Automated screening tool for dry and wet age-related maculardegeneration (ARMD) using pyramid of histogram of orientedgradients (PHOG) and nonlinear features

Acharya, Rajendra U and Hagiwara, Yuki and Koh, Joel E.W and Tan, Jen Hong and Bhandary, Sulatha V and Rao, Krishna A and Raghavendra, U (2017) Automated screening tool for dry and wet age-related maculardegeneration (ARMD) using pyramid of histogram of orientedgradients (PHOG) and nonlinear features. Journal of Computational Science, 20. pp. 41-51. ISSN 18777503

[img] PDF
2739.pdf - Published Version
Restricted to Registered users only

Download (2MB) | Request a copy
Official URL:


tAging is the prime cause of age-related macular degeneration (ARMD). There are primarily two typesof ARMD: (i) dry, and (ii) wet. The dry ARMD is the common form of ARMD. It typically starts with theformation of small pale yellowish deposits called drusen under the retina, causing atrophy at the macula,which is known as age-related macular degeneration. This, in turn, affects the central vision of a person.The wet ARMD is caused due to the abnormal growth of blood vessels under the retina. These vessels areknown as the choroidal neovascular membrane break through the retina and bleed. They finally lead toeither scarring at the macula or atrophic changes leading to severe visual impairment. Hence, the wetARMD progresses faster and leads to an irreversible loss of sight. Therefore, it is advisable to go for routineeye screening, especially for elderly subjects. Although the ARMD cannot be fully cured, an accurate earlydetection can impede the progression of vision loss. However, manual diagnosis of ARMD is difficult andsubjective. Thus, a computer-aided diagnosis (CAD) system can be utilized to automatically screen theeyes and give an accurate diagnosis of the type of ARMD. In this study, we propose a novel technique toidentify normal, dry, and wet ARMD. A total of 945 fundus images (404 normal, 517 dry ARMD, and 24wet ARMD) are used in this proposed framework. The Pyramid of Histograms of Orientation Gradients(PHOG) technique is implemented in this work to capture the subtle changes in the pixels of fundusimages. Various nonlinear features are extracted from the PHOG descriptor. To balance the number ofimages in three classes, an adaptive synthetic sampling (ADASYN) approach is used. Two feature selectiontechniques namely ant colony optimization genetic algorithm (ACO-GA) and particle swarm optimization(PSO) are used to select the best performing method. The selected features are subjected to analysis ofvariance (ANOVA) to determine highly significant features for classification. The proposed system hasachieved a maximum accuracy of 85.1%, sensitivity of 87.2%, and specificity of 80% using nine featuresselected by PSO feature selection method with support vector machine (SVM) classifier. It has obtaineda maximum accuracy of 83.3%, sensitivity of 82.6%, and specificity of 84.8% using ten features selectedby ACO-GA feature selection method with SVM classifier. The proposed CAD system yielded promisingperformance and thus, can be used as a practical adjunct ARMD screening tool in the clinical setting.

Item Type: Article
Uncontrolled Keywords: Age-related macular degenerationAnt colony optimization genetic algorithmFundus imageParticle swarm
Subjects: Engineering > MIT Manipal > Instrumentation and Control
Depositing User: MIT Library
Date Deposited: 27 Jun 2017 10:05
Last Modified: 27 Jun 2017 10:05

Actions (login required)

View Item View Item