Improving the accuracy of volumetric segmentation using pre-processing boundary detection and image reconstruction

被引：14

作者：

Archibald, R ^{[1
]}

Hu, JX

Gelb, A

Farin, G

机构：

[1] Arizona State Univ, Ctr Syst Sci & Engn Res, Tempe, AZ 85287 USA

[2] Arizona State Univ, Dept Bioengn, Tempe, AZ 85287 USA

[3] Arizona State Univ, PRISM, Tempe, AZ 85287 USA

[4] Arizona State Univ, Dept Math & Stat, Tempe, AZ 85287 USA

[5] Arizona State Univ, Dept Comp Sci, Tempe, AZ 85287 USA

来源：

IEEE TRANSACTIONS ON IMAGE PROCESSING | 2004年 / 13卷 / 04期

基金：

美国国家科学基金会;

关键词：

edge detection; Gegenbauer reconstruction; magnetic resonance imaging; Weibull E-SD field; three dimensional (3-D) segmentation;

D O I：

10.1109/TIP.2003.819862

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 [模式识别与智能系统]; 0812 [计算机科学与技术]; 0835 [软件工程]; 1405 [智能科学与技术];

摘要：

The concentration edge -detection and Gegenbauer image-reconstruction methods were previously shown to improve the quality of segmentation in magnetic resonance imaging. In this study, these methods are utilized as a pre-processing step to the Weibull E-SD field segmentation. It is demonstrated that the combination of the concentration edge detection and Gegenbauer reconstruction method improves the accuracy of segmentation for the simulated test data and real magnetic resonance images used in this study.

引用

页码：459 / 466

页数：8

共 17 条

[1]

Improving tissue segmentation of human brain MRI through preprocessing by the Gegenbauer reconstruction method [J].