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

Factors determining hydrocephalus after decompressive craniectomy: the role of interhemispheric hygroma.

Frontiers in neurology·2026
Same author

Study protocol for investigating real-world implementation of a combined glial fibrillary acidic protein (GFAP) and ubiquitin carboxy-terminal hydrolase L1 (UCH-L1) blood test in the management of adult mild traumatic brain injury in a single-centre European emergency department: the IMPACTS-BRAINI study.

BMJ open·2026
Same author

PituPhase65: An endoscopic pituitary surgery dataset for surgical phase recognition.

Scientific data·2026
Same author

High-to-Low Spectral Mapping for Cross-System Feature Adaptation in Medical Hyperspectral Imaging.

Bioengineering (Basel, Switzerland)·2026
Same author

Reappraisal of Computerized Tomography Scoring Systems for Outcome Prediction in Traumatic Brain Injury: A Comparative Analysis of Young and Older Adults.

Journal of neurotrauma·2026
Same author

Persistent sleep disturbances after mild traumatic brain injury: A prospective multimodal assessment with actigraphy and hormonal biomarkers.

Brain & spine·2026

相关实验视频

Updated: Jan 12, 2026

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

3.3K

使用自我监督的深度学习改进手术阶段识别.

Alba Centeno López1,2, Ángela González-Cebrián3, Igor Paredes4,5

  • 1Computer Science and Engineering Department, Universidad Carlos III de Madrid, Madrid, Spain. alcenten@pa.uc3m.es.

Scientific reports
|November 7, 2025
PubMed
概括

自主监督学习 (SSL) 在垂体外科手术中增强了手术阶段识别 (SPR),比传统方法更高的准确性. 此外,SSL还可以在较少标记数据的情况下保持性能,这证明了它对外科决策支持系统的稳定性.

关键词:
相反的学习学习.内镜下垂体手术是指内镜下垂体手术自主监督学习学习手术阶段识别手术阶段识别

更多相关视频

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility
07:46

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility

Published on: August 9, 2024

1.2K
Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging
11:38

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

Published on: October 4, 2024

1.0K

相关实验视频

Last Updated: Jan 12, 2026

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

3.3K
Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility
07:46

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility

Published on: August 9, 2024

1.2K
Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging
11:38

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

Published on: October 4, 2024

1.0K

科学领域:

  • 医疗人工智能 医疗人工智能
  • 计算机辅助手术 计算机辅助手术
  • 外科手术工作流程分析

背景情况:

  • 智能系统在手术中提供实时决策支持.
  • 手术阶段识别 (SPR) 改善了手术工作流程,但受到数据可用性的限制.
  • 自主监督学习 (SSL) 利用未标记的数据来学习表示,解决数据限制.

研究的目的:

  • 探索SSL对SPR在内镜垂体外科手术中的应用.
  • 为了比较SPR的SimCLR和BYOL SSL框架的性能.
  • 评估注意力加权聚合运营商对SPR绩效的影响.

主要方法:

  • 将SimCLR和BYOL SSL框架应用于内镜下垂体手术视频数据.
  • 集成了一个注意力加权的聚合运营商来增强空间特征提取.
  • 使用F1分数对下游SPR任务的评估性能,与完全监督学习和减少数据场景进行比较.

主要成果:

  • 使用注意力的SimCLR获得了66%的F1分,超过了完全监督的学习 (55%).
  • 尽管标记数据减少了50%,SSL仍然保持了高性能 (64% F1评分).
  • 在所有评估中,SimCLR表现出比BYOL更强大的稳定性.

结论:

  • SSL是一种强大的方法,可以在内镜下垂体手术中增强SPR.
  • 整合注意力机制进一步提高了SPR的SSL性能.
  • 通过SSL,在显著减少标记数据要求的情况下,可以实现可比的SPR性能,从而促进了先进的外科决定支持系统.