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

Development and Clinical Validation of a Protocol-Agnostic Machine Learning Platform for Automated Treatment Planning in External Beam Radiation Therapy.

Advances in radiation oncology·2026
Same author

Temporal changes in native and late gadolinium enhanced ultrashort echo time magnetic resonance imaging during gynecologic cancer radiation therapy.

Physics and imaging in radiation oncology·2025
Same author

American Brachytherapy Society Education Committee Technical Report: A Resident's Guide to Evaluation of Prostate Low-Dose-Rate Brachytherapy Treatment Plans.

Practical radiation oncology·2025
Same author

CT-ultrasound deformable registration for PET-determined prostate brachytherapy.

Proceedings of SPIE--the International Society for Optical Engineering·2025
Same author

Cascaded neural network segmentation pipeline for automated delineation of prostate and organs at risk in male pelvic CT.

Proceedings of SPIE--the International Society for Optical Engineering·2025
Same author

Genomic Predictors of Response to Metastasis-directed Therapy With or Without Androgen Deprivation Therapy.

European urology oncology·2025

相关实验视频

Updated: Jun 27, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.8K

使用深度强化学习优化局部前列腺癌的临床VMAT机器参数优化.

William T Hrinivich1, Mahasweta Bhattacharya1, Lina Mekki1

  • 1Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland, USA.

Medical physics
|April 26, 2024
PubMed
概括

强化学习 (RL) 快速生成高质量的体积调制弧线治疗 (VMAT) 计划用于前列腺癌. 这种自动化方法与治疗计划系统相结合,有望实现高效有效的放射治疗.

关键词:
这就是为什么VMAT VMAT.人工智能的人工智能是人工智能.自动化自动化自动化自动化深度学习是一种深度学习.前列腺癌是前列腺癌.强化学习是一种强化学习.

更多相关视频

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

8.2K
A Cognitive Fusion-guided Prostate Biopsy Using Multiparametric Magnetic Resonance Imaging and Transrectal Ultrasound
06:08

A Cognitive Fusion-guided Prostate Biopsy Using Multiparametric Magnetic Resonance Imaging and Transrectal Ultrasound

Published on: March 21, 2025

170

相关实验视频

Last Updated: Jun 27, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.8K
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

8.2K
A Cognitive Fusion-guided Prostate Biopsy Using Multiparametric Magnetic Resonance Imaging and Transrectal Ultrasound
06:08

A Cognitive Fusion-guided Prostate Biopsy Using Multiparametric Magnetic Resonance Imaging and Transrectal Ultrasound

Published on: March 21, 2025

170

科学领域:

  • 医学物理 医学物理
  • 辐射瘤学 辐射瘤学
  • 医疗保健中的机器学习

背景情况:

  • 卷度调节弧度疗法 (VMAT) 机器参数优化 (MPO) 是计算密集且对剂量目标敏感的.
  • 强化学习 (RL) 通过试错的机器学习提供了一个潜在的解决方案.

研究的目的:

  • 在临床线性加速器 (linac) 上开发和评估VMAT MPO的RL方法.
  • 快速自动生成局部前列腺癌的可交付VMAT计划.
  • 为了比较RL生成计划的剂量与现有的临床计划.

主要方法:

  • 扩展了以前的RL方法,使用VMAT MPO的3D光束模型的策略网络.
  • 训练RL以最小化基于剂量的成本函数,使用136名前列腺癌患者的数据.
  • 将受过训练的RL VMAT应用于15名患者的独立队列,并将剂量测量与临床计划进行比较.
  • 集成RL与临床治疗计划系统 (TPS) 进行自动化计划改进.

主要成果:

  • 在勘探期间,RL培训产生了40,000个计划.
  • 可交付的VMAT计划的平均执行时间为3.3 ± 0.5秒,TPS改进需要额外的77.4 ± 5.8秒.
  • 与临床计划 (21.0 ± 6.0 Gy) 相比,RL + TPS计划实现了类似的目标覆盖率和总体最大剂量,平均直肠剂量明显较低 (17.4 ± 7.4 Gy).

结论:

  • 在临床 linac 模型上开发并应用了 VMAT MPO 的 RL 方法.
  • 当RL VMAT方法与临床TPS相结合时,可以快速生成局部前列腺癌的高质量计划.
  • 这种方法显示了通过自动试错来发现先进的临床控制策略的潜力.