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
Heart and Brain Axis Targets in CNS Neurological Disorders
Recently there has been a surge of interest in delving deeper into the complex interplay between the heart and brain. This fascination stems from a growing recognition of the profound influence each organ holds over the other, particularly in the realm of central nervous system (CNS) neurological disorders. The purpose ...read more
Lifestyle Interventions to Prevent and Treat Cognitive Impairment and Dementia
More than 55 million people live with dementia worldwide. By 2050, the population affected by dementia will exceed 139 million individuals. Mild cognitive impairment (MCI) is a pre-dementia stage, also known as prodromal dementia, affecting older adults. MCI emerges years before the manifestation of dementia but can be avoidable and ...read more
Pathogenic Proteins in Neurodegenerative Diseases: From Mechanisms to Treatment Modalities
The primary objective of this thematic issue is to elucidate the molecular mechanisms by which pathogenic proteins contribute to neurodegenerative diseases and to highlight current and emerging therapeutic strategies aimed at mitigating their effects. By bringing together cutting-edge research and reviews, this issue aims to: 1.Enhance Understanding: Provide a comprehensive ...read more
Role of glial cells in autism spectrum disorder: Molecular mechanism and therapeutic approaches
Emerging evidence suggests that glial cells may play a pivotal role in neuroanatomical and behavioral changes found in autism spectrum disorder (ASD). Many individuals with ASD experience a neuro-immune system abnormalities throughout life, which implicates a potential role of microglia in the pathogenesis of ASD. Dysfunctional astrocytes and oligodendrocytes were ...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
-
Antineovascular Agents in the Treatment of Eye Diseases
Current Pharmaceutical Design Systems Cytogenomics: Are We Ready Yet?
Current Genomics Injectable Thermosensitive Chitosan/Glycerophosphate-Based Hydrogels for Tissue Engineering and Drug Delivery Applications: A Review
Recent Patents on Drug Delivery & Formulation Histone Variants and Composition in the Developing Brain: Should MeCP2 Care?
Current Topics in Medicinal Chemistry Endoplasmic Reticulum Stress and Bipolar Disorder - Almost Forgotten Therapeutic Drug Targets in the Unfolded Protein Response Pathway Revisited
CNS & Neurological Disorders - Drug Targets Perspectives of Protein Kinase C (PKC) Inhibitors as Anti-Cancer Agents
Mini-Reviews in Medicinal Chemistry Transductional and Transcriptional Targeting of Adenovirus for Clinical Applications
Current Gene Therapy Editorial [Hot Topic: Mechanisms of Drug Sensitivity and Resistance in Cancer (Guest Editor: Lorraine ODriscoll)]
Current Cancer Drug Targets Review of Selected Patents for Cancer Therapy Targeting Tumor Angiogenesis
Recent Patents on Anti-Cancer Drug Discovery Pharmacodynamics of Memantine: An Update
Current Neuropharmacology Hypoxic Radiosensitizers and Hypoxic Cytotoxins in Radiation Oncology
Current Medicinal Chemistry - Anti-Cancer Agents Role of Gap Junction Channel in the Development of Beat-to-Beat Action Potential Repolarization Variability and Arrhythmias
Current Pharmaceutical Design Clearing the Brains Cobwebs: The Role of Autophagy in Neuroprotection
Current Neuropharmacology Multiple Sclerosis, Gut Microbiota and Permeability: Role of Tryptophan Catabolites, Depression and the Driving Down of Local Melatonin
Current Pharmaceutical Design Clinical Applications and Biosafety of Human Adult Mesenchymal Stem Cells
Current Pharmaceutical Design Long Non-coding RNA DLGAP1-AS1 and DLGAP1-AS2: Two Novel Oncogenes in Multiple Cancers
Current Medicinal Chemistry Delivery and Application of Dietary Polyphenols to Target Organs, Tissues and Intracellular Organelles
Current Drug Metabolism Role of ABC Transporters in the Chemoresistance of Human Gliomas
Current Cancer Drug Targets Interfering with Hedgehog Pathway: New Avenues for Targeted Therapy in Rhabdomyosarcoma
Current Drug Targets DNA Methylation in Epithelial Ovarian Cancer: Current Data and Future Perspectives
Current Molecular Pharmacology