Ant Colony Optimization Technique on Brain Tumor Detection using Segmentation based on Machine learning Approaches.

Abstract

Problem Statement: Tumor is detected by a radiologist with help of MRI, which is an intricate process. Most of the brain tumor detection methods provide concrete information about the brain tumor and they lack in providing a precise result on existence of a tumor. As a result, a formal consultation with a radiologist is mandatory, which becomes a surplus expenditure in case of a healthy patient.  The objective of this research work is to develop a supporting system that would aid the radiologist to have the aforementioned result which reduces the time taken in brain tumor detection. 

Approach: The proposed method consists of four processing stages. In first stage, the MRI (Magnetic Resonance Imaging) Brain Image is acquired from MRI Brain Image data set. In second stage the acquired MRI Image is given to the Pre-Processing stage, where the film artifacts (labels) are removed. In third stage, the high frequency components are removed from MRI Image using various filtering techniques. Finally, this study investigates the most effective optimization method, known as Ant Colony Optimization (ACO) is considered in this proposed research work.

Result: The proposed methods reduce the time complexity for brain tumor detection which also includes more accuracy.

Conclusion: In this research work the MRI brain image is considered as input. The end users themselves examine the MRI report by normal vitalization without consulting a radiologist.