Middle pages
- 1. An efficient Brain Tumor Extraction from MRI Images using Entropy Measures 2014-15 Poornima University, Jaipur M. Tech. (Computer Engineering) Page ii CERTIFICATE This is to certify that Deepika Joshi, Registration No. 2013PUSETMCEX02345, student of M. Tech. in Computer Engineering branch, Department of Computer Engineering, School of Engineering & Technology has submitted this dissertation entitled “An efficient Brain Tumor Extraction from MRI Images using Entropy Measures” under the supervision of Mr. Devendra Kumar Somwanshi, Assistant Professor, Department of Computer Engineering, Poornima University towards partial fulfillment of the requirements for the Degree of M. Tech. from the Poornima University. Dr. Mahesh Bundele Dr. Manoj Gupta Dean, Research & Development Dean, SET
- 2. An efficient Brain Tumor Extraction from MRI Images using Entropy Measures 2014-15 Poornima University, Jaipur M. Tech. (Computer Engineering) Page iii CANDIDATE’S DECLARATION I hereby declare that the work which is being presented in this dissertation entitled, “An efficient Brain Tumor Extraction from MRI Images using Entropy Measures” in the partial fulfillment for the award of the Degree of Master of Technology in Computer Engineering branch, Department of Computer Engineering, School of Engineering & Technology, Poornima University, Jaipur, is an authentic record of original work done by me during the period from January, 2015 to July, 2015 under the supervision and guidance of Mr. Devendra Kumar Somwanshi, Assistant Professor, Department of Computer Engineering, Poornima University. I have not submitted the matter embodied in this dissertation for the award of any other degree. Dated: Deepika Joshi Place: Jaipur 2013PUSETMCSX02345 SUPERVISOR’S CERTIFICATE This is to certify that this dissertation is based on original work done by the candidate under my supervision and to the best of my knowledge; this work has not been submitted elsewhere for the award of any degree. Dated: Mr. Devendra Kumar Somwanshi Place: Jaipur Assistant Professor Department of Computer Engineering
- 3. An efficient Brain Tumor Extraction from MRI Images using Entropy Measures 2014-15 Poornima University, Jaipur M. Tech. (Computer Engineering) Page iv ACKNOWLEDGEMENT I would like to express my deep gratitude and thanks to my Guide Mr. Devendra Kumar Somwanshi, Assistant Professor, Department of Computer Engineering, Poornima University for giving me an opportunity to work under his guidance for my Dissertation Work. I would also express my sincere thanks to Dr. Mahesh Bundele, Dean, Research and Development, Poornima University, for his consistent motivation & direction in this regard for his support in Dissertation Work. I extend my deep sense of gratitude and respect towards honorable Dr. S. M. Seth, Chairperson, Poornima University and Chairman, Poornima Foundation for his continuous inspiration and motivation for the research. I would like to express my deep gratitude to Dr. K. K. S. Bhatia, President, Poornima University for his kind support and guidance from time to time. My sincere thanks are due to Mr. Shashikant Singhi, Secretary, Shanti Education Society & Director General, Poornima Foundation, who has established Poornima University and given us an opportunity to undergo research work in this university. I extend my sincere thanks to Dr. Manoj Gupta, Provost and Dean (SET and SBA), Poornima University for his continuous support and encouragements throughout the course work of my Master program. I would like to express my sincere thanks to Dr. Chandni Kirplani, Registrar, Poornima University for her support. Deepika Joshi
- 4. An efficient Brain Tumor Extraction from MRI Images using Entropy Measures 2014-15 Poornima University, Jaipur M. Tech. (Computer Engineering) Page v ABSTRACT Magnetic Resonance Imaging (MRI) is increasingly being used in medical field because of its ability to produce, non-invasively, high quality images of the inside of the human body. Since its introduction in early 70’s, more and more complex acquisition techniques have been proposed, raising MRI to be exploited in a wide spectrum of applications. Medical imaging seeks to reveal internal structures hidden by the skin and bones, as well as to diagnose and treat disease. In that way, MRI has become a useful medical diagnostic tool for the diagnosis of brain and other medical images. Brain Tumor extraction and its analysis are challenging tasks in medical image processing because brain image is complicated. Detection of brain tumor is one of the emerging topics of research in biomedical image processing. Accurate detection is critical, especially when the tumor morphological changes remain subtle, irregular and difficult to assess by clinical examination. Brain Tumor is one of the frequent and leading causes of mortality, especially in developed countries. Though brain tumor leads to death, early detection can increase the survival rate. In this dissertation work the main emphasis laid on to design an approach, which is a detection technique so that the proposed effectively detects and diagnose the tumor in their early stage. In this the threshold selection is done on the basis of different entropy measures such as Shannon, Renyi, Havrda-Charvat, Kapur and Vajda entropy measures that has been used in order to detect the Brain Tumor from MRI Images. Simulation results for different entropy measures are also presented. At the end of the process tumor is extracted from the MRI images and its exact position and shape are determined and various parameters like contrast, angular momentum and entropy value have been calculated. Here an efficient detection of brain tumor has been introduced and it has been observed that Havrda Charvat Entropy measure provides satisfactory results in early detection of Brain Tumor. The proposed work has been applied on MRI Images in order to get more clear and enhanced picture of the Tumor for its early detection. Thus the developed approach is introduced to solve the problem for tumor case of clinical MRI analysis and extracted the size and other dimensions of tumor automatically by accurately computing the abnormal tissue areas.
- 5. An efficient Brain Tumor Extraction from MRI Images using Entropy Measures 2014-15 Poornima University, Jaipur M. Tech. (Computer Engineering) Page vi TABLE OF CONTENTS Cover Page i Certificate ii Candidate’s Declaration iii Supervisor’s Certificate iii Acknowledgement iv Abstract v Table of contents vi-ix List of tables x… List of Figures xi-xii List of Acronyms xiii Chapter 1 Introduction 1-10 1.1 Brain Anatomy Overview 1 1.1.1 Brainstem 2 1.1.2 Cerebellum 2 1.1.3 Frontal Lobe 2 1.1.4 Occipital Lobe 2 1.1.5 Parietal Lobe 2 1.1.6 Temporal Lobe 3 1.2 Brain tumors 3 1.3 MRI Images 4 1.4 The Image Segmentation 6 1.5 Application of Image Segmentation 6 1.5.1 Content Based Image Retrieval 6 1.5.2 Machine Vision 7 1.5.3 Medical Imaging 7 1.5.4 Object Detection 7 1.6 Introduction to Brain Tumor Segmentation 8 1.7 Difficulties in segmentation of Brain MRI 8 1.8 Thresholding 8
- 6. An efficient Brain Tumor Extraction from MRI Images using Entropy Measures 2014-15 Poornima University, Jaipur M. Tech. (Computer Engineering) Page vii 1.10 Thresholding Algorithm 9 1.10.1 Global thresholding algorithms 9 1.10.2 Local or adaptive thresholding algorithms 9 1.11 Thresholding Methods 9 1.11.1 Histogram Shape-Based Methods 9 1.11.2 Clustering Based Methods 9 1.11.3 Entropy Based Methods 9 1.11.4 Object Attribute-Based Methods 10 1.11.5 Spatial Methods 10 1.11.6 Local Methods 10 Chapter 2 Literature Review 11-34 2.1 Review Process Adopted 11 2.1.1 Stage 0: Get a “feel” 12 2.1.2 Stage 1: Get a “picture” 12 2.1.3 Stage 2: Get the “details” 13 2.1.4 Stage 3: “Evaluate the details” 13 2.1.5 Stage 3+: “Synthesize the detail” 13 2.2 Categorical Reviews in An efficient Brain Tumor extraction from MRI Images using Entropy Measures 14 2.2.1 Review outcome in the issue 13 2.2.2 Common findings obtained in the issue 26 2.3 Issue wise solution approaches 27 2.4 Strengths and weaknesses 32 2.4.1 Strengths 32 2.4.2 Weaknesses 33 2.5 Gaps 34 2.6 Problem Statement 34 2.7 Objectives 34 Chapter 3 Theoretical Aspects 36-39 3.1 Classification of Image Segmentation 36 3.1.1 Thresholding Method 37
- 7. An efficient Brain Tumor Extraction from MRI Images using Entropy Measures 2014-15 Poornima University, Jaipur M. Tech. (Computer Engineering) Page viii 3.1.2 Edge Based Segmentation Method 37 3.1.3Region Based Segmentation Method 38 3.1.4 Clustering Based Segmentation Method 38 3.1.5 Watershed Based Segmentation Method 38 3.1.6 Partial Differential Equation Based Segmentation Method 39 3.1.7 Artificial Neural Network Based Segmentation Method 3.1.8 Comparison of various segmentation technique 39 3.2 Entropy Measures 39 Chapter 4 Design aspects of Proposed Work 44-55 4.1 System Design of the work 44 4.1.1 Input Image 44 4.1.2 Preprocessing 45 4.1.3 Feature Extraction 45 4.1.4 Segmentation 45 4.1.5 Entropy Calculation 46 4.1.6 Diagnosis 46 4.2 Details of data used 46 4.3 Design and Implementation of the work carried out 47 4.3.1 Algorithm 47 4.3.2 Process Flow Diagram 47 4.3.2.1 Flow chart for Shannon Entropy 49 4.3.2.2 Flow chart for Renyi Entropy 50 4.3.2.3 Flow chart for Havrda-Charvat Entropy 51 4.3.2.4 Flow chart for Kapur Entropy 52 4.3.2.5 Flow chart for Vajda Entropy 53 4.4 Details of Software 54 4.4.1 Software Specification 54 4.5 Details of Performance Parameters 54 4.5.1 Contrast 54
- 8. An efficient Brain Tumor Extraction from MRI Images using Entropy Measures 2014-15 Poornima University, Jaipur M. Tech. (Computer Engineering) Page ix 4.5.2 Homogeneity 54 4.5.3 Dissimilarity 55 4.5.4 Entropy 55 Chapter 5 Experimental Results and Analysis 56-74 5.1 Experimental Results and discussions 56 5.2 Result Analysis 64 5.3 Future Work 73 Chapter 6 Conclusion 75 References 77-79
- 9. An efficient Brain Tumor Extraction from MRI Images using Entropy Measures 2014-15 Poornima University, Jaipur M. Tech. (Computer Engineering) Page x LIST OF TABLES Table No. Table Name Page No. 2.1 Stage 2 questions along with probable location of answers in the papers 10 2.3 Categorical Review of Research Paper 26 2.4 Comparison of different Entropy Measures 30 3.1 Comparison of various Segmentation Techniques 38 5.1 To Perform Shannon Entropy 56 5.2 To Perform Vajda Entropy 58 5.3 To perform Kapur Entropy 60 5.4 To perform Renyi Entropy 62 5.5 To perform Havrda-Charvat Entropy 64 5.6 Result analysis using different entropies 66 5.7 Result Analysis through different MRI Images 67 5.8 Texture Feature of different MRI Images for Shannon Entropy 68 5.9 Texture Feature of different cases for Renyi Entropy 69 5.10 Texture Feature of different cases for Kapur Entropy 70 5.11 Texture Feature of different cases for Vajda Entropy 70 5.12 Texture Feature of different cases for Havrda-Charvat Entropy 70 5.13 Data Analysis of different Entropy Function 71
- 10. An efficient Brain Tumor Extraction from MRI Images using Entropy Measures 2014-15 Poornima University, Jaipur M. Tech. (Computer Engineering) Page xi LIST OF FIGURES Figure No. Figure Caption Page No. 1.1 Subdivision of Human Brain 2 1.3 Clinical Diagnosis of patient’s head 5 1.4 Three planes of clinical diagnosis 5 2.1 Review Process Stage Analysis 12 3.1 Image Segmentation Techniques 36 4.1 System Block Diagram 44 4.2 Process flow diagram 47
- 11. An efficient Brain Tumor Extraction from MRI Images using Entropy Measures 2014-15 Poornima University, Jaipur M. Tech. (Computer Engineering) Page xii LIST OF ACRONYMS CI Computational Intelligence CNN Cellular Neural Network CT Computed Tomography CPU Central Processing unit EEG Electroencephalograms GA Genetic Algorithms GFO Generalized Fuzzy Operator HSOM Hierarchical Self Organizing Map HTTP Hyper Text Markup Language IKFCM Improved Kernel Fuzzy C-Means I/O Input /Output MA Monitoring Agent MRI Magnetic Resonance Imaging OLTP Online Transaction Processing Test PDI Provable Data Integrity PET Positron Emission Tomography PSO Particle Swarm Optimization SLA Service Level Agreement SVM Support Vector Machine SWA Segmented Weighted Aggregation TCCP Trusted Cloud Computing Platform TLS Transport level security TMR Triple Modular Redundancy TTP Trusted Third Party