Automated segmentation of MR images of brain tumors

被引：325

作者：

Kaus, MR

Warfield, SK

Nabavi, A

Black, PM

Jolesz, FA

Kikinis, R

机构：

[1] Harvard Univ, Sch Med, Brigham & Womens Hosp, Dept Radiol,Surg Planning Lab, Boston, MA 02115 USA

[2] Harvard Univ, Sch Med, Brigham & Womens Hosp, Dept Neurosurg, Boston, MA 02115 USA

[3] Univ Erlangen Nurnberg, Lehrstuhl Tech Elekt, Erlangen, Germany

来源：

RADIOLOGY | 2001年 / 218卷 / 02期

关键词：

brain neoplasms; MR; magnetic resonance (MR); technology; three-dimensional; volume measurement; technology assessment;

D O I：

10.1148/radiology.218.2.r01fe44586

中图分类号：

R8 [特种医学]; R445 [影像诊断学];

学科分类号：

1002 ; 100207 ; 1009 ;

摘要：

An automated brain tumor segmentation method was developed and validated against manual segmentation with three-dimensional magnetic resonance images in 20 patients with meningiomas and low-grade gliomas. The automated method (operator time, 5-10 minutes) allowed rapid identification of brain and tumor tissue with an accuracy and reproducibility comparable to those of manual segmentation (operator time, 3-5 hours), making automated segmentation practical for low-grade gliomas and meningiomas.

引用

页码：586 / 591

页数：6

共 28 条

[1]

ALEXANDER E, 1996, IMAGE GUIDED NEUROSU, P260

[2] Development and implementation of intraoperative magnetic resonance imaging and its neurosurgical applications [J].