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

Spectral deep learning-based patient and bowtie scatter correction for clinical photon-counting CT.

Medical physics·2026

Same author

Detection of calcified plaques: comparison between coronary CT angiography and thin-slice non-contrast CT with deep learning-aided image registration.

European radiology·2026

Same author

Challenging Hounsfield Unit cutoffs: spectral thresholding for synthetic coronary plaque phantoms on photon-counting CT.

Journal of medical imaging (Bellingham, Wash.)·2026

Same author

Erratum: Modeling the DQE(<i>f</i> ) of photon-counting detectors: impact of the pixel sensitivity profile (2019<i>Phys. Med. Biol</i>.<b>64</b>105008).

Physics in medicine and biology·2026

Same author

A novel projection data domain material decomposition method for dual-energy CT and its impact on the accuracy of attenuation values.

Physics in medicine and biology·2026

Same author

Feasibility of opportunistic dental diagnostics in routine photon-counting CT examinations of the cervical spine.

BMC oral health·2026

Search research articles

相关实验视频

Updated: Jul 5, 2025

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

在临床螺旋CT中减少风车工件,使用基于深度学习的投影原始数据上采样:方法和稳定性评估.

Jan Magonov^1,2,3, Joscha Maier¹, Julien Erath²

¹Division of X-Ray Imaging and Computed Tomography, German Cancer Research Center (DKFZ) Heidelberg, Heidelberg, Germany.

Medical physics

|January 16, 2024

概括

这项研究引入了一种深度学习方法,通过改进z轴采样来减少多切片螺旋计算断层扫描 (MSCT) 中的风车工件. 与临床数据相比,使用合成数据的训练在减少这些人工物方面表现出更好的表现.

关键词:

临床螺旋CTCT 计算机断层扫描 (CT) 是一种计算机断层扫描.卷积神经网络是一种卷积神经网络.深度学习是一种深度学习.图像质量图像质量图像质量医学成像医学成像预测原始数据上采样风车工件减少风车工件减少这是一个z-flying焦点点.

更多相关视频

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer

Published on: October 13, 2023

3D Imaging of Soft-Tissue Samples using an X-ray Specific Staining Method and Nanoscopic Computed Tomography

3D Imaging of Soft-Tissue Samples using an X-ray Specific Staining Method and Nanoscopic Computed Tomography

Published on: October 24, 2019

相关实验视频

Last Updated: Jul 5, 2025

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer

Published on: October 13, 2023

3D Imaging of Soft-Tissue Samples using an X-ray Specific Staining Method and Nanoscopic Computed Tomography

3D Imaging of Soft-Tissue Samples using an X-ray Specific Staining Method and Nanoscopic Computed Tomography

Published on: October 24, 2019

科学领域:

医疗成像医学成像
计算机断层扫描 (CT) 是一种计算机断层扫描.
人工智能的人工智能

背景情况:

多切片螺旋计算断层扫描 (MSCT) 成像可以产生别名器件或风车器件,因为在z轴上采样不足.
这些文物表现为明亮的条纹,与高对比度结构分开,降低图像质量.

研究的目的:

提出基于深度学习的方法作为z-flying焦点 (zFFS) 硬件解决方案的替代方案,以减少别名化工件.
通过开发用于原始数据插值的监督学习模型来增强MSCT的纵向采样.

主要方法:

开发了一个监督学习模型,将输入预测映射到双重z方向采样所需的行中.
该方法使用临床 (40例患者扫描) 和合成 (100例模拟扫描) 数据集进行了评估,用于培训和验证.
性能在实体患者扫描和幻影测量的测试集上进行了定性和定量评估,包括对扫描配置的模拟研究.

主要成果:

深度学习模型比忽视双重纵向抽样改进了根平均平方误差大约20%,与忽视双重纵向抽样相比.
临床和合成训练数据都有效地减少了风车文物.
与临床数据相比,使用合成数据的训练在人工物减少方面取得了更好的表现.

结论:

基于深度学习的原始数据插值可以增强z轴采样并最大限度地减少MSCT中的别名化文物,为zFFS提供了替代方案.
使用合成数据的训练在减少人工制造物方面显示出特别有希望的结果.
这种方法为没有zFFS硬件功能的CT扫描仪提供了有益的解决方案.