Glaucoma, a leading cause of blindness, is a multifaceted disease with several patho-physiological features manifesting in single fundus images (e.g., optic nerve cupping) as well as fundus videos (e.g., vascular pulsatility index). Current convolutional neural networks (CNNs) developed to detect glaucoma are all based on spatial features embedded in an image. We developed a combined CNN and recurrent neural network (RNN) that not only extracts the spatial features in a fundus image but also the temporal features embedded in a fundus video (i.e., sequential images). A total of 1810 fundus images and 295 fundus videos were used to train a CNN and a combined CNN and Long Short-Term Memory RNN. The combined CNN/RNN model reached an average F-measure of 96.2% in separating glaucoma from healthy eyes. In contrast, the base CNN model reached an average F-measure of only 79.2%. This proof-of-concept study demonstrates that extracting spatial and temporal features from fundus videos using a combined CNN and RNN, can markedly enhance the accuracy of glaucoma detection.

In this review, we summarise retinal structural, functional and vascular changes reported to be associated with AD. We also review techniques employed to image these two major hall mark proteins of AD and their relevance for early detection of AD.

Dynamic assessment of retinal vascular characteristics can aid in identifying glaucoma-specific biomarkers. More specifically, a loss of spontaneous retinal venous pulsations (SVPs) has been reported in glaucoma, but a lack of readily available tools has limited the ability to explore the full potential of SVP analysis in glaucoma assessment. Advancements in smart technology have paved the way for the development of portable, noninvasive, and inexpensive imaging modalities. By combining off-theshelf optical elements and smart devices, the current study aims to determine whether SVPs can be detected and quantified using a novel tablet-based ophthalmoscope in glaucoma and glaucoma suspects. Methods: Thirty patients, including 21 with confirmed glaucoma (9 men; average age 75 ± 8 years) and 9 glaucoma suspects (5 men; average age 64 ± 9 years), were studied. All patients had intraocular pressure measurements, Humphrey visual field assessment, optical coherence tomography, and a 10-second videoscopy of the retinal circulation. The retinal vasculature recordings (46°field of view at 30 frames per second) were analyzed to extract SVP amplitudes. Results: SVPs were detected and quantified in 100% of patients with glaucoma and those with suspected glaucoma using the novel device. The average SVP amplitudes in glaucoma and glaucoma suspects were 42.6% ± 10.7% and 34% ± 6.7%, respectively. Conclusions: Our results suggest that a novel tablet-based ophthalmoscope can aid in documenting and objectively quantifying SVPs in all patients. Translational Relevance: Outcomes of this study provide an innovative, portable, noninvasive, and inexpensive solution for objective assessment of SVPs, which may have clinical relevance in glaucoma screening.

Glaucoma, the leading cause of irreversible blindness, is classified as a neurodegenerative disease, and its incidence increases with age. Pathophysiological changes, such as the deposition of amyloid-beta plaques in the retinal ganglion cell layer, as well as neuropsychological changes, including cognitive decline, have been reported in glaucoma. However, the association between cognitive ability and retinal functional and structural measures in glaucoma, particularly glaucoma subtypes, has not been studied. We studied the association between cognitive ability and the visual field reliability indices as well as the retinal ganglion cell (RGC) count estimates in a cohort of glaucoma patients. Methods: A total of 95 eyes from 61 glaucoma patients were included. From these, 20 were normal-tension glaucoma (NTG), 25 were primary open-angle glaucoma (POAG), and 16 were glaucoma suspects. All the participants had a computerised Humphrey visual field (HVF) assessment and optical coherence tomography (OCT) scan and were administered the written Montreal Cognitive Assessment (MoCA) test. RGC count estimates were derived based on established formulas using the HVF and OCT results. A MoCA cut-off score of 25 and less was designated as cognitive impairment. Student’s t-test was used to assess differences between the groups. The Pearson correlation coefficient was used to assess the association between MoCA scores and retinal structural and functional measures. Results: Significant associations were found between MoCA scores and the false-negative and pattern standard deviation indices recorded on the HVF (r = −0.19, r = −0.22, p < 0.05). The mean IOP was significantly lower in the cognitively impaired group (i.e., MOCA ≤ 25) (13.7 ± 3.6 vs. 15.7 ± 4.5, p < 0.05). No significant association was found between RGC count estimates and MoCA scores. Analysis of these parameters in individual glaucoma subtypes did not reveal any group-specific significant associations either.