An Enhanced Implementation of Brain Tumor Detection Based on Statistical Features and F-Transform

Authors

  • Nemir Ahmed Al-Azzawi Biomedical Engineering Department, University of Baghdad, Al-Jadriah, P.O.Box 47187, Baghdad, Iraq.
  • Mohannad Kadhim Sabir Biomedical Engineering Department, University of Baghdad, Al-Jadriah, P.O.Box 47187, Baghdad, Iraq.

Keywords:

MRI, Image Segmentation, Brain Tumor, Ftransform (Fuzzy-Transform), Edge Detection.

Abstract

Brain tumor is an abnormal growth of cells inside brain, which may be cancerous or non-cancerous. This paper describes the proposed approach for detection and extraction brain tumor from MRI scan images. Brain tumor need be detected, diagnosed and estimated in earliest stage. The classification involves classification of images into normal and tumor detected. The medical difficulties become serious if tumor is detected at the later stage. Asymmetry of brain is used for detection of abnormality. Statistical Features were extracted from the detected tumor texture using three kinds of features. The difference between the two halves in that row can judge each data as normal or with suspicious tumors. After detecting the tumor, the segmentation based on F-transform (FuzzyTransform) and morphological operations are performed to delineating brain tumor boundaries and calculate the area of the tumor. The F-transform is an excellent method to extract the salient edges. Experimental results on brain MR images succeed an average accuracy of 96 % and precision of 95% using the proposed algorithm.

Downloads

Download data is not yet available.

Downloads

Published

2017-06-01

How to Cite

Ahmed Al-Azzawi, N., & Sabir, M. K. (2017). An Enhanced Implementation of Brain Tumor Detection Based on Statistical Features and F-Transform. Journal of Telecommunication, Electronic and Computer Engineering (JTEC), 9(2-2), 65–70. Retrieved from https://jtec.utem.edu.my/jtec/article/view/2221