FCD segmentation using texture asymmetry of MR-T1 images of the brain

Author

Bergo, Felipe P G ; Falcao, Alexandre X. ; Yasuda, Clarissa L. ; Cendes, Fernando

Author_Institution

LIV, Inst. of Comput., Campinas

fYear

2008

fDate

14-17 May 2008

Firstpage

424

Lastpage

427

Abstract

Focal cortical dysplasia is the most common malformation in patients with intractable epilepsy. The segmentation of FCD lesions in MR-T1 images of the brain is a crucial step for treatment planning. In this work we present a new FCD segmentation technique based on analysis of texture asymmetry. This technique does not rely on template-based segmentation and is applicable to patients of any age, regardless of anatomic variations. We evaluated the method on 5 patients (aged 1 ly-51y), and obtained 100% detection rate and coverage of 76.9% of the lesional voxels.

Keywords

biomedical MRI; brain; diseases; feature extraction; image classification; image segmentation; medical image processing; MR-T1 images; brain; curvilinear reformatting computation; feature extraction; focal cortical dysplasia; image segmentation; outlier removal; pattern recognition; texture asymmetry; voxel classification; Aging; Chromium; Epilepsy; Feature extraction; Image segmentation; Image texture analysis; Lesions; Magnetic resonance imaging; Medical diagnosis; Pediatrics; Epilepsy; Focal Cortical Dysplasia; Image Segmentation; Medical diagnosis; Pattern Recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Biomedical Imaging: From Nano to Macro, 2008. ISBI 2008. 5th IEEE International Symposium on

Conference_Location

Paris

Print_ISBN

978-1-4244-2002-5

Electronic_ISBN

978-1-4244-2003-2

Type

conf

DOI

10.1109/ISBI.2008.4541023

Filename

4541023