DETECTION AND CLASSIFICATION OF BRAIN TUMOR USING ML

Avirup Chowdhury

doi:10.26483/ijarcs.v9i2.5807

Abstract

Brain tumor detection and classification is the most difficult and tedious task in the area of medicinal image preparing. MRI (Magnetic Resonance Imaging) is a medicinal procedure, generally adopted by the radiologist for representation of inner structure of the human body with no surgery. MRI gives abundant data about the human delicate tissue, which helps in the conclusion of brain tumor. Precise segmentation of MRI image is basic for the conclusion of brain tumor by computer supported clinical device. After segmentation of brain MRI images, tumor is grouped to be either malignant or benign, which is a confounded task since complexity varies in proportion to the tumor tissue traits like its shape, size, gray level intensities and location. Taking into account the aforesaid challenges, this paper is focused towards the design of an optimal and more accurate way for the detection of tumor from brain MRI scans and if it confirms the presence of tumor then it is focused on evaluating its stage, i.e., benign or malignant. We have experimentally shown that our proposed methodology has a greater accuracy than other existent methods for classifying tumor type to be either as Malignant or Benign since the maximum accuracy for detection of malignant tumor is 99.02% and for Benign tumor is 99.67%.

Highlights

The human brain is the sensitive organ of the body which controls the other part of the body
In this paper, an optimal way for the detection of tumor from brain MRI scan has been devised which on successful detection classifies the type: benign or malignant
The entire procedure consists of four stages namely: anisotropic filtering, morphological operations, feature extraction and classification

Summary

INTRODUCTION

The human brain is the sensitive organ of the body which controls the other part of the body. When a portion of the brain develops to an unnatural size the work done by the brain get hampered and some of the time brains may stop its ordinary behavior This unusual enlargement of the brain cells is named as 'brain tumor' in medical science. The customary strategy for CT and MRI brain images grouping and tumor recognition are still for the most part in light of an immediate human investigation of those images, in spite their being various other diverse techniques have just been proposed[2,3]. MRI is a non-destructive and non-invasive strategy in nature It gives high-resolution images which are generally utilized as a part of brain scanning reason.

LITERATURE SURVEY

PROPOSED METHODOLOGY

Tumor Classification

EXPERIMENTAL RESULT

Findings

CONCLUSION