Abstract
Aim: Alzheimer’s disease patients are increasing rapidly every year. Scholars tend to use computer vision methods to develop automatic diagnosis system. (Background) In 2015, Gorji et al. proposed a novel method using pseudo Zernike moment. They tested four classifiers: learning vector quantization neural network, pattern recognition neural network trained by Levenberg-Marquardt, by resilient backpropagation, and by scaled conjugate gradient.
Method: This study presents an improved method by introducing a relatively new classifier—linear regression classification. Our method selects one axial slice from 3D brain image, and employed pseudo Zernike moment with maximum order of 15 to extract 256 features from each image. Finally, linear regression classification was harnessed as the classifier. Results: The proposed approach obtains an accuracy of 97.51%, a sensitivity of 96.71%, and a specificity of 97.73%. Conclusion: Our method performs better than Gorji’s approach and five other state-of-the-art approaches. Therefore, it can be used to detect Alzheimer’s disease.Keywords: Linear regression classifier, machine learning, pathological brain detection, pattern recognition.
Graphical Abstract
CNS & Neurological Disorders - Drug Targets
Title:A Feature-Free 30-Disease Pathological Brain Detection System by Linear Regression Classifier
Volume: 16 Issue: 1
Author(s): Yi Chen, Ying Shao, Jie Yan, Ti-Fei Yuan, Yanwen Qu, Elizabeth Lee and Shuihua Wang
Affiliation:
Keywords: Linear regression classifier, machine learning, pathological brain detection, pattern recognition.
Abstract: Aim: Alzheimer’s disease patients are increasing rapidly every year. Scholars tend to use computer vision methods to develop automatic diagnosis system. (Background) In 2015, Gorji et al. proposed a novel method using pseudo Zernike moment. They tested four classifiers: learning vector quantization neural network, pattern recognition neural network trained by Levenberg-Marquardt, by resilient backpropagation, and by scaled conjugate gradient.
Method: This study presents an improved method by introducing a relatively new classifier—linear regression classification. Our method selects one axial slice from 3D brain image, and employed pseudo Zernike moment with maximum order of 15 to extract 256 features from each image. Finally, linear regression classification was harnessed as the classifier. Results: The proposed approach obtains an accuracy of 97.51%, a sensitivity of 96.71%, and a specificity of 97.73%. Conclusion: Our method performs better than Gorji’s approach and five other state-of-the-art approaches. Therefore, it can be used to detect Alzheimer’s disease.Export Options
About this article
Cite this article as:
Chen Yi, Shao Ying, Yan Jie, Yuan Ti-Fei, Qu Yanwen, Lee Elizabeth and Wang Shuihua, A Feature-Free 30-Disease Pathological Brain Detection System by Linear Regression Classifier, CNS & Neurological Disorders - Drug Targets 2017; 16 (1) . https://dx.doi.org/10.2174/1871527314666161124115531
DOI https://dx.doi.org/10.2174/1871527314666161124115531 |
Print ISSN 1871-5273 |
Publisher Name Bentham Science Publisher |
Online ISSN 1996-3181 |
- 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
-
Emerging Role of Bone Morphogenetic Proteins as a Context Dependent Pro-Angiogenic Cue
Current Angiogenesis (Discontinued) From Cerebrospinal Fluid Pulsation to Noninvasive Intracranial Compliance and Pressure Measured by MRI Flow Studies
Current Medical Imaging Activin Receptor-Like Kinase 1: a Novel Anti-angiogenesis Target from TGF-β Family
Mini-Reviews in Medicinal Chemistry HHT in Childhood: Screening for Special Patients
Current Pharmaceutical Design Ruptured Multiple Mycotic Aneurysms Following Infective Endocarditis: Effectiveness of Catheter-based Techniques Using N-butyl Cyanoacrylate in a Hemorrhage-induced Coagulopathy
Current Medical Imaging Von Willebrand Factor and Cardiovascular Disease: From a Biochemical Marker to an Attractive Therapeutic Target
Current Vascular Pharmacology Impact of Pulmonary Vascular Resistances in Heart Transplantation for Congenital Heart Disease
Current Cardiology Reviews Syncope in a Child with Pulmonary Hypertension and Positive Gene Tests for Hereditary Hemorrhagic Telangiectasia and Long QT Syndrome
Cardiovascular & Hematological Agents in Medicinal Chemistry Hereditary Haemorrhagic Telangiectasia: A Rare Disease As A Model for the Study of Human Atherosclerosis
Current Pharmaceutical Design Benign Intracranial Lesions - Radiotherapy: An Overview of Treatment Options, Indications and Therapeutic Results
Reviews on Recent Clinical Trials Editorial [Hot Topic: Molecular and Clinical Aspects of Hereditary Hemorragic Telangiectasia: A Rare Disease Executive Editor: (Emilo Jirillo)]
Current Pharmaceutical Design Current Status of Renal Arterial Endovascular Interventions
Current Hypertension Reviews Antiepileptic Drug Monotherapy: The Initial Approach in Epilepsy Management
Current Neuropharmacology Regulation of Angiogenesis by the Small Heat Shock Protein αB-Crystallin
Current Angiogenesis (Discontinued) Injecting Illicit Substances Epidemic and Infective Endocarditis
Infectious Disorders - Drug Targets Ultrasound Diagnosis of Soft Tissue Vascular Malformations and Tumours
Current Medical Imaging bmp3 is Required for Integrity of Blood Brain Barrier by Promoting Pericyte Coverage in Zebrafish Embryos
Current Molecular Medicine Advanced Techniques for Imaging the Human Spinal Cord: Review of Literature
Current Medical Imaging Pathophysiology of the Vascular Wall and its Relevance for Cerebrovascular Disorders in Aged Rodents
Current Neurovascular Research The Role of MDCT in Craniocervical Junction Pathologies: Pictorial Review
Current Medical Imaging