Global and local fuzzy clustering with spatial information for medical image segmentation

Wenchao Cui, Yi Wang, Yangyu Fan, Yan Feng, Tao Lei

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

This paper presents a new fuzzy clustering algorithm for simultaneous segmentation and bias field estimation of medical images. The proposed algorithm, by introducing the standard fuzzy C-means (FCM) objective function into the coherent local intensity clustering (CLIC) criterion function, formulates a global and local fuzzy clustering based objective function to be minimized. The local fuzzy clustering term allows the algorithm to deal with intensity inhomogeneity in images. The global fuzzy clustering term, being endowed with an adaptive weight function, improves the accuracy of segmentation. Besides, to reduce the impact of noise, the proposed algorithm incorporates spatial information into the membership function. Experiment results on clinical and simulated medical images demonstrate the superior performance of the proposed algorithm.

Original languageEnglish
Title of host publication2013 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2013 - Proceedings
Pages533-537
Number of pages5
DOIs
StatePublished - 2013
Event2013 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2013 - Beijing, China
Duration: 6 Jul 201310 Jul 2013

Publication series

Name2013 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2013 - Proceedings

Conference

Conference2013 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2013
Country/TerritoryChina
CityBeijing
Period6/07/1310/07/13

Keywords

  • Bias field estimation
  • fuzzy clustering
  • image segmentation
  • spatial information

Fingerprint

Dive into the research topics of 'Global and local fuzzy clustering with spatial information for medical image segmentation'. Together they form a unique fingerprint.

Cite this