A new method based on both fuzzy set and possibility theories for tumor volume segmentation on PET images

A S Dewalle-Vignion; N Betrouni; N Makni; D Huglo; J Rousseau; M Vermandel

doi:10.1109/IEMBS.2008.4649865

A new method based on both fuzzy set and possibility theories for tumor volume segmentation on PET images

Annu Int Conf IEEE Eng Med Biol Soc. 2008:2008:3122-5. doi: 10.1109/IEMBS.2008.4649865.

Authors

A S Dewalle-Vignion¹, N Betrouni, N Makni, D Huglo, J Rousseau, M Vermandel

Affiliation

¹ Inserm, U703, University Hospital of Lille, France. [email protected]

PMID: 19163368
DOI: 10.1109/IEMBS.2008.4649865

Abstract

A new automatic method for tumor volume segmentation on PET images has been developed. The method introduced in this paper is based on previous works in MRA segmentation and involves both fuzzy set and possibility theories. Visual results prove the method efficiency which is confirmed by obtained Jaccard index.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Algorithms
Automation
Carcinoma, Hepatocellular / pathology
Diagnosis, Computer-Assisted / methods*
Fuzzy Logic
Humans
Image Enhancement / methods*
Image Processing, Computer-Assisted
Imaging, Three-Dimensional
Liver Neoplasms / pathology
Models, Theoretical
Neoplasms / diagnosis*
Neoplasms / pathology*
Positron-Emission Tomography / methods*
Probability
Reproducibility of Results