A PHP Error was encountered

Severity: Notice

Message: Undefined offset: 1

Filename: views/ijrpetpaper.php

Line Number: 60


File: /home/journaln/public_html/application/views/ijrpetpaper.php
Line: 60
Function: _error_handler

File: /home/journaln/public_html/application/controllers/JournalNXpaper.php
Line: 24
Function: view

File: /home/journaln/public_html/index.php
Line: 315
Function: require_once


Volume 2, Issue 4


Authors :
Abstracts : The brain is the most important part of the central nervous system. The structure and function of the brain need to be studied non-invasively by researchers and medical practitioners using MRI imaging techniques. The body is formed by number of different types of cells. Each type of cell has special functions. When cells lose the ability to control their growth, they divide too often and without following any law. The extra cells form a mass of tissue called a tumour. MRI acts as an assistant diagnostic tool for the medical practitioners during disease diagnosis and treatment. This imaging modality produces images of soft tissues using MRI technique. The acquired medical images show the internal structure, but the medical practioners want to know more than peer images, such as emphasizing the abnormal tissue, quantifying its size, depicting its shape, and soon. If such tasks are covered by the medical practioners themselves, it may be inaccurate, time consuming and burden them heavily. Segmentation is an vital process for extraction of suspicious region from complex medical images. This increase time to reach the optimal solution in order to accelerate the segmentation process an application specific knowledge is used to initialize the centres of required clusters. There are no standard image segmentation techniques that can reliable results for all imaging applications like brain MRI, brain cancer diagnosis etc. An integrated k-means clustering algorithm with watershed and optimized k-means and c-mean clustering algorithm is used to overcome some segmentation problem. It will help to detect the brain tumour and thereby help the medical practioners for analyzing tumour size and region [1].
Pages :
Downloads : 27
Publication Date :
Modified Date : 2016-04-25
Urmila Ravindra Patil , Prof. R. T. Patil , "A REVIEW OF COMPUTER AIDED DIAGNOSTIC SYSTEM FOR BRAIN TUMOUR DETECTION USING K-MEANS CLUSTERING", JournalNX - A Multidisciplinary Peer Reviewed Journal, Volume 2, Issue 4, ISSN : 2581-4230, Page No.
Peer reviewed