IMAGE SEGMENTATION FOR BRAIN TUMOUR PREDICTION USING WATERSHED ALGORITHN

COMPUTER ENGINEERING

Abstract Background/Objectives The objective of this paper is to study of segmentation methods implemented in Magnetic Resonance Imaging (MRI) images of Brain using MATLAB and compare time and accuracy of various segmentation techniques. Statistical Analysis/Findings Pre-processing is required for better segmentation, as it removes noise and makes images as better quality. De-noising is necessary to reduce the affect of noise on the image results. In this paper for de-noising, I have studied various morphological filters and used that filters and some techniques to predict the brain tumour .Segmentation using fuzzy C-Means and watershed Algorithm, these two methods is performed and compared with time and accuracy of that segmentation. Some techniques are used in order to get segmented image have higher accuracy. These techniques are Median Filter, Bias Field, Gaussian Mixer Model and Fuzzy Local GMM. Application/Improvement Segmented tumour with higher efficiency leads to help doctor in anatomy and pathology to classify tumour detection. So that treatment could be started accordingly as soon as possible.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.