DMCA
Testing of Brain Tumor Segmentation Using Hierarchal Self Organizing
BibTeX
@MISC{Net_testingof,
author = {Www. Iasir. Net and Dr. M. Anto Bennet and G. Sankar Babu and S. Lokesh and S. Sankaranarayanan},
title = {Testing of Brain Tumor Segmentation Using Hierarchal Self Organizing},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Abstract: A forceful segmentation tool for the detection of brain tumor is used to assist clinician and researchers in radio surgery applications. A clustering based approach using hierarchal self organizing map algorithm is proposed for MR image segmentation. Hierarchal self organizing map (HSOM) is a dynamically growing neural network model evolves into a hierarchical structure according to the requirements of the input data during an unsupervised training process. This algorithm proved to be exceptionally successful for data visualization applications. HSOM is the extension of the conventional self organizing map which is used to classify the image row by row. In this technique lowest level of weight vector, a higher value of tumor pixels and the computation speed is achieved by the HSOM with vector quantization. Hierarchal self organizing map (HSOM) segmentation is done in two phases: In the first phase MRI brain image is acquired from patient data base and the image is pre-processed where the noise is removed. In the second phase tumor present in the brain and the severances of the tumor is detected. Finally the numbers of affected cells are counted using the row and column wise scanning method. The proposed system uses HSOM. A self-organizing map (SOM) or self-organizing feature map (SOFM) is a type of artificial neural network for unsupervised learning. SOMs operate in two modes: training and mapping. Training is a competitive process, also called vector quantization. Mapping automatically classifies a new input vector. Segmentation is an important process to extract
Keyphrases
vector quantization computation speed competitive process input data radio surgery application neural network model patient data base image row weight vector map algorithm proposed system tumor pixel hierarchal self unsupervised learning brain tumor conventional self important process artificial neural network self-organizing map column wise first phase mri brain image data visualization application unsupervised training process new input vector second phase tumor present self-organizing feature map mr image segmentation affected cell forceful segmentation tool hierarchical structure
