Automatic Detection and Classification of Malarial Retinopathy- Associated Retinal Whitening in Digital Retinal Images

Abstract

Malarial retinopathy addresses diseases that are characterized by abnormalities in retinal fundus imaging. Macular whitening is one of the distinct signs of cerebral malaria but has hardly been explored as a critical bio-marker. The paper proposes a computerized detection and classification method for malarial retinopathy using retinal whitening as a bio-marker. The paper combines various statistical and color based features to form a sound feature set for accurate detection of retinal whitening. All features are extracted at image level and feature selection is performed to detect most discriminate features. A new method for macula location is also presented. The detected macula location is further used for grading of whitening as macular or peripheral whitening. Support vector machine along with radial basis function is used for classification of normal and malarial retinopathy patients. The evaluation is performed using a locally gathered dataset from malarial patients and it achieves an accuracy of 95% for detection of retinal whitening and 100% accuracy for grading of retinal whitening as macular or non-macular. One of the major contributions of proposed method is grading of retinal whitening into macular or peripheral whitening.

Authors and Affiliations

M. U. Akram, A. B. N. Alvi, S. A. Khan

Keywords

Related Articles

Routine of Encryption in Cognitive Radio Network

Today data transmission is very important through different channels. Need of network security comes to secure data transformation from one network to another network. As the complexity of the systems and the networks in...

Adaptation of Information Quality and Assurance Management Paradigm in a Strategic Public Sector Organization

Information quality despite being a critical area in organizations lacks in comprehensive methodologies for its adaptation and improvement even after years of active research and practice. Therefore adaptation of informa...

A Family of 2n-Point Ternary Non-Stationary Interpolating Subdivision Scheme

This article offers 2n-point ternary non-stationary interpolating subdivision schemes, with the tension parameter, by using Lagrange identities. By choosing the suitable value of tension parameter, we can get different l...

Assessing the Removal of Turbidity and Coliform Transport through Canal-Bed Sediment at Lab-Scale: Column Experiments

This study was conducted at lab scale to determine the performance of the canal-bed for the removal of turbidity and microorganisms TC (Total Coliforms) from surface water. The canal-bed sediments were collected and anal...

Individual and Organizational Impact of Enterprises Resources Planning System in Healthcare Sector

Use of ERPS (Enterprise Resource Planning System) in healthcare sector has positive impacts. The purpose of this research is to find out the individual and organizational impact in healthcare sector. Hypotheses were post...

Download PDF file
  • EP ID EP226285
  • DOI 10.22581/muet1982.1704.19
  • Views 100
  • Downloads 0

How To Cite

M. U. Akram, A. B. N. Alvi, S. A. Khan (2017). Automatic Detection and Classification of Malarial Retinopathy- Associated Retinal Whitening in Digital Retinal Images. Mehran University Research Journal of Engineering and Technology, 36(4), 941-956. https://europub.co.uk/articles/-A-226285