Abstract
Background: Cotton-wool spots also referred as soft exudates are the early signs of complications in the eye fundus of the patients suffering from diabetic retinopathy. Early detection of exudates helps in the diagnosis of the disease and provides better medical attention.
Methods: In this paper, an automated system for the detection of soft exudates has been suggested. The system has been developed by the combination of different techniques like Scale Invariant Feature Transform (SIFT), Visual Dictionaries, K-means clustering and Support Vector Machine (SVM).
Results: The performance of the system is evaluated on a publically available dataset and AUC of 94.59% is achieved with the highest accuracy obtained is 94.59%. The experiments are also performed after mixing three datasets and AUC of 92.61% is observed with 91.94% accuracy.
Conclusion: The proposed system is easy to implement and can be used by medical experts both online and offline for referral of Cotton-wool spots in large populations. The system shows promising performance.
Keywords: Cotton-wool spots, diabetic retinopathy, eye fundus, SIFT, SVM, visual dictionary.
Current Diabetes Reviews
Title:Automated System for Referral of Cotton-Wool Spots
Volume: 14 Issue: 2
Author(s): Syed A.G. Naqvi*, Hafiz M.F. Zafar and Ihsan ul Haq
Affiliation:
- Department of Electronic Engineering, Faculty of Engineering and Technology, International Islamic University, Islamabad,Pakistan
Keywords: Cotton-wool spots, diabetic retinopathy, eye fundus, SIFT, SVM, visual dictionary.
Abstract: Background: Cotton-wool spots also referred as soft exudates are the early signs of complications in the eye fundus of the patients suffering from diabetic retinopathy. Early detection of exudates helps in the diagnosis of the disease and provides better medical attention.
Methods: In this paper, an automated system for the detection of soft exudates has been suggested. The system has been developed by the combination of different techniques like Scale Invariant Feature Transform (SIFT), Visual Dictionaries, K-means clustering and Support Vector Machine (SVM).
Results: The performance of the system is evaluated on a publically available dataset and AUC of 94.59% is achieved with the highest accuracy obtained is 94.59%. The experiments are also performed after mixing three datasets and AUC of 92.61% is observed with 91.94% accuracy.
Conclusion: The proposed system is easy to implement and can be used by medical experts both online and offline for referral of Cotton-wool spots in large populations. The system shows promising performance.
Export Options
About this article
Cite this article as:
Naqvi A.G. Syed*, Zafar M.F. Hafiz and ul Haq Ihsan, Automated System for Referral of Cotton-Wool Spots, Current Diabetes Reviews 2018; 14 (2) . https://dx.doi.org/10.2174/1573399812666161201114309
DOI https://dx.doi.org/10.2174/1573399812666161201114309 |
Print ISSN 1573-3998 |
Publisher Name Bentham Science Publisher |
Online ISSN 1875-6417 |
- 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
- Announcements
Related Articles
-
Risk Factors for Suicide – An Alternative View
CNS & Neurological Disorders - Drug Targets In Silico Studies in ADME/Tox: Caveat Emptor
Current Computer-Aided Drug Design From Adipose Tissue Protein Secretion to Adipopharmacology of Disease
Immunology, Endocrine & Metabolic Agents in Medicinal Chemistry (Discontinued) Effect of Alpha-1-Acid Glycoprotein Binding on Pharmacokinetics and Pharmacodynamics
Current Drug Metabolism Effect of Methylxanthine Derivatives on Doxorubicin Transport and Antitumor Activity
Current Drug Metabolism The Role of Growth Factors in the Prevention and Treatment of Chemotherapy-Induced Peripheral Neurotoxicity
Current Drug Safety MiRNA-145 and Its Direct Downstream Targets in Digestive System Cancers: A Promising Therapeutic Target
Current Pharmaceutical Design Design, Synthesis and In-vivo Hypoglycemic Evaluation of Novel Non - TZD’S in a Type - 2 Diabetic Model
Medicinal Chemistry Ovulation Inducing Agents and Cancer Risk: Review of Literature
Current Drug Safety Gonadal Hormones in Adolescent Females with β-Thalassemia in Relation to Iron Load
Endocrine, Metabolic & Immune Disorders - Drug Targets subject Index To Volume 2
Current Drug Targets - Infectious Disorders Role of the Endocannabinoid System in the Neuroendocrine Responses to Inflammation
Current Pharmaceutical Design Editorial (Thematic Issue: The Long Way to a Successful Medical Therapy of Heart Failure with Beta-blockers in Children with Heart Disease)
Reviews on Recent Clinical Trials Novel Methods of Insulin Replacement: The Artificial Pancreas and Encapsulated Islets
Reviews on Recent Clinical Trials Study of Antihyperglycemic, Antihyperlipidemic and Antioxidant Activities of Tannins Extracted from Warionia saharae Benth. & Coss
Endocrine, Metabolic & Immune Disorders - Drug Targets Drugs that Activate Specific Nitric Oxide Sensitive Guanylyl Cyclase Isoforms Independent of Nitric Oxide Release
Current Medicinal Chemistry Consumption of Cooked Navy Bean Powders Modulate the Canine Fecal and Urine Metabolome
Current Metabolomics Genetic, Epigenetic and Biological Effects of Zinc Transporter (SLC30A8) in Type 1 and Type 2 Diabetes
Current Diabetes Reviews Renal Effects Of The Lectin From Canavalia Brasiliensis Seeds
Protein & Peptide Letters Ligand Binding Domain of Vitamin D Receptors
Current Topics in Medicinal Chemistry