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

Diagnostic approaches and clinical challenges of imaging in peripheral nerve tumors: data from the multicenter Peripheral Nerve Tumor Registry.

Journal of neurosurgery·2026
Same author

Relationship between Vascular Tortuosity Rate and Atherosclerotic Risk Factors in Patients with Carotid Artery Stenosis.

Magnetic resonance in medical sciences : MRMS : an official journal of Japan Society of Magnetic Resonance in Medicine·2026
Same author

Generating Synthetic MR Perfusion Maps From DWI and FLAIR in Acute Ischemic Stroke: Development and External Validation of a Deep Learning Model.

Stroke·2026
Same author

Initial appearance and temporal distribution of pedicle screw loosening after single-level lumbar interbody fusion.

Scientific reports·2026
Same author

Comparative immunogenicity and cross-protection of wild-type and reverse genetics H5N8 (clade 2.3.4.4b) oil-adjuvanted vaccines against circulating H5N1 avian influenza viruses from clades 2.3.4.4b and 2.2.1.2.

Avian pathology : journal of the W.V.P.A·2026
Same author

Characterizing Pain in Peripheral Nerve Tumors: Interim Results from a Prospective Bicenter Cohort.

Cancers·2026

相关实验视频

Updated: May 7, 2025

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

2.1K

基于深度学习的多类细分在动脉瘤下arachnoid 出血中的多类细分.

Julia Kiewitz1,2, Orhun Utku Aydin1, Adam Hilbert1

  • 1CLAIM - Charité Lab for AI in Medicine, Charité Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, Berlin, Germany.

Frontiers in neurology
|December 30, 2024
PubMed
概括

深度学习模型现在可以在CT扫描上自动细分脑出血,匹配人类的准确性. 这项技术有助于预测患有下关节出血的患者的结果.

关键词:
深度学习是一种深度学习.评价者之间的可靠性.多类细分化的多类细分化.结果预测结果预测.脑下关节下部出血

更多相关视频

A Volumetric Method for Quantification of Cerebral Vasospasm in a Murine Model of Subarachnoid Hemorrhage
08:12

A Volumetric Method for Quantification of Cerebral Vasospasm in a Murine Model of Subarachnoid Hemorrhage

Published on: July 28, 2018

8.0K
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

2.6K

相关实验视频

Last Updated: May 7, 2025

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

2.1K
A Volumetric Method for Quantification of Cerebral Vasospasm in a Murine Model of Subarachnoid Hemorrhage
08:12

A Volumetric Method for Quantification of Cerebral Vasospasm in a Murine Model of Subarachnoid Hemorrhage

Published on: July 28, 2018

8.0K
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

2.6K

科学领域:

  • 神经外科 神经外科
  • 放射学 放射学是一门学科.
  • 人工智能的人工智能

背景情况:

  • 传统的放射性评分下关节出血 (SAH) 患有变化和不完整的数据利用.
  • 图像细分提供了精确的划分和潜在的SAH范围的自动评估.
  • 开发自动化工具对于提高诊断准确性和在SAH中预测患者结果至关重要.

研究的目的:

  • 开发一种深度学习模型,用于自动化多类细分与动脉瘤下大脑关节出血相关的病理.
  • 为了评估模型的性能与人类评分器和外部验证数据集.
  • 探索自动化细分的潜力,以创建用于SAH结果预测的成像生物标志物.

主要方法:

  • 使用了73个非对比性CT扫描,来自动脉瘤下关节出血患者.
  • 手动分为六个类别:下关节,心室内,脑内和体内出血,动脉瘤和心室.
  • 采用nnU-Net深度学习框架 (2D和3D配置),并进行了评分器间可靠性分析和外部验证.

主要成果:

  • 在 nnU-Net 模型中,在关键的出血和心室类别中,nnU-Net 模型实现了与高级评级者可比的细分性能.
  • 在内部测试组中,出血细分的子系数中位数为0.664 (3D) 和0.673 (2D).
  • 在初级脑内出血患者的外部验证中,出血细分的Dice系数中位数为0.831.

结论:

  • 深度学习促进了SAH相关病理的自动化多类细分,其性能接近人类评分器.
  • 来自入院CT扫描的SAH病理的自动体积测量可以导致新的成像生物标志物.
  • 这种方法有望改善脑下下垂体出血患者的预测结果.