Search research articles

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 Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

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

First Southeast Asian Experience of Terbium-161 PSMA Therapy for Metastatic Castration-Resistant Prostate Cancer (mCRPC): Quantitative Imaging and Dosimetric Approach.

Molecular imaging and radionuclide therapy·2026

Same author

Combined Input Deep Learning Pipeline for Embryo Selection for In Vitro Fertilization Using Light Microscopic Images and Additional Features.

Journal of imaging·2025

Same author

Comparative post-therapeutic dosimetry between 2D planar-based and hybrid-based methods for personalized Lu-177 treatment.

Annals of nuclear medicine·2024

Same author

Dual-time-point dynamic <sup>68</sup>Ga-PSMA-11 PET/CT for parametric imaging generation in prostate cancer.

Annals of nuclear medicine·2024

Same author

Comparison of absorbed doses to the tumoral and non-tumoral liver in HCC patients undergoing <sup>99m</sup>Tc-MAA and <sup>90</sup>Y-microspheres radioembolization.

Annals of nuclear medicine·2023

Same author

Patient dosimetry of <sup>177</sup>Lu-PSMA I&T in metastatic prostate cancer treatment: the experience in Thailand.

Annals of nuclear medicine·2021

Search research articles

相关实验视频

Updated: Jul 4, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

在胸部CT中使用基于U-Net模型的卷积神经网络进行自动化尺寸特定剂量估计框架.

Sakultala Ruenjit^1,2,3, Punnarai Siricharoen⁴, Kitiwat Khamwan^1,3,5

¹Medical Physics Program, Department of Radiology, Faculty of Medicine, Chulalongkorn University, Bangkok, Thailand.

Journal of applied clinical medical physics

|January 31, 2024

概括

本研究引入了一种自动卷积神经网络 (CNN) 方法,用于计算胸部CT扫描中的尺寸特定剂量估计 (SSDE). CNN准确地确定了校正有效直径 (Deffcorr),为手工计算提供了可靠的替代方案.

关键词:

在U-Net模型中,卷积神经网络是一种卷积神经网络.尺寸特定的剂量估计.胸部CTCT是指胸部的CT.

更多相关视频

Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

Published on: May 19, 2023

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

相关实验视频

Last Updated: Jul 4, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

Published on: May 19, 2023

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

科学领域:

医疗成像医学成像
辐射物理学辐射物理学
医疗保健中的人工智能

背景情况:

精确的辐射剂量评估在计算机断层扫描 (CT) 中至关重要.
尺寸特定剂量估计 (SSDE) 有助于标准化不同患者尺寸的剂量报告.
手动计算诸如正确有效直径 (Deffcorr) 等参数可能耗时且容易变化.

研究的目的:

开发和验证使用卷积神经网络 (CNN) 在胸部CT中计算SSDE的自动化方法.
根据自动细分获得的纠正有效直径 (Deffcorr) 来确定SSDE.
将自动化方法的结果与手动计算和既定的剂量指标进行比较.

主要方法:

基于U-Net的CNN架构用于胸部CT图像的自动细分.
CNN对肺部,骨和其他组织进行了细分,以计算尺寸,随后纠正有效直径 (Deffcorr).
开发的模型在108个胸部CT数据集上进行了训练,结果与使用线性回归和布兰德-阿尔特曼分析的手动测量和水等价直径 (Dw) 计算进行了比较.

主要成果:

自动化的CNN方法与基于Deffcorr.com的SSDE的手动计算具有很高的一致性.
平均SSDE值在各方法中是可比的:14.3 ± 2.1 mGy (手动Deffcorr),14.6 ± 2.2 mGy (Dw) 和14.5 ± 2.4 mGy (自动Deffcorr).
经过训练的U-Net模型准确地预测了SSDE,结果与手工估计一致.

结论:

建议使用CNN的自动化框架为计算Defcorr-basedSSDEs在胸部CT中提供了可靠和高效的解决方案.
这种人工智能驱动的方法可以简化CT检查中的剂量评估.
自动化方法为提高胸部CT中辐射剂量报告的准确性和一致性提供了一个有希望的工具.