LEGION—Based Segmentation of Magnetic Resonance Images of the Brain

Abstract

In this paper a new biologically inspired oscillator network, called Locally Excitatory Globally Inhibitory Oscillator Network (LEGION), is used to perform segmentation on sampled medical image datasets. An image segmentation algorithm that uses LEGION components and an adaptive scheme to choose tolerances is described. The results of the algorithm on MRI medical image datasets, with manual segmentation are obtained and compared. LEGION'S computational and architectural properties make it a promising approach for real-time medical image segmentation using multiple features.

Indexing terms:

• LEGION
• MRI
• Oscillatory correlation
• Segmentation

Additional information

Notes on contributors

G Sivaradje

G Sivaradje received BE degree from University of Madras, in 1991 and MTech degree in Electronics and Communication Engineering from Pondicherry Engineering College, Pondicherry, in 1996. He has six years teaching and 4 years of Industrial Experience. He is currently working as Senior Lecturer in the Depaertment of Electronics and Communication Engineering, Pondicherry Engineering College, Pondicherry. He has 4 publications in reputed International Journals and also presented papers more than 10 in International Conferences and in 12 National Conferences. His area of interest is Wireless Communication, ATM Networking and Signal Processing.

D Saraswady

D Saraswady received BTech degree and MTech Degree in Electronics and Communication Engineering from Pondicherry Engineering College, Pondicherry, in 1993 and 1996 respectively. She has seven years of teaching experience. She is currently working as Senior Lecturer in the Depaertment of Electronics and Communication Engineering, Pondicherry Engineering College, Pondicherry. She has 3 publications in reputed Journals and presented more than 8 papers in International Conferences and 8 in National Conferences. His area of interest is Wireless Networking, Mobile Communication and Signal Processing.

P Dananjayan

P Dananjayan received BSc degree in Physics from University of Madras, in 1979, BTech and MTech degree in Electronics Engineering from Madras Institute of Technology, Madras in 1982 and 1984 respectively and PhD degree from Anna University, Chennai in 1998. He has 16 years experience in teaching. He is currently working as Professor and Head of department of Electronics and Instrumentation Engineering, Pondicherry Engineering College, Pondicherry. He has 4 publications in reputed International Journals and also presented papers more than 14 in International Conferences and in 15 National Conferences. His area of interest is Wireless Communication, ATM Network and Spread Spectrum communication.