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

Ultrasound II: Endoscopic Ultrasound and FibroScan01:25

Ultrasound II: Endoscopic Ultrasound and FibroScan

131
Endoscopic Ultrasound (EUS) and FibroScan are valuable diagnostic tools in gastroenterology and hepatology, each with specific applications and techniques.
Endoscopic Ultrasound (EUS):
131

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

Therapeutic endoscopic ultrasound with a novel adaptable endoscopic ultrasound probe and vision system.

VideoGIE : an official video journal of the American Society for Gastrointestinal Endoscopy·2026
Same author

Normative Values for Prosaccade and Antisaccade Eye Movements in Adolescents Using a New Saccadometry Test.

Journal of the American Academy of Audiology·2026
Same author

Guidewire use in electrocautery-enhanced lumen-apposing metal stent procedures: Results of an online survey from an international working group.

Endoscopy international open·2026
Same author

Another step further into the understanding of pacemaker recovery after transcatheter aortic valve replacement.

International journal of cardiology·2026
Same author

Comparative efficacy and safety of endoscopic treatments for gastric varices: a systematic review and network meta-analysis.

Endoscopy·2026
Same author

EUS-guided gastroenterostomy for benign gastric outlet obstruction: Clinical and technical outcomes from a multicenter cohort study.

Endoscopy international open·2026

相关实验视频

Updated: Jul 13, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.8K

开发卷积神经网络模型,在实时辐射阵列和线性阵列EUS (带视频) 中识别正常解剖结构.

Carlos Robles-Medranda1, Jorge Baquerizo-Burgos1, Miguel Puga-Tejada1

  • 1Gastroenterology and Endoscopy Division, Instituto Ecuatoriano de Enfermedades Digestivas, Guayaquil, Ecuador.

Gastrointestinal endoscopy
|October 12, 2023
PubMed
概括

卷积神经网络 (CNN) 模型被开发用于在内超声波 (EUS) 程序中识别正常解剖. 这些人工智能工具显示出高精度,可能有助于EUS培训.

更多相关视频

Author Spotlight: Integrating Ultrasound Imaging with Biochemical Markers for Thyroid Disease Diagnosis
05:41

Author Spotlight: Integrating Ultrasound Imaging with Biochemical Markers for Thyroid Disease Diagnosis

Published on: February 9, 2024

643
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.9K

相关实验视频

Last Updated: Jul 13, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.8K
Author Spotlight: Integrating Ultrasound Imaging with Biochemical Markers for Thyroid Disease Diagnosis
05:41

Author Spotlight: Integrating Ultrasound Imaging with Biochemical Markers for Thyroid Disease Diagnosis

Published on: February 9, 2024

643
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.9K

科学领域:

  • 医学成像医学成像
  • 医学中的人工智能.
  • 胃肠病学 胃肠病学

背景情况:

  • 内镜超声波 (EUS) 是一种复杂的技能,需要广泛的培训.
  • 有限的全球培训设施对EUS能力发展构成挑战.
  • 卷积神经网络 (CNN) 模型为医学成像中的自动对象检测提供了潜力.

研究的目的:

  • 开发和评估基于EUS的CNN模型,用于识别正常的解剖结构.
  • 在实时线性和辐射阵列EUS评估中评估CNN模型的性能.
  • 为加强EUS培训和技能获取提供一个工具.

主要方法:

  • 两种CNN模型 (CNNv1和CNNv2) 是使用记录的线性和辐射阵列EUS视频开发的.
  • 专家内声学家确定并标记了20个正常的解剖结构,用于模型训练和验证.
  • 通过使用平均平均精度 (mAP) 和总损失指标,CNN模型的性能与专家内声学家进行了比较.

主要成果:

  • CNNv2模型表现出更好的性能,线性数组实现了88.7%的mAP (0.06损失),辐射数组实现了83.5%的mAP (0.07损失).
  • 在临床验证过程中,CNNv2模型准确地检测到所有研究的正常解剖结构,在临床验证过程中达成超过98%的一致性.
  • 最初的CNNv1模型显示性能较低 (75.65%和71.36% mAP).

结论:

  • 开发的CNN模型准确地识别了预先录制和实时EUS中的正常解剖结构.
  • 这些人工智能模型通过提供实时反,有望改善EUS培训.
  • 需要进一步的前性试验来评估对EUS实习生学习曲线的影响.