Segmenting articular cartilage automatically by edge detection and support vector machine

庞剑飞; 邱明国; 陈伟; 刘杰; 陈永林

您当前的位置：

首页 >

文章列表页 >

Segmenting articular cartilage automatically by edge detection and support vector machine

更新时间：2026-01-09

- Segmenting articular cartilage automatically by edge detection and support vector machine
- Journal of Army Medical University Vol. 35, Issue 16, Pages: 1653-1657(2013)
- 作者机构：
- 作者简介：
- 基金信息：
- DOI：
  CLC： R312;R322.72;R445.2
- Published：2013
- 稿件说明：
移动端阅览
庞剑飞,邱明国,陈伟,刘杰,陈永林.基于边缘检测与支持向量机的关节软骨自动分割算法研究[J].陆军军医大学学报(原第三军医大学学报),2013,35(16):1653-1657.

　Pang Jianfei,Qiu Mingguo,Chen Wei,Liu Jie,Chen Yonglin.Segmenting articular cartilage automatically by edge detection and support vector machine[J].J Amry Med Univ (J Third Mil Med Univ),2013,35(16):1653-1657.
庞剑飞,邱明国,陈伟,刘杰,陈永林.基于边缘检测与支持向量机的关节软骨自动分割算法研究[J].陆军军医大学学报(原第三军医大学学报),2013,35(16):1653-1657. DOI：

　Pang Jianfei,Qiu Mingguo,Chen Wei,Liu Jie,Chen Yonglin.Segmenting articular cartilage automatically by edge detection and support vector machine[J].J Amry Med Univ (J Third Mil Med Univ),2013,35(16):1653-1657. DOI：

摘要

目的设计并实现一种针对核磁共振成像（MRI）图像的关节软骨自动分割算法。方法利用像素的整体与局部特征分别构建二分类支持向量机（support vector machine，SVM）分类器对股软骨、胫软骨及髌软骨进行自动分割。首先提出一种基于边缘数目反馈的Canny检测器阈值迭代法并利用该方法提取图像的主要边缘，随后根据特征参数对提取的边缘进行识别并标记出不同的骨-软骨边缘，利用训练的SVM分类器对软骨进行初步分割并根据软骨的解剖位置缩小搜索空间，最后利用形态学操作对初步分割结果进行优化。结果自动分割结果中软骨的形态轮廓与原始图像吻合效果好，股软骨、胫软骨及髌软骨的Dice’s系数平均值分别为0.80、0.76、0.74，与手工分割结果具有较好的一致性。结论该算法能够准确、快速地分割出MRI图像中不同的软骨组织。

Abstract

Objective To explore the possibilities of automatic segmentation of articular cartilage in the MR images. Methods Three binary classifiers were built with edge-distance

intensity and other voxel features using support vector machine to segment the femur cartilage

tibia cartilage and patellar cartilage separately. Firstly

an iterative procedure based on the feedback of the number of main edges was designed to get an appropriate threshold for Canny operator and extract the main edges with it from MRI images. Secondly

the different edges with some feature parameters were identified

which distinguished different cartilages synchronously. To improve the speed of segmentation

the search space was reduced according to the cartilage edge and its anatomic location. Thirdly

the cartilage tissues were segmented preliminarily with different trained classifiers. Finally

morphological operations were used to make those results better. Results The cartilage edge was smooth in automatic segmentation results and had a good consistency with manual segmentation results. The mean Dice similarity coefficient of femoral cartilage

tibial cartilage and patellar cartilage was 0.80

0.76 and 0.74

respectively. Conclusion The algorithm can segment the articular cartilage automatically from MR images more accurately and quickly.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Automatic segmentation of lung tissue in thoracic MRI images

Radiologic features of fumarate hydratase-deficient renal cell carcinoma

Prediction of in-hospital mortality risk in intensive care unit with support vector machine

Arthroscopic microfracture procedure in treatment of osteochondral lesions of the talus

Prediction of outer membrane proteins with encoding based on grouped weight and feature selection techniques

Related Author

潘进洪

胡南

吴毅

张绍祥

罗洪艳

杨维萍

李晓明

段光杰

Related Institution

Department of Pathology， Frist Affiliated Hospital， Army Medical University （Third Military Medical University）

Institute of Clinical Pathology， Key Laboratory of Tumor Immunopathology， Ministry of Education

Department of Radiology

⁰