Delineation and quantitation of brain lesions by fuzzy clustering in positron emission tomography

被引：30

作者：

Boudraa, AEO

Champier, J

Cinotti, L

Bordet, JC

Lavenne, F

Mallet, JJ

机构：

[1] Laboratoire de Biophysique, Fac. de Méd. Alexis Carrel, 63972 Lyon Cedex 08, rue Guillaume Paradin

[2] Ctr. d'Exploration/de Rech. M., 69500 Bron

[3] Hospices Civiles de Lyon, INSERM U 331, Laboratoire d'Hémobiologie, 69372 Lyon Cedex 08, rue Guillaume Paradin

来源：

COMPUTERIZED MEDICAL IMAGING AND GRAPHICS | 1996年 / 20卷 / 01期

关键词：

Positron Emission Tomography; lesion; fuzzy clustering; cluster; segmentation;

D O I：

10.1016/0895-6111(96)00025-0

中图分类号：

R318 [生物医学工程];

学科分类号：

0831 ;

摘要：

In this study, we investigate the application of the fuzzy clustering to the anatomical localization and quantitation of brain lesions in Positron Emission Tomography (PET) images. The method is based on the Fozzy C-Means (FCM) algorithm. The algorithm segments the PET image data points into a given number of clusters. Each cluster is an homogeneous region of the brain (e.g. tumor), A feature vector is assigned to a cluster which has the highest membership degree. Having the label affected by the FCM algorithm to a cluster, one may easily compute the corresponding spatial localization, area and perimeter, Studies concerning the evolution of a tumor after different treatments in two patients are presented, Copyright (C) 1996 Elsevier Science Ltd.

引用

页码：31 / 41

页数：11

共 29 条

[21] FAST AND RELIABLE IMAGE-ENHANCEMENT USING FUZZY RELAXATION TECHNIQUE [J].