Download the full-sized PDF of Efficient Technique for Corpus Callosum Segmentation in Midsagittal Brain MR ImagesDownload the full-sized PDF



Permanent link (DOI):


Export to: EndNote  |  Zotero  |  Mendeley


This file is in the following communities:

Graduate Studies and Research, Faculty of


This file is in the following collections:

Theses and Dissertations

Efficient Technique for Corpus Callosum Segmentation in Midsagittal Brain MR Images Open Access


Other title
image segmentation
adaptive mean shift
template matching
Geometric active contour
corpus callosum
Type of item
Degree grantor
University of Alberta
Author or creator
Li, Yue
Supervisor and department
Mrinal K. Mandal, Department of Electrical and Computer Engineering
S. Nizam Ahmed, Department of Medicine
Examining committee member and department
Roger Zemp, Department of Electrical and Computer Engineering
Jie Chen, Department of Electrical and Computer Engineering
Department of Electrical and Computer Engineering
Signal and Image Processing
Date accepted
Graduation date
2016-06:Fall 2016
Master of Science
Degree level
Neurological disorders are among major causes of disability in Canada. In the diagnostic procedure, Magnetic Resonance Imaging (MRI) is commonly used as it is non-invasive and can produce dramatic contrast between different brain tissues. Brain tissue segmentation is a fundamental step in brain MR images analysis. Corpus Callosum (CC) is an important brain tissue and is always adopted as the landmark of human brain. In this thesis, we propose an intelligent computer-aided detection (CAD) system for automatic segmentation of CC in T1-weighted midsagittal brain MRI slices. The proposed CAD system has three modules: Adaptive Mean Shift Clustering (AMS), Automated CC Contour Initialization (ACI), and Geometric Active Contour (GAC) based Segmentation. In the first module, homogenous regions in the input image are divided into clusters with an adaptive mean shift clustering method. In the second module, area analysis, template matching, shape and location analysis are used to identify the cluster that contains CC and extract a rough boundary of CC as the initial contour. In the last module, the boundary of recognized CC region is used as the initial contour in the GAC model, and is evolved to obtain the final segmentation result of CC. Experimental results demonstrate that the proposed AMS-ACI technique is able to provide accurate initial CC contour, and the proposed AMS-ACI-GAC technique overcomes the problem of user-guided initialization in existing GAC techniques, and provides a reliable and accurate performance in CC segmentation.
This thesis is made available by the University of Alberta Libraries with permission of the copyright owner solely for the purpose of private, scholarly or scientific research. This thesis, or any portion thereof, may not otherwise be copied or reproduced without the written consent of the copyright owner, except to the extent permitted by Canadian copyright law.
Citation for previous publication

File Details

Date Uploaded
Date Modified
Audit Status
Audits have not yet been run on this file.
File format: pdf (PDF/A)
Mime type: application/pdf
File size: 3897202
Last modified: 2016:11:16 13:38:15-07:00
Filename: Li_Yue_201609_MSc.pdf
Original checksum: 6af55a216db7ac04645022712165799f
Activity of users you follow
User Activity Date