Abstract
This paper presents an automatic classification system for segregating pathological brain from normal brains in magnetic resonance imaging scanning. The proposed system employs contrast limited adaptive histogram equalization scheme to enhance the diseased region in brain MR images. Two-dimensional stationary wavelet transform is harnessed to extract features from the preprocessed images. The feature vector is constructed using the energy and entropy values, computed from the level- 2 SWT coefficients. Then, the relevant and uncorrelated features are selected using symmetric uncertainty ranking filter. Subsequently, the selected features are given input to the proposed AdaBoost with support vector machine classifier, where SVM is used as the base classifier of AdaBoost algorithm. To validate the proposed system, three standard MR image datasets, Dataset-66, Dataset-160, and Dataset- 255 have been utilized. The 5 runs of k-fold stratified cross validation results indicate the suggested scheme offers better performance than other existing schemes in terms of accuracy and number of features. The proposed system earns ideal classification over Dataset-66 and Dataset-160; whereas, for Dataset- 255, an accuracy of 99.45% is achieved.
Keywords: AdaBoost with SVM, computer-aided diagnosis, contrast limited adaptive histogram equalization, magnetic resonance imaging, stationary wavelet transform.
CNS & Neurological Disorders - Drug Targets
Title:Stationary Wavelet Transform and AdaBoost with SVM Based Pathological Brain Detection in MRI Scanning
Volume: 16 Issue: 2
Author(s): Deepak Ranjan Nayak, Ratnakar Dash and Banshidhar Majhi
Affiliation:
Keywords: AdaBoost with SVM, computer-aided diagnosis, contrast limited adaptive histogram equalization, magnetic resonance imaging, stationary wavelet transform.
Abstract: This paper presents an automatic classification system for segregating pathological brain from normal brains in magnetic resonance imaging scanning. The proposed system employs contrast limited adaptive histogram equalization scheme to enhance the diseased region in brain MR images. Two-dimensional stationary wavelet transform is harnessed to extract features from the preprocessed images. The feature vector is constructed using the energy and entropy values, computed from the level- 2 SWT coefficients. Then, the relevant and uncorrelated features are selected using symmetric uncertainty ranking filter. Subsequently, the selected features are given input to the proposed AdaBoost with support vector machine classifier, where SVM is used as the base classifier of AdaBoost algorithm. To validate the proposed system, three standard MR image datasets, Dataset-66, Dataset-160, and Dataset- 255 have been utilized. The 5 runs of k-fold stratified cross validation results indicate the suggested scheme offers better performance than other existing schemes in terms of accuracy and number of features. The proposed system earns ideal classification over Dataset-66 and Dataset-160; whereas, for Dataset- 255, an accuracy of 99.45% is achieved.
Export Options
About this article
Cite this article as:
Nayak Ranjan Deepak, Dash Ratnakar and Majhi Banshidhar, Stationary Wavelet Transform and AdaBoost with SVM Based Pathological Brain Detection in MRI Scanning, CNS & Neurological Disorders - Drug Targets 2017; 16 (2) . https://dx.doi.org/10.2174/1871527315666161024142036
DOI https://dx.doi.org/10.2174/1871527315666161024142036 |
Print ISSN 1871-5273 |
Publisher Name Bentham Science Publisher |
Online ISSN 1996-3181 |
Call for Papers in Thematic Issues
Diagnosis and treatment of central nervous system infectious diseases
Infectious diseases of the central nervous system (CNS) can be divided into bacterial, tuberculous, viral, fungal, parasitic infections, etc. Early etiological treatment is often the most crucial means to reduce the mortality rate of patients with central nervous system infections, reduce complications and sequelae, and improve prognosis. The initial clinical ...read more
Techniques of Drug Repurposing: Delivering a new life to Herbs & Drugs
Of late, with the adaptation of innovative approaches and integration of advancements made towards medical sciences as well as the availability of a wide range of tools; several therapeutic challenges are being translated into viable clinical solutions, with a high degree of efficacy, safety, and selectivity. With a better understanding ...read more
Trends and perspectives in the rational management of CNS disorders
Central nervous system (CNS) diseases enforce a significant global health burden, driving ongoing efforts to improve our understanding and effectiveness of therapy. This issue investigates current advances in the discipline, focusing on the understanding as well as therapeutic handling of various CNS diseases. The issue covers a variety of diseases, ...read more
- Author Guidelines
- Graphical Abstracts
- Fabricating and Stating False Information
- Research Misconduct
- Post Publication Discussions and Corrections
- Publishing Ethics and Rectitude
- Increase Visibility of Your Article
- Archiving Policies
- Peer Review Workflow
- Order Your Article Before Print
- Promote Your Article
- Manuscript Transfer Facility
- Editorial Policies
- Allegations from Whistleblowers
Related Articles
-
A Comparative Study of Two Novel Nanosized Radiolabeled Analogues of Methionine for SPECT Tumor Imaging
Current Medicinal Chemistry Structure Prediction of Neuroendocrine Convertase -2: A Potential Target in Various Cancers
Protein & Peptide Letters Role of Resveratrol in Modulating microRNAs in Human Diseases: From Cancer to Inflammatory Disorder
Current Medicinal Chemistry Cannabis sativa L. Constituents and Their Role in Neuroinflammation
Current Bioactive Compounds Signal Transduction Therapy for Cancer - Whither Now?
Current Signal Transduction Therapy T Cell Costimulatory and Inhibitory Receptors as Therapeutic Targets for Inducing Anti-Tumor Immunity
Current Cancer Drug Targets Recent Advances on Glioblastoma Multiforme and Nano-drug Carriers: A Review
Current Medicinal Chemistry Azole Antimycotics - A Highway to New Drugs or a Dead End?
Current Medicinal Chemistry Relevance of the Deletion Polymorphisms of the Glutathione S-Transferases GSTT1 and GSTM1 in Pharmacology and Toxicology
Current Drug Metabolism Passive Targeting of Cyclophosphamide-Loaded Carbonate Apatite Nanoparticles to Liver Impedes Breast Tumor Growth in a Syngeneic Model
Current Pharmaceutical Design Class II Phosphoinositide 3-Kinases as Potential Novel Drug Targets
Current Signal Transduction Therapy Pharmacodynamics of Radiolabelled Anticancer Drugs for Positron Emission Tomography
Current Pharmaceutical Design Mutant Cell Surface Receptors as Targets for Individualized Cancer Diagnosis and Therapy
Current Cancer Drug Targets Hyperpolarized 13Carbon MR
Current Pharmaceutical Biotechnology Targeted Ultrasound Imaging of Cancer: An Emerging Technology on its Way to Clinics
Current Pharmaceutical Design Semaphorins at the Interface of Development and Cancer
Current Drug Targets Epigenetics in Brain Tumors: HDACs Take Center Stage
Current Neuropharmacology Human Immunodeficiency Virus-Mononuclear Phagocyte Interactions:Emerging Avenues of Biomarker Discovery, Modes of Viral Persistence and Disease Pathogenesis
Current HIV Research An Update of the Classical and Novel Methods Used for Measuring Fast Neurotransmitters During Normal and Brain Altered Function
Current Neuropharmacology Encapsulation of Imatinib in Targeted KIT-5 Nanoparticles for Reducing its Cardiotoxicity and Hepatotoxicity
Anti-Cancer Agents in Medicinal Chemistry