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

Computed Tomography

Computed Tomography

Tomography refers to imaging by sections. Computed tomography (CT) is a non-invasive imaging technique that uses computers to analyze several cross-sectional X-rays to reveal minute details about structures in the body.
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...

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

Multimodal echocardiographic techniques in the diagnosis of cardiac tumors: applications and recent advances.

Frontiers in cardiovascular medicine·2026

Same author

Sweat and air permeable electronics enabled by engineered hierarchical fabric system for exercise management.

Microsystems & nanoengineering·2026

Same author

Spectral computed tomography characterization of coronary atherosclerotic plaque: principles, imaging biomarkers, and clinical significance.

Frontiers in cardiovascular medicine·2026

Same author

An electron-density point-cloud framework for robust protein-ligand interaction prediction.

Nature communications·2026

Same author

CT imaging features of pulmonary SMARCA4-deficient undifferentiated carcinoma: a retrospective case series.

Frontiers in oncology·2026

Same author

Clustering of quantitative CT features identifies HCC subtypes with distinct prognosis and immune signatures.

European radiology experimental·2026

Search research articles

相关实验视频

Updated: Jun 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

多尺度感知调制网络用于低剂量计算机断层扫描,消除噪音.

Jiexing Huang¹, Anni Zhong², Yujian Liu¹

¹Department of Radiation Oncology, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China.

Quantitative imaging in medicine and surgery

|December 19, 2024

概括

此摘要是机器生成的。

这项研究引入了一种新的深度学习网络,用于低剂量计算机断层扫描 (LDCT). 开发的多尺度感知调制网络 (MSPMnet) 有效地减少噪音和文物,同时保持图像质量,优于现有方法.

关键词:

低剂量计算机断层扫描 (LDCT)可分解的卷积卷积.拒绝使用,拒绝使用.模块化调制的方法多个尺度的感知感知.

更多相关视频

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Published on: April 12, 2024

相关实验视频

Last Updated: Jun 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

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Published on: April 12, 2024

科学领域:

医疗成像医学成像
人工智能的人工智能
计算机视觉计算机视觉

背景情况:

低剂量计算机断层扫描 (LDCT) 尽量减少辐射暴露,但引入噪音和文物,损害诊断准确性.
现有的卷积神经网络 (CNN) 对于LDCT无声化具有有限的受体场,阻碍了性能.
在CNN中增加内核大小可以提高性能,但会显著提高计算成本.

研究的目的:

开发一种新的LDCT,以扩大受体场和降低计算复杂度,反对CNN.
引入一个多尺度感知调制网络 (MSPMnet),能够有效地扩展感受场和多尺度特征捕获.

主要方法:

开发了一种多头可分解卷积 (MHDC) 模块,以有效地扩展受体场并捕获多尺度特征.
MHDC将最大共享与深度智能卷积相结合,并将大型2D内核分解为1D内核,以提高计算效率.
引入了一个可接收的现场道机制,以逐步模拟随着网络深度增加的远程依赖.

主要成果:

根据梅奥诊所数据集进行评估,MSPMnet与传统算法,CNN和变形机相比,显示出优越的视觉和定量无色化性能.
MSPMnet有效地减少了噪音和文物,同时保留了关键的图像结构,边缘和纹理.
实现了最低的RMSE (8.3094±1.9325) 和最高的PSNR (33.8525±1.8213dB),SSIM (0.9309±0.0272) 和FSIM (0.9699±0.0113) 的结果.

结论:

拟议的MSPMnet在LDCT的申诉方面取得了重大进展.
它有效地消除噪音和文物,同时保持高图像保真性,优于当前最先进的方法.
MSPMnet为高质量的LDCT图像重建提供了一个计算效率高的解决方案.