Automatic detection of peripapillary atrophy in retinal fundus images using statistical features. (August 2018)

• Record Type: Journal Article
• Authors: Septiarini, Anindita; Harjoko, Agus; Pulungan, Reza; Ekantini, Retno
• Is Part Of: Biomedical signal processing and control. Volume 45(2018)
• Page Start: 151
• Page End: 159
• Publication Date: 2018-08
• Subjects: Peripapillary atrophy -- Features extraction -- Classification -- Optic nerve head -- Fundus image; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2018.05.028
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: Peripapillary atrophy (PPA) is detected using statistical features and Backpropagation Neural Network as the classifier. The idea of forming an extraction area is proposed. Gain ratio is implemented to select the important features. The existence of blood vessels make our work more challenging. Our method achieves a competitive result of accuracy. Abstract: The presence of peripapillary atrophy (PPA) is associated with two kinds of diseases, namely glaucoma and myopia. PPA is one of the characteristics of these diseases that can be observed through retinal fundus images. We propose an automatic detection method of PPA in retinal fundus images using statistical features and Backpropagation Neural Network. In this research, those images are classified into two classes: no-PPA and PPA. The features are extracted from the focal areas, which capture the areas where PPA may occur in each sector. There are three features used in this method namely, standard deviation, smoothness and third moment; they are selected using gain ratio method. The performance of the proposed method achieves the accuracy of 0.95, 0.96, and 0.96 for three different datasets. These are obtained using 155 retinal fundus images, from which training and testing data of 47 images and 108 images, respectively, are randomly selected.