Registration Based Super-Resolution Reconstruction for Lung 4D-CT Image

WU Xiu-xiu; XIAO Shan; ZHANG Yu

doi:10.3969/j.issn.0372-2112.2015.02.027

您当前的位置：

首页 >

文章列表页 >

Registration Based Super-Resolution Reconstruction for Lung 4D-CT Image

更新时间：2025-07-16

- Registration Based Super-Resolution Reconstruction for Lung 4D-CT Image
- Acta Electronica Sinica Vol. 43, Issue 2, Pages: 383-386(2015)
- 作者机构：
  
  南方医科大学生物医学工程学院,广东,广州,510515
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.0372-2112.2015.02.027
  CLC： TP751
- Published：2015
- 稿件说明：
移动端阅览
WU Xiu-xiu, XIAO Shan, ZHANG Yu. Registration Based Super-Resolution Reconstruction for Lung 4D-CT Image[J]. Acta Electronica Sinica, 2015, 43(2): 383-386.
DOI：

WU Xiu-xiu, XIAO Shan, ZHANG Yu. Registration Based Super-Resolution Reconstruction for Lung 4D-CT Image[J]. Acta Electronica Sinica, 2015, 43(2): 383-386. DOI： 10.3969/j.issn.0372-2112.2015.02.027.

摘要

肺4D-CT数据在肺癌治疗中有重要意义.但肺4D-CT数据纵向(

方向)分辨率低

为显示正确比例图像需进行插值运算

由此带来图像的模糊.本文提出了一种基于Active Demons配准的超分辨率重建技术来提高肺4D-CT图像分辨率.我们将不同相位同一位置的低分辨率图像视为不同帧图像.首先采用Active Demons配准方法得到不同帧图像之间的运动估计;而后采用凸集投影(Projection Onto Convex Set

POCS)超分辨率算法重建高分辨率肺图像.实验结果表明

与三次样条插值和反投影方法相比较

我们的方法能得到更清晰的肺图像

明显增强图像结构.

Abstract

Lung 4D-CT plays an important role in lung cancer radiotherapy.However

due to the great inter-slice thickness

the fuzzy images will be induced because of interpolation operation during the multi-plane display.In this paper

we take the low-resolution images of different phases in the corresponding position as different frame images

and propose a registration based super-resolution reconstruction method to improve the resolution of lung 4D-CT images.First

we employ the Active Demons registration to estimate the motion field between different frames.Then

the projection onto convex set (POCS) approach is employed to reconstruction high-resolution lung images.The experimental results show that our method can get more clear lung images and significantly enhance image structure

compared with the cubic spline interpolation and back projection method.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Cross Feature Updating-Based Network for Light Field Image Super Resolution

A Review of Single Image Super-Resolution Reconstruction Based on Deep Learning

A Super-Resolution Reconstruction Method for Land Cover Maps Using Multiple-Point Statistics

Related Author

CHEN Jia-ni

WU Ying-chun

LÜ Tian-qi

LIU Li

ZHAO Xian-ling

WU Jing

YE Xiao-jing

HUANG Feng

Related Institution

School of Electronic and Information Engineering, Taiyuan University of Science and Technology

School of Mechanical Engineering and Automation, Fuzhou University

Advanced Technology Innovation Institute, Fuzhou University

College of Computer and Data Science, Fuzhou University

School of Electronic Engineering and Optoelectronic Techniques,Nanjing University of Science and Technology

⁰