Multi-parameter Registration Model for Brain MR Image Segmentation Based on Label Fusion

ZHANG Wan; LIU Gang; ZHU Kai; LIAO Heng-xu

doi:10.3969/j.issn.0372-2112.2017.09.022

您当前的位置：

首页 >

文章列表页 >

Multi-parameter Registration Model for Brain MR Image Segmentation Based on Label Fusion

更新时间：2025-07-16

- Multi-parameter Registration Model for Brain MR Image Segmentation Based on Label Fusion
- Acta Electronica Sinica Vol. 45, Issue 9, Pages: 2202-2209(2017)
- 作者机构：
  
  1. 上海电力学院自动化工程学院,上海,200090
  2. 国网浙江省电力公司金华供电公司,浙江,金华,321000
  3. 上海电力学院自动化工程学院,上海,200090
  4. 国网浙江省电力公司金华供电公司,浙江,金华,321000
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China (No.61203224);Innovation Program of Shanghai Municipal Education Commission (No.13YZ101)
- DOI：10.3969/j.issn.0372-2112.2017.09.022
  CLC： TP391
- Published Online：25 September 2017，
  
  Published：2017
- 稿件说明：
移动端阅览
ZHANG Wan, LIU Gang, ZHU Kai, et al. Multi-parameter Registration Model for Brain MR Image Segmentation Based on Label Fusion[J]. Acta Electronica Sinica, 2017, 45(9): 2202-2209.
DOI：

ZHANG Wan, LIU Gang, ZHU Kai, et al. Multi-parameter Registration Model for Brain MR Image Segmentation Based on Label Fusion[J]. Acta Electronica Sinica, 2017, 45(9): 2202-2209. DOI： 10.3969/j.issn.0372-2112.2017.09.022.

摘要

配准技术在基于多图谱的分割方法中能有效地将医学图谱的先验知识融入分割过程，再结合以高效的标记融合算法，最终实现精确地自动分割.针对图谱配准的较大误差及其对标记融合的重要影响，本文建立了一种新的概率图模型框架并以此提出了基于多参数配准模型的分割算法，将此方法与高效的标记融合算法相结合，可以提高目标图像中特定组织区域的分割精度，更使其在少量图谱分割的情形下具有重要应用.首先，使用多种配准参数对所有目标图像进行配准；然后，分别采用不同的算法对配准图像进行灰度融合和标记融合，实现训练图像的重构过程；最后，利用高效的标记融合算法对重构后的图像进行融合得到最终精确的分割结果.实验结果表明该方法均优于本文其他分割算法，能够有效提升脑部组织分割精度.

Abstract

Registration technology can effectively integrate the prior knowledge of medical atlases into the segmentation process

and then combine with the efficient label fusion algorithm to obtain the segmentation results accurately and automatically.Aimed at the large error in registration of target image and its great influence on label fusion

a framework of probabilistic graphical model is established and the idea of multi-parameter registration model is proposed.Combined with an efficient algorithm on label fusion

this framework can improve the segmentation accuracy of specific tissue regions on target image

which has important application value in segmentation with a few available atlases.After the multi-parameter registration and the reconstruction process of training sets on target images

the final segmentation results are obtained by an efficient fusion algorithm.According to the experiment which was conducted on the brain magnetic resonance image segmentation with different segmentation methods

the proposed framework can effectively improve the accuracy of segmentation.

关键词

Keywords

references

Views

350

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Multi-dimensional Registration of X-Ray Image and CT Image

Enhanced PFCM Algorithm for Noisy Image Segmentation Combining Regional and Neighborhood-Level Information

SwinT-Unet: Ultrasound Image Segmentation Based on Two-Channel Self-Attention Mechanism

A Variational Level Set Model Based on Beer-Lambert Law

ED-NAS: Ceramic Grain Segmentation Based on Neural Architecture Search Using SEM Images

Related Author

ZHANG Hui

PASCAL Haigron

SHU Hua-zhong

LUO Li-min

WANG Xiao-peng

WANG Hai-zhou

CHEN Hao-ran

SONG Yan-tao

Related Institution

LIST Lab.Dept.of Biomedical Engineering,Southeast University.,Jingsu

.of Treatment of Signal and Image,University of Rennes 1. Rennes

LIST Lab.Dept.of Biomedical EngineeringSoutheast University.NanjingJingsu 210096China

.of Treatment of Signal and ImageUniversity of Rennes 1. Rennes35042France

School of Electronic and Information Engineering, Lanzhou Jiaotong University

⁰