Automatic screening of narrow anterior chamber angle and angle-closure glaucoma based on slit-lamp image analysis by using support vector machine

Abstract

At present, Van Herick's method is a standard technique used to screen a Narrow Anterior Chamber Angle (NACA) and Angle-Closure Glaucoma (ACG). It can identify a patient who suffers from NACA and ACG by considering the width of peripheral anterior chamber depth (PACD) and corneal thickness. However, the screening result of this method often varies among ophthalmologists. So, an automatic screening of NACA and ACG based on slit-lamp image analysis by using Support Vector Machine (SVM) is proposed. SVM can automatically generate the classification model, which is used to classify the result as an angle-closure likely or an angle-closure unlikely. It shows that it can improve the accuracy of the screening result. To develop the classification model, the width of PACD and corneal thickness from many positions are measured and selected to be features. A statistic analysis is also used in the PACD and corneal thickness estimation in order to reduce the error from reflection on the cornea. In this study, it is found that the generated models are evaluated by using 5-fold cross validation and give a better result than the result classified by Van Herick's method.

Parameterization of Limbus Distance in Van Herick method's angle closure glaucoma diagnosis

“…Theeraworm et al [15] increased the threshold of CT over PACD ratio to twice of VH as in her method the slit-lamp beam incidents did tend to be farther from LD. While there was no direct measurement of LD conducted, the new threshold derived based on analyzing classification's Receiver Operating Characteristics (ROC) curve of range of thresholds against gonioscopy results as ground truth.…”

“…Then applied the traditional VH grading procedures to classify ACG. Theeraworn et al [15] went a step further, by introducing a slightly modified hardware. The slit-lamp and imaging device positions were switched, and angle increased from 60 degrees to 80 degrees.…”

“…Accuracy of the algorithm's measurements surpassed ophthalmologists participated in the experiment. Finally, Support Vector Machines (SVM) were utilized for the improvement of the classification in et al [17]. In the latter study, it was concluded …”

“…W is set of parameters and B is bias of classifier. W vector components are modified iteratively based on optimization techniques to minimize Mean Square Error over N data samples, equation (15).…”

“…Constraints inequality shown in equation (16). To perform a non-linear optimization, input space could be mapped into feature space by use of kernel function, equation (17). Based on geometric model of the problem, this study employs a Quadratic Function kernel shown in equation (18).…”