Date of Award

12-2015

Degree Name

Master of Science in Engineering

Department

Electrical and Computer Engineering

First Advisor

Dr. Ikhlas Abdel-Qadar

Second Advisor

Dr. Raghvendra Gejji

Third Advisor

Dr. Jareer Abdel Qader

Keywords

Brain tumor, MRI, edge detection, segmentation, morphological operations

Access Setting

Masters Thesis-Open Access

Abstract

Detecting the precise boundary of the area containing a recognized brain tumor is a complex problem and must be addressed since it applies to many medical modalities and tumor types. The objective of this thesis is to provide an efficient algorithm for detecting edges of brain tumors to help neurosurgeons identify the border of the critical area and distinguish the precise margin of the tumor from the rest of the brain tissue during the surgery. This thesis work exploits MRI brain tumor images as a tool to aid surgeons. MRI image segmentation is an essential step as a preliminary process to localize the region of interest, which is the brain tumor region. This work proposes a new method using morphological operators and utilizing an erosion process to identify and extract the boundary of a brain tumor. Using abnormal images of a variety of brain tumors, this study shows that the proposed algorithm provides a robust method in terms of accuracy and computation time, making it suitable for real-time processing. Results also show that this algorithm is capable of producing one-pixel-width continuous edges as well as accurate positioning of abnormal cells. This study also presents the results of a comparative study of its proposed method and common edge detection techniques such as Sobel, Robert, Prewitt, Canny and Cellular Automata.

Share

COinS