AEKOC+: Kernel Ridge Regression-Based Auto-Encoder for One-Class Classification Using Privileged Information

In recent years, non-iterative learning approaches for kernel have received quite an attention by researchers and kernel ridge regression (KRR) approach is     

Ocular sequelae in severe COVID-19 recovered patients of second wave

Purpose:To evaluate the retinal microvascular changes in patients, recovered from severe COVID-19 during the second wave of the pandemic in North India.Methods:In this observational cross-sectional study, 70 eyes of 35 patients who recovered from severe COVID-19 during the second wave underwent detailed ophthalmic evaluation 4–6 weeks after discharge. Twelve controls were also enrolled, and the difference in the findings between the case and control groups on optical coherence tomography (OCTA) were studied.Result:The ages of study participants ranged from 27 to 60 years with the male:female ratio being 1.05:1. The fundus changes suggestive of ischemia in the form of cotton wool spots and vascular tortuosity were seen in 25 eyes (35.71%). Increased venous tortuosity was the most common finding seen in 23 eyes (32.85%), of which 10 eyes (28.57%) had concurrent hypertensive retinopathy (HTR) changes. There was a significant reduction in the mean vascular density (VD) and perfusion density (PD) for both the superficial capillary plexus (SCP) and deep capillary plexus (DCP) at inner, outer ring, and whole (P < 0.05). Foveal avascular zone was significantly enlarged in both the SCP (P = 0.01) and the DCP (P = 0.03). The mean ganglion cell-inner plexiform layer (GC-IPL) was significantly reduced in comparison to controls (P < 0.001).Conclusion:Severe COVID-19 can result in microvascular changes at the macula in the form of reduction in vascular and perfusion density, which can be evaluated using OCTA. As structural changes precede functional changes, a close watch is recommended in patients showing compromise in retinal microvasculature.     

Recent Advancements in Retinal Vessel Segmentation

Retinal vessel segmentation is a key step towards the accurate visualization, diagnosis, early treatment and surgery planning of ocular diseases. For the last two decades, a tremendous amount of research has been dedicated in developing automated methods for segmentation of blood vessels from retinal fundus images. Despite the fact, segmentation of retinal vessels still remains a challenging task due to the presence of abnormalities, varying size and shape of the vessels, non-uniform illumination and anatomical variability between subjects. In this paper, we carry out a systematic review of the most recent advancements in retinal vessel segmentation methods published in last five years. The objectives of this study are as follows: first, we discuss the most crucial preprocessing steps that are involved in accurate segmentation of vessels. Second, we review most recent state-of-the-art retinal vessel segmentation techniques which are classified into different categories based on their main principle. Third, we quantitatively analyse these methods in terms of its sensitivity, specificity, accuracy, area under the curve and discuss newly introduced performance metrics in current literature. Fourth, we discuss the advantages and limitations of the existing segmentation techniques. Finally, we provide an insight into active problems and possible future directions towards building successful computer-aided diagnostic system.     

Workup following retinal artery occlusion—experience from an outpatient retina clinic and the delay in workup

Graefe's Archive for Clinical and Experimental Ophthalmology - Acute retinal artery occlusion (RAO) is an urgent ophthalmic condition often indicative of future ischemic pathology. Patients...