和信任度.

关键词:
大脑瘤 脑瘤是什么分类 分类 分类 分类.内分显微镜是指内分显微镜可以解释性 解释性监督的对比学习学习

更多相关视频

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

2.4K

相关实验视频

Last Updated: May 2, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

990
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

2.4K

科学领域:

  • 神经外科 神经外科
  • 医疗成像医学成像
  • 人工智能的人工智能

背景情况:

  • 使用基于探针的聚焦激光内微镜 (pCLE) 精确的脑组织表征对于手术指导和瘤切除至关重要.
  • 目前对PCLE数据的深度学习模型缺乏解释性,阻碍了外科医生的信任.
  • 现有的分类方法经常使用交叉损失,这可能无法优化有效区分组织类别.

研究的目的:

  • 开发一种新的,可解释的图像分类框架,用于使用pCLE数据进行脑组织表征.
  • 提高神经外科人工智能模型的准确性,稳定性和可解释性.
  • 为外科医生提供可靠的AI工具,为组织分类提供清晰的洞察力.

主要方法:

  • 提出一个标签对比学习 (LCL) 损失来增强类别内部的相似性和类别间的对比性,生成具有代表性的数据嵌入.
  • 引入了一个 Saliency 一致性 (SC) 模块,具有 Top-K 最大和最小聚合 (TK-MMP) 层,用于临床相关的 Saliency 地图生成.
  • 用于全球组织类别嵌入的指数移动平均值 (EMA) 和全球嵌入推理 (GEI) 层,通过等号相似性进行稳健的分类.

主要成果:

  • 与最先进的模型相比,拟议的框架在ex-vivo和in-vivopCLE大脑数据上实现了优越的分类性能.
  • 在脑组织分类的准确性,稳定性和可解释性方面取得了显著的改进.
  • 生成临床相关的突出性图,增强对模型预测的理解.

结论:

  • 新的LCL和SC框架为使用pCLE进行脑组织表征提供了高度准确,强大和可解释的解决方案.
  • 这种方法有可能显著增强外科医生对神经外科手术程序的信任和决策.
  • 开发的方法为医疗成像应用中的可解释AI提供了一个新的标准.