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

Absorption of Radiation01:05

Absorption of Radiation

1.2K
The rate of heat transfer by emitted radiation is described by the Stefan-Boltzmann law of radiation:
1.2K

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

Quality assurance phantoms for deep hyperthermia devices: design principles informed by computational modeling.

Physics in medicine and biology·2026
Same author

Roadmap towards personalized approaches and safety considerations in non-ionizing radiation: from dosimetry to therapeutic and diagnostic applications.

Physics in medicine and biology·2025
Same author

3D electroacoustic tomography image enhancement using deep learning with the SAM-Med3D encoder.

Physics in medicine and biology·2025
Same author

Evaluation of a Balloon Implant for Simultaneous Magnetic Nanoparticle Hyperthermia and High-Dose-Rate Brachytherapy of Brain Tumor Resection Cavities.

Cancers·2023
Same author

Bioremediation of PAEs-contaminated saline soil: The application of a marine bacterial strain isolated from mangrove sediment.

Marine pollution bulletin·2023
Same author

Using machine learning approach to predict depression and anxiety among patients with epilepsy in China: A cross-sectional study.

Journal of affective disorders·2023

相关实验视频

Updated: Jan 18, 2026

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

8.6K

自动特定吸收率 (SAR) 预测用于使用深度学习方法进行高温症治疗规划.

Yankun Lang1, Dario B Rodrigues1, Lei Ren1

  • 1Department of Radiation Oncology Physics, University of Maryland, Baltimore, MD, USA.

International journal of hyperthermia : the official journal of European Society for Hyperthermic Oncology, North American Hyperthermia Group
|September 9, 2025
PubMed
概括
此摘要是机器生成的。

一个新的深度学习模型准确地预测了用于高热症治疗计划 (HTP) 的特定吸收率 (SAR) 分布. 这将计算速度从几分钟加快到几秒钟,使实时的脑癌治疗调整成为可能.

关键词:
超热疗法是一种超热疗法.大脑癌症 脑癌 脑癌特定的吸收率是什么有监督的深度学习.治疗计划 治疗计划

更多相关视频

Author Spotlight: Computing the Effects of a Local Radiofrequency Hyperthermia Intervention on Tumor Biomechanics
10:23

Author Spotlight: Computing the Effects of a Local Radiofrequency Hyperthermia Intervention on Tumor Biomechanics

Published on: December 1, 2023

972
Magnetic Resonance-Guided High Intensity Focused Ultrasound Generated Hyperthermia: A Feasible Treatment Method in a Murine Rhabdomyosarcoma Model
13:41

Magnetic Resonance-Guided High Intensity Focused Ultrasound Generated Hyperthermia: A Feasible Treatment Method in a Murine Rhabdomyosarcoma Model

Published on: January 13, 2023

2.8K

相关实验视频

Last Updated: Jan 18, 2026

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

8.6K
Author Spotlight: Computing the Effects of a Local Radiofrequency Hyperthermia Intervention on Tumor Biomechanics
10:23

Author Spotlight: Computing the Effects of a Local Radiofrequency Hyperthermia Intervention on Tumor Biomechanics

Published on: December 1, 2023

972
Magnetic Resonance-Guided High Intensity Focused Ultrasound Generated Hyperthermia: A Feasible Treatment Method in a Murine Rhabdomyosarcoma Model
13:41

Magnetic Resonance-Guided High Intensity Focused Ultrasound Generated Hyperthermia: A Feasible Treatment Method in a Murine Rhabdomyosarcoma Model

Published on: January 13, 2023

2.8K

科学领域:

  • 生物医学工程 生物医学工程
  • 医学物理 医学物理
  • 人工智能的人工智能

背景情况:

  • 准确的特定吸收率 (SAR) 预测对于有效的高温症治疗计划 (HTP) 至关重要.
  • 目前用于SAR分布的模拟方法是计算密集的,限制了实时处理调整.
  • 深度学习为快速准确的SAR预测提供了一个潜在的解决方案.

研究的目的:

  • 开发一种深度学习方法,以快速准确地预测人脑中的SAR分布.
  • 支持大脑癌症患者实时超热症治疗计划 (HTP).

主要方法:

  • 一个编码器-解码器神经网络与交叉注意力阻断被提出.
  • 该模型使用大脑电气特性,瘤坐标和天线相位设置预测SAR地图.
  • 201个有限元建模模拟的数据集被用于培训和评估.

主要成果:

  • 该模型在整个大脑中实现了3.3W/kg的平均RMSE和1.6W/kg的MAE.
  • 在目标地区,RMSE和MAE分别为4.8W/kg和2.5W/kg.
  • 计算时间从10分钟缩短到4秒,平均SSIM为0.90.

结论:

  • 深度学习方法使HTP的准确和高效的SAR预测成为可能.
  • 这种方法有可能支持实时HTP,优化瘤温度并改善临床结果.
  • 这项工作引入了一种新的深度学习方法,可以显著加速适应性高温疗法策略的SAR计算.