Marinko V. Sarunic

Précis: Glaucoma was associated with axial bowing and rotation of Bruchs membrane opening (BMO) and anterior laminar insertion (ALI), skewed neural canal, and deeper anterior lamina cribrosa surface (ALCS). Longer axial length was associated with wider, longer, and more skewed neural canal and flatter ALCS. Purpose: Investigate the effects of myopia and glaucoma in the prelaminar neural canal and anterior lamina cribrosa using 1060-nm swept-source optical coherence tomography. Patients: 19 control (38 eyes) and 38 glaucomatous subjects (63 eyes). Materials and Methods: Participants were imaged with swept-source optical coherence tomography, and the images were analyzed for the BMO and ALI dimensions, prelaminar neural canal dimensions, and ALCS depth. Results: Glaucomatous eyes had more bowed and nasally rotated BMO and ALI, more horizontally skewed prelaminar neural canal, and deeper ALCS than the control eyes. Increased axial length was associated with a wider, longer, and more horizontally skewed neural canal and a decrease in the ALCS depth and curvature. Conclusion: Our findings suggest that glaucomatous posterior bowing or cupping of lamina cribrosa can be significantly confounded by the myopic expansion of the neural canal. This may be related to higher glaucoma risk associated with myopia from decreased compliance and increased susceptibility to IOP-related damage of LC being pulled taut.

Optical coherence tomography (OCT) and OCT angiography (OCT-A) may benefit the screening of diabetic retinopathy (DR). This study investigated the effect of laterally subsampling OCT/OCT-A en face scans by up to a factor of 8 when using deep neural networks for automated referable DR classification. There was no significant difference in the classification performance across all evaluation metrics when subsampling up to a factor of 3, and only minimal differences up to a factor of 8. Our findings suggest that OCT/OCT-A can reduce the number of samples (and hence the acquisition time) for a volume for a given field of view on the retina that is acquired for rDR classification.

Image degradation due to wavefront aberrations can be corrected with adaptive optics (AO). In a typical AO configuration, the aberrations are measured directly using a Shack-Hartmann wavefront sensor and corrected with a deformable mirror in order to attain diffraction limited performance for the main imaging system. Wavefront sensor-less adaptive optics (SAO) uses the image information directly to determine the aberrations and provide guidance for shaping the deformable mirror, often iteratively. In this report, we present a Deep Reinforcement Learning (DRL) approach for SAO correction using a custom-built fluorescence confocal scanning laser microscope. The experimental results demonstrate the improved performance of the DRL approach relative to a Zernike Mode Hill Climbing algorithm for SAO.

Optical coherence tomography (OCT) has become an essential tool in the evaluation of glaucoma, typically through analyzing retinal nerve fiber layer changes in circumpapillary scans. Three-dimensional OCT volumes enable a much more thorough analysis of the optic nerve head (ONH) region, which may be the site of initial glaucomatous optic nerve damage. Automated analysis of this region is of great interest, though large anatomical variations and the termination of layers make the requisite peripapillary layer and Bruch’s membrane opening (BMO) segmentation a challenging task. Several machine learning-based segmentation methods have been proposed for retinal layer segmentation, and a few for the ONH region, but they typically depend on either heavily averaged or pre-processed B-scans or a large amount of annotated data, which is a tedious task and resource-intensive. We evaluated a semi-supervised adversarial deep learning method for segmenting peripapillary retinal layers in OCT B-scans to take advantage of unlabeled data. We show that the use of a generative adversarial network and unlabeled data can improve the performance of segmentation. Additionally, we use a Faster R-CNN architecture to automatically segment the BMO. The proposed methods are then used for the 3D morphometric analysis of both control and glaucomatous ONH volumes to demonstrate the potential for clinical utility.

Purpose: Optical coherence tomography angiography (OCT-A) permits visualization of the changes to the retinal circulation due to diabetic retinopathy (DR), a microvascular complication of diabetes. We demonstrate accurate segmentation of the vascular morphology for the superficial capillary plexus (SCP) and deep vascular complex (DVC) using a convolutional neural network (CNN) for quantitative analysis. Methods: The main CNN training dataset consisted of retinal OCT-A with a 6 × 6-mm field of view (FOV), acquired using a Zeiss PlexElite. Multiple-volume acquisition and averaging enhanced the vasculature contrast used for constructing the ground truth for neural network training. We used transfer learning from a CNN trained on smaller FOVs of the SCP acquired using different OCT instruments. Quantitative analysis of perfusion was performed on the resulting automated vasculature segmentations in representative patients with DR. Results: The automated segmentations of the OCT-A images maintained the distinct morphologies of the SCP and DVC. The network segmented the SCP with an accuracy and Dice index of 0.8599 and 0.8618, respectively, and 0.7986 and 0.8139, respectively, for the DVC. The inter-rater comparisons for the SCP had an accuracy and Dice index of 0.8300 and 0.6700, respectively, and 0.6874 and 0.7416, respectively, for the DVC. Conclusions: Transfer learning reduces the amount of manually annotated images required while producing high-quality automatic segmentations of the SCP and DVC that exceed inter-rater comparisons. The resulting intercapillary area quantification provides a tool for in-depth clinical analysis of retinal perfusion. Translational Relevance: Accurate retinal microvasculature segmentation with the CNN results in improved perfusion analysis in diabetic retinopathy.

Purpose: To evaluate the role of ensemble learning techniques with deep learning in classifying diabetic retinopathy (DR) in optical coherence tomography angiography (OCTA) images and their corresponding co-registered structural images. Methods: A total of 463 volumes from 380 eyes were acquired using the 3 × 3-mm OCTA protocol on the Zeiss Plex Elite system. Enface images of the superficial and deep capillary plexus were exported from both the optical coherence tomography and OCTA data. Component neural networks were constructed using single data-types and fine-tuned using VGG19, ResNet50, and DenseNet architectures pretrained on ImageNet weights. These networks were then ensembled using majority soft voting and stacking techniques. Results were compared with a classifier using manually engineered features. Class activation maps (CAMs) were created using the original CAM algorithm and Grad-CAM. Results: The networks trained with the VGG19 architecture outperformed the networks trained on deeper architectures. Ensemble networks constructed using the four fine-tuned VGG19 architectures achieved accuracies of 0.92 and 0.90 for the majority soft voting and stacking methods respectively. Both ensemble methods outperformed the highest single data-type network and the network trained on hand-crafted features. Grad-CAM was shown to more accurately highlight areas of disease. Conclusions: Ensemble learning increases the predictive accuracy of CNNs for classifying referable DR on OCTA datasets. Translational Relevance: Because the diagnostic accuracy of OCTA images is shown to be greater than the manually extracted features currently used in the literature, the proposed methods may be beneficial toward developing clinically valuable solutions for DR diagnoses.

Adaptive Optics (AO) is required to achieve diffraction limited resolution in many real-life imaging applications in biology and medicine. AO is essential to guarantee high fidelity visualization of cellular structures for retinal imaging by correcting ocular aberrations. Aberration correction for mouse retinal imaging by direct wavefront measurement has been demonstrated with great success. However, for mouse eyes, the performance of the wavefront sensor (WFS) based AO can be limited by several factors including non-common path errors, wavefront reconstruction errors, and an ill-defined reference plane. Image-based AO can avoid these issues at the cost of algorithmic execution time. Furthermore, image-based approaches can provide improvements to compactness, accessibility, and even the performance of AO systems. Here, we demonstrate the ability of image-based AO to provide comparable aberration correction and image resolution to the conventional Shack-Hartmann WFS-based AO approach. The residual wavefront error of the mouse eye was monitored during a wavefront sensorless optimization to allow comparison with classical AO. This also allowed us to improve the performance of our AO system for small animal retinal imaging.

Background: The roles of the retinal microvasculature and the retinal pigment epithelium (RPE) in maintaining the health and metabolic activity of the retina lend great clinical value to their high-resolution visualization. Methods: By integrating polarization diversity detection (PDD) into multi-scale and -contrast sensorless adaptive optics optical coherence tomography (MSC-SAO-OCT), we have developed a novel multi-contrast SAO OCT system for imaging pigment in the RPE as well as flow in the retinal capillaries using OCT angiography (OCTA). Aberration correction was performed based on the image quality using transmissive deformable optical elements. Results: MSC-SAO-OCTA imaging was performed at multiple fields-of-view (FOVs) with adjustable numerical aperture (NA). Retinal flow and RPE structural images for in vivo healthy and pathological human posterior eyes were demonstrated to show clinical feasibility of the system. Conclusions: High-resolution imaging of retinal vasculature at both large and small FOVs, as well as characterization of RPE topology and deformation, enables more sophisticated and concise investigation of retinal pathologies for in vivo human imaging. MSC imaging may permit detection and analysis of even subtle deformations in the RPE layer using a single instrument.

Vision researchers often use small animals due to the availability of many transgenic strains that model human diseases or express biomarkers. Adaptive optics (AO) enables non-invasive single-cell imaging in a living animal but often results in high system complexity. Sensorless AO (SAO) can provide depth-resolved aberration correction with low system complexity. We present a multi-modal sensorless AO en face retina imaging system that includes optical coherence tomography (OCT), OCT-angiography, confocal scanning laser ophthalmoscopy (SLO), and fluorescence detection. We present a compact lens-based imaging system design that allows for a 50-degree maximum field of view (FOV), which can be reduced to the region of interest to perform SAO with the modality of choice. The system performance was demonstrated on wild type mice (C57BL/6J), and transgenic mice with GFP labeled cells. SAO SLO was used for imaging microglia (Cx3cr1-GFP) over ~1 hour, where dynamics of the microglia branches were clearly observed. Our results also include volumetric cellular imaging of microglia throughout the inner retina.