Please use this identifier to cite or link to this item: http://hdl.handle.net/10603/313408
Title: Brain Tumor Detection and Classification Using Machine Learning and Soft Computing Techniques from Magnetic Resonance Images
Researcher: Sahu, Premananda
Guide(s): Mishra, Satyasis and Senapati, Manas Ranjan
Keywords: Brain Tumor Detection,
Brain Tumor Detection, Classification, Segmentation, Feature Extraction, Machine Learning, Magnetic Resonance image
Classification,
Feature Extraction,
Machine Learning
Segmentation,
University: Centurion University of Technology and Management
Completed Date: 2020
Abstract: The domain of image processing provides unique functionalities and its applicability in biomedical imaging. The manual detection and classification of the tumor becomes a rigorous and hectic task for the radiologists. The extraction of infected tumor area from magnetic resonance (MR) images is a tedious and time taking task performed by radiologists or clinical experts. To ameliorate the performance and abbreviate the intricacy involved in the image segmentation process, the FCM predicated image segmentation processes are investigated in this research work. Furthermore, to improve the precision and quality rate of the neural network classifier, germane features are extracted from each segmented tissue and aligned as input to the classifiers for automatic detection and relegation of encephalon tumors. The experimental performance of proposed technique has been evaluated, validated and presented. newlineThis research work presents an automatic detection and classification of brain tumor using a novel APSO (Accelerated Particle Swarm Optimization) predicated LLRBFNN model for relegation of Benign and Malignant tumors. The proposed LLRBFNN model parameters are optimized by utilizing APSO training which will provide unique solution to mitigation the hectic task of radiologist from manual detection of encephalon tumors from MR Images. Additionally, the centers of the LLRBFNN model are culled by the Enhanced FCM algorithm and updated by the APSO algorithm. The results of proposed APSO-LLRBFNN model has been compared with PSO-LLRBFNN model, APSO-RBFNN and PSO-RBFNN model and the comparison results are presented. APSO Based LLWNN (Local Linear Wavelet Neural Network) model has been proposed for automatic brain tumor classification to show the robustness of the classification model. The Improved Enhanced fuzzy c means (IEnFCM) algorithm has been proposed for image segmentation and the GLCM (Gray Level Co-occurrence Matrix) feature extraction technique has been used for feature extraction from MR images.
Pagination: 3.9MB
URI: http://hdl.handle.net/10603/313408
Appears in Departments:Computer Sc. and Enggineering

Files in This Item:
File Description SizeFormat 
80_recommendation.pdfAttached File443.67 kBAdobe PDFView/Open
certificate.pdf254.75 kBAdobe PDFView/Open
chapter 1.pdf287.47 kBAdobe PDFView/Open
chapter 2.pdf428.55 kBAdobe PDFView/Open
chapter 3.pdf1.31 MBAdobe PDFView/Open
chapter 4.pdf757.95 kBAdobe PDFView/Open
chapter 5.pdf973.11 kBAdobe PDFView/Open
chapter 6.pdf1.62 MBAdobe PDFView/Open
chapter 7.pdf279.92 kBAdobe PDFView/Open
preliminary pages.pdf701.29 kBAdobe PDFView/Open
title page.pdf168.54 kBAdobe PDFView/Open


Items in Shodhganga are protected by copyright, with all rights reserved, unless otherwise indicated.

Altmetric Badge: