Interobserver and Intertest Agreement in Telemedicine Glaucoma Screening with Optic Disk Photos and Optical Coherence Tomography.

Purpose: To evaluate interobserver and intertest agreement between optical coherence tomography (OCT) and retinography in the detection of glaucoma through a telemedicine program. Methods: A stratified sample of 4113 individuals was randomly selected, and those who accepted underwent examination including visual acuity, intraocular pressure (IOP), non-mydriatic retinography, and imaging using a portable OCT device. Participants' data and images were uploaded and assessed by 16 ophthalmologists on a deferred basis. Two independent evaluations were performed for all participants. Agreement between methods was assessed using the kappa coefficient and the prevalence-adjusted bias-adjusted kappa (PABAK). We analyzed potential factors possibly influencing the level of agreement. Results: The final sample comprised 1006 participants. Of all suspected glaucoma cases (n = 201), 20.4% were identified in retinographs only, 11.9% in OCT images only, 46.3% in both, and 21.4% were diagnosed based on other data. Overall interobserver agreement outcomes were moderate to good with a kappa coefficient of 0.37 and a PABAK index of 0.58. Higher values were obtained by experienced evaluators (kappa = 0.61; PABAK = 0.82). Kappa and PABAK values between OCT and photographs were 0.52 and 0.82 for the first evaluation. Conclusion: In a telemedicine screening setting, interobserver agreement on diagnosis was moderate but improved with greater evaluator expertise.

Automatic glaucoma classification using color fundus images based on convolutional neural networks and transfer learning.

Glaucoma detection in color fundus images is a challenging task that requires expertise and years of practice. In this study we exploited the application of different Convolutional Neural Networks (CNN) schemes to show the influence in the performance of relevant factors like the data set size, the architecture and the use of transfer learning vs newly defined architectures. We also compared the performance of the CNN based system with respect to human evaluators and explored the influence of the integration of images and data collected from the clinical history of the patients. We accomplished the best performance using a transfer learning scheme with VGG19 achieving an AUC of 0.94 with sensitivity and specificity ratios similar to the expert evaluators of the study. The experimental results using three different data sets with 2313 images indicate that this solution can be a valuable option for the design of a computer aid system for the detection of glaucoma in large-scale screening programs.