You could be reading the full-text of this article now if you...

If you have access to this article through your institution,
you can view this article in

Contour-Based Brain Segmentation Method for Magnetic Resonance Imaging Human Head Scans

Somasundaram, K.; Kalavathi, P.

Journal of Computer Assisted Tomography:
doi: 10.1097/RCT.0b013e3182888256

Abstract: The high-resolution magnetic resonance brain images often contain some nonbrain tissues (ie, skin, fat, muscle, neck, eye balls, etc) compared with the functional images such as positron emission tomography, single-photon emission computed tomography, and functional magnetic resonance imaging (MRI) scans, which usually contain few nonbrain tissues. Automatic segmentation of brain tissues from MRI scans remains a challenging task due to the variation in shape and size, use of different pulse sequences, overlapping signal intensities and imaging artifacts. This article presents a contour-based automatic brain segmentation method to segment the brain regions from T1-, T2-, and proton density–weighted MRI of human head scans. The proposed method consists of 2 stages. In stage 1, the brain regions in the middle slice is extracted. Many of the existing methods failed to extract brain regions in the lower and upper slices of the brain volume, where the brain appears in more than 1 connected region. To overcome this problem, in the proposed method, a landmark circle is drawn at the center of the extracted brain region of a middle slice and is likely to pass through all the brain regions in the remaining lower and upper slices irrespective of whether the brain is composed of 1 or more connected components. In stage 2, the brain regions in the remaining slices are extracted with reference to the landmark circle obtained in stage 1. The proposed method is robust to the variability of brain anatomy, image orientation, and image type, and it extracts the brain regions accurately in T1-, T2-, and proton density–weighted normal and abnormal brain images. Experimental results by applying the proposed method on 100 volumes of brain images show that the proposed method exhibits best and consistent performance than by the popular existing methods brain extraction tool, brain surface extraction, watershed algorithm, hybrid watershed algorithm, and skull stripping using graph cuts.

Author Information

From the Department of Computer Science and Applications, Gandhigram Rural Institute–Deemed University, Dindigul, Tamil Nadu, India.

Received for publication July 29, 2012; accepted January 7, 2013.

Reprints: P. Kalavathi, Department of Computer Science and Applications Gandhigram Rural Institute–Deemed University, Gandhigram 624 302, Dindigul, Tamil Nadu, India (e-mail:

The authors declare that they have no conflicts of interest.

© 2013 by Lippincott Williams & Wilkins