Automatic Brain Tumor Detection in MR Images Using Neural Network Based Classification

Journal Title: International Journal of Scientific Research and Management - Year 2013, Vol 1, Issue 2

Abstract

This paper presents a neural network - based te chnique for automatic classification of magnetic resonance images (MRI) of the brain in two categories of benign, and malignant. The proposed method consists of five following stages; i.e., preprocessing, connected component labeling (CCL), fuzzy connected ness segmentation, feature extraction using DWT and classification using RBF and SVM respectively. Preprocessing involves removing low - frequency surroundings noise, normalize the intensity of the individual particles images, remove reflections, and masking portions of images. Anisotropic filter is used to remove the background noise and thus preserving the edge points in the image. In the third stage, once all groups dogged, each pixel is labeled according to the element to which it is assigned to. In the third stage, the fuzzy Connectedness segmentation is used for partitioning the image into meaningful regions. have been In the fourth stage, the obtained feature connected to MRI images using the discrete wavelet transform (DWT).In the classification stage , the RBF kernel and SVM is used to classify the subjects to normal or abnormal (benign, malignant) and Level set method is used for automatic detection and segmentation of Meningioma and glioma tumor. The proposed technique gives high - quality results for brain tissue detection and is more robust and efficient compared with other recent works.

Authors and Affiliations

C. Ramalakshmi

Keywords

Related Articles

Experimental Analysis of the Cutting Forces and Material Removal R ate during Dry Turning of En - 36 Steel

n the present case study, an attempt has been made to i nvestigate the effect of process parameters (cutting speed, feed rate and depth of cut) on axial force, radial force, main cutting force and material r emoval ra...

“A study on the perception of investment and the selection behavior of investors towards the mutual funds.

A Mutual Fund is a trust that pools the savings of a number of investors who share a common financial goal. The investment is the process of investing of money on an investment assets like shares, de...

Audio Signature in Graphical Password Authentication System

Graphical passwords, which consist of clicking or dragging activities on the pictures rather than typing textual characters, might be the op tion to overcome the problems that arise from the te...

Modified local tetra pattern based CBIR system

Content based image retrieval (CBIR) is a method of retrieving images from large image database, which has been found according to user’s interest. This paper repre sents high order local pattern...

Comparison of Turkish State Banks’ Performances via Multi - Criteria Performance Measurement Method

The banks are the most efficient aspects of countries. As efficiency and reliability of the banks increase, contributions of account owners to national economy increase as well. Increasing competitiveness and market sha...

Download PDF file
  • EP ID EP206421
  • DOI -
  • Views 162
  • Downloads 0

How To Cite

C. Ramalakshmi (2013). Automatic Brain Tumor Detection in MR Images Using Neural Network Based Classification. International Journal of Scientific Research and Management, 1(2), -. https://europub.co.uk./articles/-A-206421