Retinal Nerve Fiber Layer Defect Detection using Machine Learning on Optic Disc Photograph

Glaucoma is a neurodegenerative disease presents with retinal nerve fiber layer (RNFL) defects. We apply machine learning classifiers on the color information of the RNFL to differentiate between intact RNFL (i-RNFL) and RNFL defect (d-RNFL) on optic disc photographs (DPs). DPs from individuals with and without glaucoma were collected. Then, a semi-circle was automatically marked on the DPs, to label i-RNFL versus d-RNFL. RGB intensities and other color spaces of two profiles were collected. Five-fold cross validation is used to compare classification efficiency of five classifiers. A total of 2,051 profiles from 89, 32 and 15 DPs from patients with glaucoma, glaucoma suspects and control subjects were collected. There were 702 and 175 points of d-RNFL and 940 and 234 of i-RNFL in the training and test sets. In the training set, the 3 best classifiers using RGB intensities were fine Gaussian support vector machine (SVM), medium k-Nearest Neighbor and ensemble RUSBoosted Trees, with accuracies of 81.8%, 79.4% and 79.2%. The performance of the fine Gaussian SVM was similar between RGB and other color spaces. In the test set, the highest sensitivity (71.4%) and specificity (88.5%) were archived using RGB and the combination of RGB and Cb and Cr.

I. Introduction

Glaucoma is the leading cause of irreversible blindness worldwide. It is estimated that the number of patients will be 111.8 million in 2040, with affected older people mainly in Asia and Africa [1]. Glaucoma causes progressive retinal nerve fiber layer (RNFL) loss, which leads to visual field abnormalities and blindness in untreated patients. However, people often do not seek an ophthalmic examination because the disease is mostly asymptomatic until in an advanced stage. The number of undiagnosed cases was 90% in Brazil, 85.1% in Singapore and 55% – 78% in the US [2]–[6]. Early detection of glaucoma is important for the prevention of blindness. However, the conventional methods are not suitable for screening.