Adaptive Neuro-Fuzzy Inference System for brain abnormality segmentation

Author

Noor, Noorhayati Mohamed ; Khalid, Noor Elaiza Abdul ; Hassan, Rohaida ; Ibrahim, Shafaf ; Yassin, Ihsan Mohd

Author_Institution

Fac. of Comput. & Math. Sci., Univ. Teknol. Mara, Shah Alam, Malaysia

fYear

2010

fDate

22-22 June 2010

Firstpage

68

Lastpage

70

Abstract

This paper studies the application of the Adaptive Neuro-Fuzzy Inference System (ANFIS) for segmentation of brain abnormality in MRI images. Segmentation of MRI image is an important part of brain imaging research. In this study, 150 MRI images were used as testing data for the system. The data was created by combining the shapes and size of various abnormalities and pasting it onto normal brain image. Several types of backgrounds were tested - low, medium and high grey levels. The experimental results show good segmentation for medium and low background levels value for both light and dark abnormality levels over different backgrounds.

Keywords

biomedical MRI; brain; fuzzy neural nets; image segmentation; inference mechanisms; ANFIS; MRI image segmentation; abnormality levels; adaptive neuro-fuzzy inference system; brain abnormality segmentation; brain imaging research; Accuracy; Adaptive systems; Brain; Control systems; Image segmentation; Magnetic resonance imaging; Adaptive Neuro-Fuzzy Inference System (ANFIS); Brain Abnormality Segmentation; Magnetic Resonance Imaging (MRI);

fLanguage

English

Publisher

ieee

Conference_Titel

Control and System Graduate Research Colloquium (ICSGRC). 2010 IEEE

Conference_Location

Shah Alam

Print_ISBN

978-1-4244-7238-3

Type

conf

DOI

10.1109/ICSGRC.2010.5562519

Filename

5562519