This study aimed to assess the utility of optic nerve head (onh) en-face images, captured with scanning laser ophthalmoscopy (slo) during standard optical coherence tomography (oct) imaging of the posterior segment, and demonstrate the potential of deep learning (dl) ensemble method that operates in a low data regime to differentiate glaucoma patients from healthy controls. The two groups of subjects were initially categorized based on a range of clinical tests including measurements of intraocular pressure, visual fields, oct derived retinal nerve fiber layer (rnfl) thickness and dilated stereoscopic examination of onh. 227 slo images of 227 subjects (105 glaucoma patients and 122 controls) were used. A new task-specific convolutional neural network architecture was developed for slo image-based classification. To benchmark the results of the proposed method, a range of classifiers were tested including five machine learning methods to classify glaucoma based on rnfl thickness—a well-known biomarker in glaucoma diagnostics, ensemble classifier based on inception v3 architecture, and classifiers based on features extracted from the image. The study shows that cross-validation dl ensemble based on slo images achieved a good discrimination performance with up to 0.962 of balanced accuracy, outperforming all of the other tested classifiers.

Automated segmentation of the eye’s morphological features in OCT datasets is fundamental to support rapid clinical decision making and to avoid time-consuming manual segmentation of the images. In recent years, deep learning (DL) techniques have become a commonly employed approach to tackle image analysis problems. This study provides a description of the development of automated DL segmentation methods of the Bruch’s membrane opening (BMO) from a series of OCT cross-sectional scans. A range of DL techniques are systematically evaluated, with the secondary goal to understand the effect of the network input size on the model performance. The results indicate that a fully semantic approach, in which the whole B-scan is considered with data augmentation, results in the best performance, achieving high levels of similarity metrics with a dice coefficient of 0.995 and BMO boundary localization with a mean absolute error of 1.15 pixels. The work further highlights the importance of fully semantic methods over patch-based techniques in the classification of OCT regions.

No abstract