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

Size-Controlled Electronic Structure Tuning in Ru-CrO<sub><i>x</i></sub> Heteronanoclusters.

The journal of physical chemistry. A·2026
Same author

Opening Extra Transport Channels by Atomically Precise Doping in Gold Nanoclusters with Electronic Structure Modulation.

The journal of physical chemistry. A·2026
Same author

Atomic-scale strain engineering of atomically resolved Pt clusters transcending natural enzymes.

Nature communications·2024
Same author

Pursuing Extreme Descriptive Power and Generality in Chemical Bond Theories: A Method to Decipher "Interatomic Genomes" from Interatomic Electron Structures.

Journal of chemical theory and computation·2024
Same author

Functional group induced transformations in stacking and electron structure in Mo<sub>2</sub>CT<i><sub>x</sub></i>/NiS heterostructures.

Journal of physics. Condensed matter : an Institute of Physics journal·2024
Same author

Bioactive NIR-II gold clusters for three-dimensional imaging and acute inflammation inhibition.

Science advances·2023

相关实验视频

Updated: May 10, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.6K

一个轻量级的机器学习模型,用于高精度的胃肠道流体瘤识别.

Xin Sun1,2,3, Xiwen Mo3, Jing Shi3

  • 1Haihe Hospital, Tianjin University, Tianjin 300350, China.

Bioengineering (Basel, Switzerland)
|April 26, 2025
PubMed
概括

一个新的轻量级人工智能模型使用内镜超声波 (EUS) 图像准确地分类胃肠道 stromal 瘤 (GISTs) 和 leiomyomas. 这种人工智能模型显示出高准确度,并且在GIST诊断中表现优于人类专家.

关键词:
一个轻量级的模型.内镜超声波图像的内镜超声波图像.胃肠道 stromal 瘤的发生.高精度的高精度的高精度.

更多相关视频

Molecular and Immunologic Techniques in a Genetically Engineered Mouse Model of Gastrointestinal Stromal Tumor
07:21

Molecular and Immunologic Techniques in a Genetically Engineered Mouse Model of Gastrointestinal Stromal Tumor

Published on: May 2, 2022

2.0K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.1K

相关实验视频

Last Updated: May 10, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.6K
Molecular and Immunologic Techniques in a Genetically Engineered Mouse Model of Gastrointestinal Stromal Tumor
07:21

Molecular and Immunologic Techniques in a Genetically Engineered Mouse Model of Gastrointestinal Stromal Tumor

Published on: May 2, 2022

2.0K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.1K

科学领域:

  • 胃肠病学 胃肠病学
  • 医疗成像医学成像
  • 人工智能的人工智能

背景情况:

  • 胃肠道 stromal 瘤 (GIST) 由于其潜在的恶性瘤和在内镜超声波 (EUS) 图像中与其他瘤相似,因此带来了诊断挑战.
  • 准确地区分GISTs和leiomyomas对于适当的患者管理至关重要.

研究的目的:

  • 开发和评估一种轻量级的卷积神经网络 (CNN) 模型,用于仅使用EUS图像对GIST和肌瘤进行分类.
  • 评估轻量级CNN模型与人类专家评估的性能.

主要方法:

  • 使用了来自703名患者的13,277张增强灰度EUS图像的数据集,确保了GIST和瘤病例的平衡表现.
  • 一个轻量级的CNN架构与七个卷积单元和完全连接的层被设计和优化.
  • 该模型经过5倍交叉验证的训练和评估.

主要成果:

  • 优化的轻量级CNN模型实现了96.2%的平均验证准确度.
  • 该模型展示了高性能指标:97.7%的灵敏度,94.7%的特异性,94.6%的积极预测值和97.7%的负预测值.
  • 人工智能模型显著超过了内镜医生的诊断准确度.

结论:

  • 轻量级的CNN模型,其更简单的设计,可以有效地捕捉基本的图像特征,并减少噪音,以实现准确的GIST分类.
  • 拟议的轻量级模型为更复杂的深度学习模型提供了强大的和一致的替代方案,与奥卡姆剃刀原理保持一致.
  • 这种以人工智能为驱动的方法显示出在EUS成像中提高GIST和肌瘤诊断准确性的巨大潜力.