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

相关实验视频

Updated: Sep 11, 2025

Simulator Training for Endovascular Neurosurgery
08:08

Simulator Training for Endovascular Neurosurgery

Published on: May 6, 2020

3.8K

在手术模拟器中绘制图形神经网络以实现现实的出血预测.

Yasar C Kakdas1, Suvranu De2, Doga Demirel3

  • 1Department of Computer Science, Florida Polytechnic University, Lakeland, FL, USA.

Journal of imaging informatics in medicine
|August 12, 2025
PubMed
概括

这项研究使用图形神经网络来预测医疗扫描中的内部出血风险,增强创伤紧急情况的外科模拟器现实性. 这种新的方法准确地识别出血的可能性,有助于快速诊断和拯救生命的干预.

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

Analysis and objective assessment of transoral robotic surgery.

International journal of computer assisted radiology and surgery·2026
Same author

Real-Time Haptic-Based Soft Body Suturing in Virtual Open Surgery Simulations.

Computers & graphics·2025
Same author

Time and Expertise in Open Structural Rhinoplasty: A Task-Based Analysis Using Hierarchical Task Analysis and Machine Learning.

The Journal of craniofacial surgery·2025
Same author

Validity of a virtual reality-based straight coloanal anastomosis simulator.

International journal of computer assisted radiology and surgery·2024
Same author

Endoscopic sleeve gastroplasty: stomach location and task classification for evaluation using artificial intelligence.

International journal of computer assisted radiology and surgery·2024
Same author

GPU based Position Based Dynamics for Surgical Simulators.

HCI in Games : 5th International Conference, HCI-Games 2023, held as part of the 25th HCI International Conference, HCII 2023, Copenhagen, Denmark, July 23-28, 2023, proceedings. Part I. HCI-Games (Conference) (5th : 2023 : Copenhagen, ...·2023

科学领域:

  • 医学成像分析 医学成像分析
  • 医疗保健中的人工智能
  • 计算生理学计算生理学

背景情况:

  • 检测内部出血在紧急医疗中至关重要,特别是在创伤病例中.
  • 现有的外科模拟器缺乏现实的出血建模,限制了训练的有效性.
  • 准确预测出血风险可以显著改善患者的结果.

研究的目的:

  • 利用图形神经网络 (GNN) 开发一种用于预测内部出血风险的新方法.
  • 通过整合出血风险预测模型来增强外科模拟器的现实性.
  • 改善应急响应和外科手术培训,以应对创伤情景.

主要方法:

  • 医学图像 (CT,MRI) 被细分并转换为血管图表.
  • 基于物理学的启发式 (哈根-波泽尔方程) 用于计算血管节点出血概率.
  • 训练了一个图表注意网络,从图表数据中预测出血风险,通过1708个血管图表进行验证.

主要成果:

  • 在预测出血风险方面,GNN模型实现了0.86 (高达0.9188) 的平均R平方.
  • 观察到低平均训练 (0.0069) 和验证 (0.0074) 损失.
  • 该模型表现出强大的性能,特别是在连接良好的血管图表上,尽管数据稀疏.
关键词:
预测出血 预测出血图表神经网络的神经网络医学成像医学成像手术模拟器手术模拟器创伤训练培训 创伤训练培训虚拟现实虚拟现实就是虚拟现实.

更多相关视频

A Training and Testing System for Performing Vascular Reconstruction In Vitro
09:52

A Training and Testing System for Performing Vascular Reconstruction In Vitro

Published on: October 26, 2019

8.0K
A New Hybrid Quantitative Evaluation Model for Axillary Junctional Hemorrhage in Swine
08:27

A New Hybrid Quantitative Evaluation Model for Axillary Junctional Hemorrhage in Swine

Published on: December 6, 2024

392

相关实验视频

Last Updated: Sep 11, 2025

Simulator Training for Endovascular Neurosurgery
08:08

Simulator Training for Endovascular Neurosurgery

Published on: May 6, 2020

3.8K
A Training and Testing System for Performing Vascular Reconstruction In Vitro
09:52

A Training and Testing System for Performing Vascular Reconstruction In Vitro

Published on: October 26, 2019

8.0K
A New Hybrid Quantitative Evaluation Model for Axillary Junctional Hemorrhage in Swine
08:27

A New Hybrid Quantitative Evaluation Model for Axillary Junctional Hemorrhage in Swine

Published on: December 6, 2024

392

结论:

  • 图形神经网络提供了一个强大的工具,用于预测医疗成像中的内部出血风险.
  • 开发的模型可以集成到虚拟现实外科模拟器中,以实现现实的创伤训练.
  • 这种方法有可能提高外科准备,并改善紧急情况下的患者护理.