Search

Diabetic retinopathy (DR) is a leading cause of blindness in middle-aged diabetic patients. Regular screening for DR using fundus imaging aids in detecting complications and delays the progression of the disease. Because manual screening takes time and is subjective, deep learning has been used to help graders. Pre-trained or brute force CNN models are used in existing DR grading CNN-based approaches that are not suited to fundus image complexity. To solve this problem, we present a method for automatically customizing CNN models based on fundus image lesions. It uses k-medoid clustering, principal component analysis (PCA), and inter-class and intra-class variations to determine the CNN model's depth and width. The designed models are lightweight, adapted to the internal structures of fundus images, and encode the discriminative patterns of DR lesions. The technique is validated on a local dataset from King Saud University Medical City, Saudi Arabia, and two challenging Kaggle datasets: EyePACS and APTOS2019. The auto-designed models outperform well-known pre-trained CNN models such as ResNet152, DenseNet121, and ResNeSt50, as well as Google's AutoML and Auto-Keras models based on neural architecture search (NAS). The proposed method outperforms current CNN-based DR screening methods. The proposed method can be used in various clinical settings to screen for DR and refer patients to ophthalmologists for further evaluation and treatment. [ABSTRACT FROM AUTHOR]

Chronic Ocular Diseases (COD) such as myopia, diabetic retinopathy, age-related macular degeneration, glaucoma, and cataract can affect the eye and may even lead to severe vision impairment or blindness. According to a recent World Health Organization (WHO) report on vision, at least 2.2 billion individuals worldwide suffer from vision impairment. Often, overt signs indicative of COD do not manifest until the disease has progressed to an advanced stage. However, if COD is detected early, vision impairment can be avoided by early intervention and cost-effective treatment. Ophthalmologists are trained to detect COD by examining certain minute changes in the retina, such as microaneurysms, macular edema, hemorrhages, and alterations in the blood vessels. The range of eye conditions is diverse, and each of these conditions requires a unique patient-specific treatment. Convolutional neural networks (CNNs) have demonstrated significant potential in multi-disciplinary fields, including the detection of a variety of eye diseases. In this study, we combined several preprocessing approaches with convolutional neural networks to accurately detect COD in eye fundus images. To the best of our knowledge, this is the first work that provides a qualitative analysis of preprocessing approaches for COD classification using CNN models. Experimental results demonstrate that CNNs trained on the region of interest segmented images outperform the models trained on the original input images by a substantial margin. Additionally, an ensemble of three preprocessing techniques outperformed other state-of-the-art approaches by 30% and 3%, in terms of Kappa and F1 scores, respectively. The developed prototype has been extensively tested and can be evaluated on more comprehensive COD datasets for deployment in the clinical setup. [ABSTRACT FROM AUTHOR]

Background: Subthalamic nucleus deep brain stimulation (STN-DBS) is widely used for the treatment of primary motor symptoms in patients with Parkinson's disease (PD). Further, recent evidence suggests that STN-DBS may relieve a few ophthalmic symptoms in PD, such as eye-blink rate and the flexibility of eye saccades. However, its exact effect on visual function remains unknown. Herein, we report the case of a patient with PD who underwent STN-DBS and experienced visual symptoms following levodopa reduction. Case presentation: A 63-year-old male patient with PD developed severe visual impairment after six months of high-frequency STN-DBS. His symptoms resolved after adjusting the levodopa dose prescribed to the patient. Conclusions: This case report suggests that DBS is beneficial in patients with PD in terms of eye-blink rate. However, the rapid reduction of medication after STN-DBS may lead to retinal atrophy and the shrinkage of vessel density in the ocular fundus. Thus, neurosurgeons should pay close attention to patients with visual symptoms when adjusting levodopa dosages. [ABSTRACT FROM AUTHOR]

Early detection of lesions is of great significance for treating fundus diseases. Fundus photography is an effective and convenient screening technique by which common fundus diseases can be detected. In this study, we use color fundus images to distinguish among multiple fundus diseases. Existing research on fundus disease classification has achieved some success through deep learning techniques, but there is still much room for improvement in model evaluation metrics using only deep convolutional neural network (CNN) architectures with limited global modeling ability; the simultaneous diagnosis of multiple fundus diseases still faces great challenges. Therefore, given that the self-attention (SA) model with a global receptive field may have robust global-level feature modeling ability, we propose a multistage fundus image classification model MBSaNet which combines CNN and SA mechanism. The convolution block extracts the local information of the fundus image, and the SA module further captures the complex relationships between different spatial positions, thereby directly detecting one or more fundus diseases in retinal fundus image. In the initial stage of feature extraction, we propose a multiscale feature fusion stem, which uses convolutional kernels of different scales to extract low-level features of the input image and fuse them to improve recognition accuracy. The training and testing were performed based on the ODIR-5k dataset. The experimental results show that MBSaNet achieves state-of-the-art performance with fewer parameters. The wide range of diseases and different fundus image collection conditions confirmed the applicability of MBSaNet. [ABSTRACT FROM AUTHOR]

Objective: To evaluate the indirect ophthalmoscopy performed in ophthalmologic consultations, analyzing the prevalence of the study and comparing them with the reason for the consultation. Methods: Cross-sectional study, with data found during the indirect ophthalmoscopy exam of inpatients or in emergency room care. The data analyzed for each patient was sex, the requested medical age, the reason for the consultation and the funduscopic examination findings. Results: One hundred and four patients were evaluated and 43.27% of patients with a prevalence of changes in the exam. The most requested reasons for requesting ophthalmologic evaluation were trauma (16.35%) and neurological alterations (15.38%). The most prevalent finding was papillary edema, representing 17.3% of the general estimates. Other very prevalent findings were diabetic and hypertensive retinopathies, both with 11.53% in the general assessment, but with 83.3% and 53.84% prevalence in patients whose reasons for consultation were decompensated DM and hypertensive crisis, respectively. Conclusions: Papillary edema and diabetic and hypertensive retinopathies were the most prevalent alterations, which demonstrates the importance of multidisciplinary care whenever possible, with greater attention to hypertensive and diabetic patients. [ABSTRACT FROM AUTHOR]

The pathogenic variant p.G90D in RHO is believed to be responsible for a spectrum of phenotypes, including congenital stationary blindness (for the purpose of this study termed night blindness without degeneration; NBWD), Sector RP, Pericentral RP, and Classic RP. We present a correlation between the serum concentration of vitamin A and disease severity in patients with this variant. This prospective study involved 30 patients from 7 families (17 male; median age 46 years, range 8–73). Full ophthalmological examination including visual acuity, Goldmann perimetry, slit-lamp exam, optical coherence tomography, fundus autofluorescence, and electrophysiology was performed to determine the presenting phenotype. The serum concentration of vitamin A was determined from a fasting blood sample taken on the day of the exam, where it was found that 23.3% (7/30) of patients had NBWD, 13.3% (4/30) had Sector RP, 3.3% (1/30) had Pericentral RP, and 60% (18/30) had Classic RP. Multiple logistic regression revealed a significantly higher probability of having a milder phenotype (NBWD or Sector RP) in association with younger age (p < 0.05) and a higher concentration of vitamin A (p < 0.05). We hypothesize that vitamin A in its 11-cis-retinal form plays a role in stabilizing the constitutively active p.G90D rhodopsin and its supplementation could be a potential treatment strategy for p.G90D RHO patients. [ABSTRACT FROM AUTHOR]

In recent years, there has been a significant increase in the number of people suffering from eye illnesses, which should be treated as soon as possible in order to avoid blindness. Retinal Fundus images are employed for this purpose, as well as for analysing eye abnormalities and diagnosing eye illnesses. Exudates can be recognised as bright lesions in fundus pictures, which can be the first indicator of diabetic retinopathy. With that in mind, the purpose of this work is to create an Integrated Model for Exudate and Diabetic Retinopathy Diagnosis (IMEDRD) with multi-level classifications. The model uses Support Vector Machine (SVM)-based classification to separate normal and abnormal fundus images at the first level. The input pictures for SVM are pre-processed with Green Channel Extraction and the retrieved features are based on Gray Level Co-occurrence Matrix (GLCM). Furthermore, the presence of Exudate and Diabetic Retinopathy (DR) in fundus images is detected using the Adaptive Neuro Fuzzy Inference System (ANFIS) classifier at the second level of classification. Exudate detection, blood vessel extraction, and Optic Disc (OD) detection are all processed to achieve suitable results. Furthermore, the second level processing comprises Morphological Component Analysis (MCA) based image enhancement and object segmentation processes, as well as feature extraction for training the ANFIS classifier, to reliably diagnose DR. Furthermore, the findings reveal that the proposed model surpasses existing models in terms of accuracy, time efficiency, and precision rate with the lowest possible error rate. [ABSTRACT FROM AUTHOR]

One type of diabetes is diabetic retinopathy, which results in vascular abnormalities that can result in blindness. Because the effects of this disease are irreversible, early detection is essential because unchecked eye disease can lead to blindness. A crucial first step in automated screening for diabetic retinopathy is the detection of microaneurysms in digital color fundus images. Normal, mild, moderate, severe, and PDR are the five DR stages or grades (proliferative diabetic retinopathy), colored fundus images are often examined by highly qualified specialists to identify this catastrophic condition. Manual diagnosis of this illness (by clinicians) takes time and is error-prone. Numerous computer vision-based methods for automatically identifying DR and its various stages from retina images have so been developed. This study uses fundus-colored images to demonstrate an automated strategy for detecting this condition early and classifying its severity using a convolution neural network. [ABSTRACT FROM AUTHOR]

Strabismus and amblyopia are common ophthalmologic developmental diseases caused by abnormal visual experiences. However, the underlying pathogenesis and visual defects are still not fully understood. Most studies have used experimental interference to establish diseaseassociated animal models, while ignoring the natural pathophysiological mechanisms. This study was designed to investigate whether natural strabismus and amblyopia are associated with abnormal neurological defects. We screened one natural strabismic monkey (Macaca fascicularis) and one natural amblyopic monkey from hundreds of monkeys, and retrospectively analyzed one human strabismus case. Neuroimaging, behavioral, neurophysiological, neurostructural, and genovariation features were systematically evaluated using magnetic resonance imaging (MRI), behavioraltasks, flash visual evoked potentials (FVEP), electroretinogram (ERG), optical coherence tomography (OCT), and whole-genome sequencing (WGS), respectively. Results showed that the strabismic patient and natural strabismic and amblyopic monkeys exhibited similar abnormal asymmetries in brain structure, i.e., ipsilateral impaired right hemisphere. Visual behavior, visual function, retinal structure, and fundus of the monkeys were impaired. Aberrant asymmetry in binocular visual function and structure between the strabismic and amblyopic monkeys was closely related, with greater impairment of the left visual pathway.Several similar known mutant genes for strabismus and amblyopia were also identified. In conclusion, natural strabismus and amblyopia are accompanied by abnormal asymmetries of the visual system, especially visual neurophysiological and neurostructural defects. Our results suggest that future therapeutic and mechanistic studies should consider defects and asymmetries throughout the entire visual system. [ABSTRACT FROM AUTHOR]

A 47-year-old woman with hypertension and rheumatoid arthritis presented with non-necrotizing scleritis in both eyes. Despite a course of oral corticosteroids, she continued to experience persistent symptoms. A rheumatologist was consulted and initiated treatment with tofacitinib, a JAK/STAT inhibitor. Treatment with tofacitinib and oral corticosteroids resulted in an improvement in the scleritis in both eyes. However, a fundus examination of her left eye revealed a superior-temporal branch retinal vein occlusion. Given the growing concern regarding the increased risk of thromboembolic events with tofacitinib therapy, it is essential to consider the risk of retinal vascular occlusions when starting tofacitinib therapy, particularly in patients with underlying systemic comorbidities. [ABSTRACT FROM AUTHOR]

PurposeTo evaluate the association between optical coherence tomography angiography (OCTA) macular and circumpapillary vessel density and visual field mean deviation (MD) in advanced primary open angle glaucoma.DesignCross-sectional study.MethodsMacula (superficial layer) and optic nerve head (ONH) with capillary density (CD) and without vessel density (VD) automated removal of large vessels OCTA of 34 eyes (34 patients, MD < -10 dB) were investigated as macula whole image VD (wiVD), parafoveal VD (pfVD), ONH wiVD, wiCD, circumpapillary VD, and cpCD. Spectral domain OCT circumpapillary retinal nerve fiber layer, macular ganglion cell complex, and ganglion cell inner plexiform layer were also analyzed.ResultsMacular and ONH VD decreased significantly with worsening MD. Each 1-dB decrease in MD was associated with a reduction of 0.43% and 0.46% for macular wiVD and pfVD with R2 of 0.28 and 0.27, respectively (all P < .01). The association between MD and VD was strongest for measures of ONH with large vessels removed, wiCD, and cpCD, followed by wiVD and circumpapillary VD with R2 of 0.26, 0.22, 0.17, 0.14, and a VD reduction of 0.43%, 0.51%, 0.33%, and 0.40%, respectively (all P < .02). There was a reduction of 1.19 μm in Avanti parafoveal ganglion cell complex, 1.13 μm in Spectralis ganglion cell inner plexiform layer, and 1.01 μm in Spectralis circumpapillary retinal nerve fiber layer, with R2 of 0.19 (P = .006), 0.23 (P = .002), and 0.24 (P = .002), respectively.ConclusionsONH and macula OCTA VD and thickness are associated with the severity of visual field damage in advanced primary open angle glaucoma.

Background/aimsTo better understand the pattern of degeneration progression in cases with choroideremia.MethodsA cohort of genotypically confirmed choroideremia cases who underwent optical coherence tomography (OCT) and fundus autofluorescence (FAF) imaging was studied. Using HEYEX review software, the foveal centre was marked on FAF images under guidance of corresponding OCT images, followed by application of an ETDRS grid. The boundaries of preserved autofluorescence (AF) were manually segmented in each individual ETDRS subfield. The regional distribution of preserved AF was assessed by comparing its area among the various subfields.ResultsA total of 168 eyes from 84 choroideremia cases were enrolled. There was a statistically significant difference in the amount of preserved AF area between inner subfields as determined by one-way analysis of variance (F (3,668)=9.997, p

This report describes the first documented case of choriovitreal neovascularization (CVNV) occurring after infectious chorioretinitis, with OCT-angiography (OCT-A) demonstrating flow through the vitreal portion of the lesion, and response to anti-VEGF therapy.

PurposeTo evaluate the utility of different optical coherence tomography angiography scan protocols in evaluating retinal changes in non-proliferative diabetic retinopathy.MethodsPatients were imaged with the RTVue XR Avanti OCT 3 mm × 3 mm and 6 mm × 6 mm "Angio Retina" scan protocols. Ability to clearly delineate the foveal avascular zone (FAZ), FAZ remodeling, microaneurysms, capillary nonperfusion, motion, and doubling artifacts were evaluated.ResultsForty-six eyes from 27 patients were enrolled. Eighty-nine percent of 3 mm × 3 mm versus 59% of 6 mm × 6 mm scans clearly delineated the FAZ (P = 0.001). Eighty percent of 3 mm × 3 mm versus 43% of 6 mm × 6 mm scans demonstrated FAZ remodeling (P = 0.0002). Microaneurysms were detected by 57% of 6 mm × 6 mm and 35% of 3 mm × 3 mm scans (P = 0.003). Capillary nonperfusion was detected in 87% of 3 mm × 3 mm scans versus 89% of 6 mm × 6 mm scans (P = 0.99). No significant differences were noted in the incidence of artifacts between the scan sizes (motion artifact P = 0.29 and doubling artifact P = 0.29).Conclusion3 mm × 3 mm scan delineated FAZ and remodeling better than 6 mm × 6 mm scan, likely because of its higher scan density. 6 mm × 6 mm scans detected microaneurysms more readily than 3 mm × 3 mm, likely because of its larger scan area. There were utility for both 3 mm × 3 mm and 6 mm × 6 mm scans when evaluating these patients.

Diabetic retinopathy (DR) is one of the most common causes of visual impairment. Automatic detection of hard exudates (HE) from retinal photographs is an important step for detection of DR. However, most of existing algorithms for HE detection are complex and inefficient. We have developed and evaluated an automatic retinal image processing algorithm for HE detection using dynamic threshold and fuzzy C-means clustering (FCM) followed by support vector machine (SVM) for classification. The proposed algorithm consisted of four main stages: (i) imaging preprocessing; (ii) localization of optic disc (OD); (iii) determination of candidate HE using dynamic threshold in combination with global threshold based on FCM; and (iv) extraction of eight texture features from the candidate HE region, which were then fed into an SVM classifier for automatic HE classification. The proposed algorithm was trained and cross-validated (10 fold) on a publicly available e-ophtha EX database (47 images) on pixel-level, achieving the overall average sensitivity, PPV, and F-score of 76.5%, 82.7%, and 76.7%. It was tested on another independent DIARETDB1 database (89 images) with the overall average sensitivity, specificity, and accuracy of 97.5%, 97.8%, and 97.7%, respectively. In summary, the satisfactory evaluation results on both retinal imaging databases demonstrated the effectiveness of our proposed algorithm for automatic HE detection, by using dynamic threshold and FCM followed by an SVM for classification.

PURPOSE: Glaucoma screening can be performed by assessing the vertical-cup-to-disk ratio (VCDR) of the optic nerve head from fundus photography, but VCDR grading is inherently subjective. This study investigated whether computer software could improve the accuracy and repeatability of VCDR assessment. METHODS: In this cross-sectional diagnostic accuracy study, 5 ophthalmologists independently assessed the VCDR from a set of 200 optic disk images, with the median grade used as the reference standard for subsequent analyses. Eight non-ophthalmologists graded each image by two different methods: by visual inspection and with assistance from a custom-made publicly available software program. Agreement with the reference standard grade was assessed for each method by calculating the intraclass correlation coefficient (ICC), and the sensitivity and specificity determined relative to a median ophthalmologist grade of ≥0.7. RESULTS: VCDR grades ranged from 0.1 to 0.9 for visual assessment and from 0.1 to 1.0 for software-assisted grading, with a median grade of 0.4 for each. Agreement between each of the 8 graders and the reference standard was higher for visual inspection (median ICC 0.65, interquartile range 0.57 to 0.82) than for software-assisted grading (median ICC 0.59, IQR 0.44 to 0.71); P = 0.02, Wilcoxon signed-rank test). Visual inspection and software assistance had similar sensitivity and specificity for detecting glaucomatous cupping. CONCLUSION: The computer software used in this study did not improve the reproducibility or validity of VCDR grading from fundus photographs compared with simple visual inspection. More clinical experience was correlated with higher agreement with the ophthalmologist VCDR reference standard.

Preclinical models of diabetic retinopathy are indispensable in the drug discovery and development of new therapies. They are, however, imperfect facsimiles of diabetic retinopathy in humans. This chapter discusses the advantages, limitations, and physiological and pathological relevance of preclinical models of diabetic retinopathy. The judicious interpretation and extrapolation of data derived from these models to humans and a correspondingly greater emphasis placed on translational medical research in early-stage clinical trials are essential to more successfully inhibit the development and progression of diabetic retinopathy in the future.

Choroidal melanocytes (HCMs) are melanin-producing cells in the vascular uvea of the human eye (iris, ciliary body and choroid). These cranial neural crest-derived cells migrate to populate a mesodermal microenvironment, and display cellular functions and extracellular interactions that are biologically distinct to skin melanocytes. HCMs (and melanins) are important in normal human eye physiology with roles including photoprotection, regulation of oxidative damage and immune responses. To extend knowledge of cytoplasmic melanins and melanosomes in label-free HCMs, a non-invasive 'fit-free' approach, combining 2-photon excitation fluorescence lifetimes and emission spectral imaging with phasor plot segmentation was applied. Intracellular melanin-mapped FLIM phasors showed a linear distribution indicating that HCM melanins are a ratio of two fluorophores, eumelanin and pheomelanin. A quantitative histogram of HCM melanins was generated by identifying the image pixel fraction contributed by phasor clusters mapped to varying eumelanin/pheomelanin ratio. Eumelanin-enriched dark HCM regions mapped to phasors with shorter lifetimes and longer spectral emission (580-625 nm) and pheomelanin-enriched lighter pigmented HCM regions mapped to phasors with longer lifetimes and shorter spectral emission (550-585 nm). Overall, we demonstrated that these methods can identify and quantitatively profile the heterogeneous eumelanins/pheomelanins within in situ HCMs, and visualize melanosome spatial distributions, not previously reported for these cells.

Introduction: Several neurologic conditions can produce or mimic psychotic symptoms. It is important to make an exhaustive differential diagnosis between a psychiatric manifestation of an underlying neurological condition and a primary psychiatric one. We explore through the present clinical case of a young woman admitted to neurology the relationship between intracranial hypertension and a case of atypical psychosis that resolved itself with the treatment of the intracranial hypertension, without the need for antipsychotic medication. Objectives: To explore through the presented clinical case and the concerning literature the concept and management of psychotic-like symptoms in patients with intracranial hypertension. Methods: We present a clinical case and a review of the existing literature concerning atypical psychosis or psychosis-like symptoms in cases of intracranial hypertension. Results: We report the case of a 24 year old woman with no relevant medical history hospitalised in the neurology unit due to suspected encephalitis. Native to New Zealand, she is brought from the airport due to behavioural alterations. During the last few days before admission she had presented with incoherent speech, derailment, religious and persecutory delusions, and erotomania towards her cousin. She described feelings of strangeness with her surroundings and of time moving at a different speed than usual, either faster or slower. She also had a headache and visual alterations, as well as memory errors concerning recent events, clouding of consciousness and inattention. No fever or other relevant physical symptoms. A lumbar puncture is done, which shows an opening pressure of 37mmHg but no other anomalies. Body CT scan shows no relevant findings. Empirical treatment with dexamethasone is initiated for suspected encephalitis, progressively reducing the dosage until suspension in the following days. During her stay at the hospital she is assessed by ophthalmology, which finds no abnormalities in the eye fundus examination, and psychiatry. A second evacuating lumbar punture is done to reduce intracraneal hypertension. No antipsychotic treatment is initiated: the symptomatology remitted with the lowering of intracranial pressure. At time of discharge, the patient remained asymptomatic without treatment and was able to return home to continue outpatient neurologic study of the etiology of the intracranial hypertension. Finally, we conduct a review ot the existing literature concerning psychotic and psychosis-like symptoms in patients with intracranial hypertension, to explore the diagnostic and management options of this rare finding. Conclusions: Our findings point to the existing relationship between intracranial hypertension and psychosis-like symptoms. Further studies on pathogenic mechanisms and therapeutic management are required. Disclosure of Interest: None Declared [ABSTRACT FROM AUTHOR]

The authors present the multimodal imaging findings of an unusual case of bilateral acquired progressive myelination of the optic disc during a 10-year follow-up period in a hyperopic adolescent patient in the absence of an underlying ocular or systemic abnormality. Myelination of the left optic disc was noted at age 7 and of the right optic disc at age 13, but no other ocular or systemic abnormalities were identified. Cross-sectional optical coherence tomography (OCT) and en face OCT angiography confirmed the presence of myelination of the retinal nerve fiber layer and excluded other etiologic possibilities including an astrocytic hamartoma. [Ophthalmic Surg Lasers Imaging Retina. 2018;49:e147-e150.].

Background: The main barriers keeping individuals with high-risk of angle closure from seeking eye-care service are the absence of both disease awareness and convenient and low-cost access to the ocular health care system. Present study described the efficacy of a health examination center-based screening model designed to detect eyes with high risk of angle closure (HRAC) among healthy individuals using anterior segment optical coherence tomography (AS-OCT). Methods: From March 1 to April 30, 2017, consecutive individuals aged ≥ 40 years undergoing routine physical examinations at a health examination center were invited to enroll. Presenting visual acuity (PVA), intraocular pressure (IOP) measurement, non-mydriatic fundus photography and AS-OCT were performed by three trained nurses. Participants with PVA < 6/12 in the better-seeing eye, IOP ≥ 24 mmHg, or abnormal fundus photography in either eye were referred to the outpatient clinic, but not included in the analysis. Eyes with HRAC were defined as having trabecular-iris angle < 12 degrees in ≥ 3 quadrants. Configuration of the iris was classified into flat, bowing, bombe, thick peripheral iris and mixed mechanism. Results: Altogether, 991 participants (77.3%) with readable OCT images (mean age 55.5 ± 9.0 years; 58.4% men) were included. HRAC was diagnosed in 78 eyes (7.9%, 61.3 ± 8.2 years, 41.0% men). The prevalence of HRAC increased with age (p < 0.001) and was much higher among women (11.2%) than men (5.5%) (p = 0.001). The mixed mechanism iris configuration was most common among eyes with HRAC (37/78, 47.4%). Conclusion: HRAC is prevalent among asymptomatic Chinese adults undergoing routine health screening. Health examination center-based eye screening with AS-OCT administered by non-specialists may be a good model to screen narrow angles in the population at large. [ABSTRACT FROM AUTHOR]

Over the past decade, ocular imaging strategies have greatly advanced the diagnosis and follow-up of patients with optic neuropathies. Developments in optic nerve imaging have specifically improved the care of patients with papilloedema and idiopathic intracranial hypertension, inflammatory optic neuropathies, and compressive optic neuropathies. For example, optic nerve imaging with optical coherence tomography (OCT) is now widely used as an outcome measure in clinical trials of neurological disorders (eg, demyelinating diseases), and OCT findings could be informative of disease progression in patients with various neurodegenerative disorders (eg, Alzheimer's disease or Parkinson's disease). In the past 5 years, multimodality optic nerve imaging has expanded to systematically include focused and wide-field colour and autofluorescence fundus photographs; various types of optic nerve, macular, and vascular OCT; and specific MRI techniques. Such multimodality imaging makes the diagnosis of optic neuropathies easier and provides objective information on optic nerve damage, which is useful for prognosis. Non-mydriatic ocular fundus cameras and OCT have become readily available in non-ophthalmic settings and could easily be implemented in neurological clinics and emergency departments, allowing for direct access to optic nerve imaging and enabling teleconsultations. In the future, these imaging studies could be used in association with artificial intelligence deep-learning systems, which are already transforming the field of ocular imaging. [ABSTRACT FROM AUTHOR]

Automated detection of retinal structures, such as retinal vessels (RV), the foveal avascular zone (FAZ), and retinal vascular junctions (RVJ), are of great importance for understanding diseases of the eye and clinical decision-making. In this paper, we propose a novel Voting-based Adaptive Feature Fusion multi-task network (VAFF-Net) for joint segmentation, detection, and classification of RV, FAZ, and RVJ in optical coherence tomography angiography (OCTA). A task-specific voting gate module is proposed to adaptively extract and fuse different features for specific tasks at two levels: features at different spatial positions from a single encoder, and features from multiple encoders. In particular, since the complexity of the microvasculature in OCTA images makes simultaneous precise localization and classification of retinal vascular junctions into bifurcation/crossing a challenging task, we specifically design a task head by combining the heatmap regression and grid classification. We take advantage of three different en face angiograms from various retinal layers, rather than following existing methods that use only a single en face. We carry out extensive experiments on three OCTA datasets acquired using different imaging devices, and the results demonstrate that the proposed method performs on the whole better than either the state-of-the-art single-purpose methods or existing multi-task learning solutions. We also demonstrate that our multi-task learning method generalizes across other imaging modalities, such as color fundus photography, and may potentially be used as a general multi-task learning tool. We also construct three datasets for multiple structure detection, and part of these datasets with the source code and evaluation benchmark have been released for public access. [ABSTRACT FROM AUTHOR]

X-linked retinoschisis (XLRS) is a rare retinal dystrophy due to pathogenic variants in the RS1 gene. The hallmark of the disease is a foveal spoke-wheel appearance. The purpose of this report is to expand the phenotypic spectrum of XLRS reporting a patient with atypical phenotype of XLRS associated with Coats-like phenotype. This is a case report of a patient diagnosed with XLRS who underwent ophthalmologic multimodal imaging and next-generation sequencing panel. The proband is a 14-year-old male patient who presented at Instituto Suel Abujamra with a history of Coats Disease in the right eye treated with retinal laser in both eyes two years ago. His best-corrected visual acuity was count finger at 1 foot in the right eye and 20/40 in the left eye. Fundus exam showed an extensive area of exudation and retinal detachment in the right eye and cystic change at the fovea in a spoke-wheel pattern in the left eye. The next-generation sequencing panel targeting inherited retinal diseases with 236 genes found a pathogenic hemizygous variant c.304C>T (p.Arg102Trp) in RS1 that has already been reported. The association of peripheral vascular incompetence and XLRS has already been described. Retinal exudation in the setting of XLRS is probably the result of vascular disruption and compromise. The loss of retinoschisin function that leads to foveal retinoschisis may also lead to vascular anomalies. [ABSTRACT FROM AUTHOR]

Background: The prognostic value of common and frequently associated diabetic microvascular complications (MVC), namely chronic kidney disease (CKD), cardiac autonomic neuropathy (CAN), peripheral neuropathy (DPN), and retinopathy (DR), is well established. However, the impact of their different combinations on long-term mortality has not been adequately assessed. Methods: We retrospectively analyzed 21-year longitudinal data from 303 patients with long-standing type 1 (T1D) or type 2 diabetes (T2D), who were thoroughly characterized at baseline for the presence of MVC using 99mTc-DTPA dynamic renal scintigraphy, overnight urine collection, cardiovascular autonomic tests, monofilament testing, and dilated fundus oculi examination. Results: After a 5,244 person-years follow-up, a total of 133 (43.9%) deaths occurred. The presence of CKD and CAN, regardless of other MVC, increased the adjusted all-cause mortality risk by 117% (HR 2.17 [1.45–3.26]) and 54% (HR 1.54 [1.01–2.36]), respectively. Concomitant CKD&CAN at baseline were associated with the highest mortality risk (HR 5.08 [2.52–10.26]), followed by CKD&DR (HR 2.95 [1.63–5.32]), and CAN&DR (HR 2.07 [1.11–3.85]). Compared with patients free from MVC, the mortality risk was only numerically higher in those with any isolated MVC (HR 1.52 [0.87–2.67]), while increased by 203% (HR 3.03 [1.62–5.68]) and 692% (HR 7.92 [2.93–21.37]) in patients with two and three concomitant MVC, respectively. Conclusions: Our study demonstrates the long-term, synergistic, negative effects of single and concomitant diabetic MVC on all-cause mortality, which should encourage comprehensive screenings for MCV in both T1D and T2D to improve risk stratification and treatment. [ABSTRACT FROM AUTHOR]

To describe the demographic clinical characteristics and to identify the risk factors of patients diagnosed with fungemia and secondary intraocular involvement. Retrospective cohort of 97 patients diagnosed with fungemia and with or without involvement of the posterior segment. Demographic, clinical and ophthalmological variables were identified to establish the risk of retinal seeding. An incidence of ocular involvement of 22.68% was obtained and no clear risk factor was found for subsequent showings in patients with fungemia. A risk trend was only found in patients with diabetes with an OR: 2.85; CI 95%: (0.80–10.12) and history of HIV with an OR: 2.29 CI95%: (0.85–6.12). In this first cohort carried out in Colombia according to our search, findings were obtained that agree with those of other authors worldwide, where there is no evidence of a decrease in incidence compared with older studies and the absence of risk factors for the compromise of the posterior pole in patients with fungemia. Systematic fundus evaluation by an ophthalmologist in patients with candidaemia is a recommended practice based on low-quality evidence. The identification of real risk factors for retinal compromise in fungemia would allow us to be more selective with the population to be evaluated. Fungemia generally occurs in critically ill patients, where access and availability of ophthalmology evaluation are a resource that is not always available. [ABSTRACT FROM AUTHOR]

Diabetic retinopathy is one of the most common microvascular complications of diabetes. Early detection and treatment can effectively reduce the risk. Hence, a robust computer-aided diagnosis model is important. Based on the labeled fundus images, we build a binary classification model based on ResNet-18 and transfer learning and, more importantly, improve the robustness of the model through supervised contrastive learning. The model is tested with different learning rates and data augmentation methods. The standard deviations of the multiple test results decrease from 4.11 to 0.15 for different learning rates and from 1.53 to 0.18 for different data augmentation methods. In addition, the supervised contrastive learning method also improves the average accuracy of the model, which increases from 80.7% to 86.5%. [ABSTRACT FROM AUTHOR]

COVID-19 disease may cause alterations of microfluidic properties of blood circulation in the retinal tissue. For the pre-study of microfluidic blood physiology and transport, retinal fundus images are applied for clinical screening of abnormal vessels forms. However, fundus images captured by operators with various levels of experience have diversity in quality. Low-quality fundus images increase uncertainty in clinical observation and lead to the risk of misdiagnosis. Due to the optical beam of fundus image acquisition and vessel structure of the retina, natural image restoration methods cannot be applied straight to address this problem. The semi-automatic blind deblurring is a useful technique to restore the underlying sharp image given some assumed or known information about the cause of degradation. In this work, we propose a new hybrid algorithm for image restoration that does not require a priori knowledge of the noise distribution. The degraded image is first de-convoluted in Fourier space by parametric Wiener filtering; then, it is smoothed by using the anisotropic diffusion. The filtering model was tested on 177 fundus images. Experiment filtering results show the efficiency of our algorithm with a superlative performance (p-value < 0.05) when compared with state of the art methods. [ABSTRACT FROM AUTHOR]

To analyze the performance of ultra-wide-field (UWF) fundus photography compared with ophthalmoscopy in identifying and classifying retinal diseases. Patients examined for presumed major retinal disorders were consecutively enrolled. Each patient underwent indirect ophthalmoscopic evaluation, with scleral depression and/or fundus biomicroscopy, when clinically indicated, and mydriatic UWF fundus imaging by means of CLARUS 500™ fundus camera. Each eye was classified by a clinical grader and two image graders in the following groups: normal retina, diabetic retinopathy, vascular abnormalities, macular degenerations and dystrophies, retinal and choroidal tumors, peripheral degenerative lesions and retinal detachment and myopic alterations. 7024 eyes of new patients were included. The inter-grader agreement for images classification was perfect (kappa = 0.998, 95% Confidence Interval (95%CI) = 0.997–0.999), as the two methods concordance for retinal diseases diagnosis (kappa = 0.997, 95%CI = 0.996–0.999) without statistically significant difference. UWF fundus imaging might be an alternative to ophthalmoscopy, since it allows to accurately classify major retinal diseases, widening the range of disorders possibly diagnosed with teleophthalmology. Although the clinician should be aware of the possibility that a minority of the most peripheral lesions may be not entirely visualized, it might be considered a first line diagnostic modality, in the context of a full ophthalmological examination. [ABSTRACT FROM AUTHOR]

Retinal vein occlusion (RVO) is one of the most common retinal vascular diseases leading to vision loss if not diagnosed and treated in time. RVO can be classified into two types: CRVO (blockage of the main retinal veins) and BRVO (blockage of one of the smaller branch veins). Automated diagnosis of RVO can improve clinical workflow and optimize treatment strategies. However, to the best of our knowledge, there are few reported methods for automated identification of different RVO types. In this study, we propose a new hypermixed convolutional neural network (CNN) model, namely, the VGG-CAM network, that can classify the two types of RVOs based on retinal fundus images and detect lesion areas using an unsupervised learning method. The image data used in this study is collected and labeled by three senior ophthalmologists in Shanxi Eye Hospital, China. The proposed network is validated to accurately classify RVO diseases and detect lesions. It can potentially assist in further investigating the association between RVO and brain vascular diseases and evaluating the optimal treatments for RVO. [ABSTRACT FROM AUTHOR]

Glaucoma is an eye disease that causes loss of vision and blindness by damaging a nerve in the back of the eye called optic nerve. The optic nerve collects the visual information from the eyes and transmits to the brain. Glaucoma is mainly caused by an abnormal high pressure in the eyes. Over time, the increased pressure can erode the tissues of optic nerve, leading to vision loss or blindness. If it is diagnosed in advance, then only it can prevent the vision loss. To diagnose the glaucoma, it must accurately differentiate between the optic disc (OD), optic cup (OC), and the retinal nerve fiber layer (RNFL). The segmentation of the OD, OC, and RNFL remains a challenging issue under a minimum contrast image of boundaries. Therefore, in this study, an innovative method of Hybrid Symbiotic Differential Evolution Moth-Flame Optimization (SDMFO)-Multi-Boost Ensemble and Support Vector Machine (MBSVM)-based segmentation and classification framework is proposed for accurately detecting the glaucoma disease. By using Group Search Optimizer (GSO), the affected parts of the OD, OC and RNFL are segmented. The proposed SDMFO-MBSVM method is executed in MATLAB site, its performance is analyzed with three existing methods. From the comparison, the accuracy of the proposed method in OD segmentation gives better results of 3.37%, 4.54% and 2.22%, OC segmentation gives better results of 2.22%, 3.37% and 4.54%, and RNFL segmentation gives the better results of 3.37%, 97.21% and 5.74%. [ABSTRACT FROM AUTHOR]

Diabetes is an illness that happens with a high level of glucose in the body, and can harm the retina, causing permanent loss vision or diabetic retinopathy. The fundus oculi method comprises detecting the eyes to perform a pathology test. In this research, we implement a method to predict the progress of diabetic retinopathy. There is a research gap that exists for the detection of diabetic retinopathy progression employing deep learning models. Therefore, in this research, we introduce a recurrent CNN (R-CNN) model to detect upcoming visual field inspections to predict diabetic retinopathy progression. A benchmark dataset of 7000 eyes from healthy and diabetic retinopathy progress cases over the years are utilized in this research. Approximately 80% of ocular cases from the dataset is utilized for the training stage, 10% of cases are used for validation, and 10% are used for testing. Six successive visual field tests are used as input and the seventh test is compared with the output of the R-CNN. The precision of the R-CNN is compared with the regression model and the Hidden Markov (HMM) method. The average prediction precision of the R-CNN is considerably greater than both regression and HMM. In the pointwise classification, R-CNN depicts the least classification mean square error among the compared models in most of the tests. Also, R-CNN is found to be the minimum model affected by the deterioration of reliability and diabetic retinopathy severity. Correctly predicting a progressive visual field test with the R-CNN model can aid physicians in making decisions concerning diabetic retinopathy. [ABSTRACT FROM AUTHOR]

A 4-year old Clydesdale mare was presented with history of gradual muscle wastage despite good appetite since one year ago, which had progressed to severe hindquarter atrophy and weakness leading to total recumbency few days ago. Muscle fasciculations, wide hind leg stance, stiff neck and low head carriage could be observed. No abnormalities in vital parameters and no cranial nerve or spinal reflex deficits, except of a weak tail tonus were found. Estimation of ataxia was not possible due to the weakness. Ophthalmologic examination revealed no abnormalities in the fundus of the eye. Laboratory results showed slightly increased value of aspartate aminotransferase (AST), normal creatine kinase (CK) and high level of serum vitamin E (alpha-tocopherol). Equine Herpes Virus 1 and 4, as well as Bornavirus and West Nile Virus were ruled out using antibody titers and/or PCR of samples from blood and nasopharynx. Muscle biopsies taken from M. Semimembranosus, M. Sacrocaudalis dorsalis medialis and M. Gluteus showed neurogenic atrophy and abnormal intracellular glycogen distribution. The horse was diagnosed with concurrent Equine Motor Neuron Disease (EMND) and Polysaccharide Storage Myopathy Type 2 (PSSM2). Pathology of cervical spinal cord specimens post-mortem confirmed the diagnosis of Equine Motor Neuron Disease. The clinical presentation of the disease and the histological findings are discussed in this report. [ABSTRACT FROM AUTHOR]

Purpose: To analyze the typical presentation of acute posterior vitreous detachment (PVD), including demographics and prevalence of various treatable findings in the same and fellow eye. Methods: Retrospective analysis of medical records from 2346 patients with acute PVD. Descriptive statistics were generated on age, sex, contact date, visual acuity, and slit lamp, and fundoscopy findings. Multivariate regressions were used to generate odds ratios with 95% confidence intervals (CI) to quantify associations between variables. Results: A total of 4692 eyes from 2346 patients were analyzed. Most patients were female (60.5%) with an average age of 62.8 years old. Overall, 605 patients (25.8%) had any additional ocular finding on fundus exam, including pigmentation (N = 184, 7.8%), lattice degeneration (N = 158, 6.7%), tear (N = 131, 5.6%), and hole (N = 131, 5.2%). Unilateral retinal detachment was present in 26 patients (1.1%), and these patients demonstrated a similar rate (26.9%) of additional ocular findings compared to the entire sample size. Female sex (OR 1.21, 95% CI 1.03–1.43, p = 0.020) was independently associated with presentation during spring or summer. Conclusion: Acute PVD is associated with a number of risk factors and peripheral lesions. These findings may be useful in treating and predicting the course and development of PVD. [ABSTRACT FROM AUTHOR]

In this study, we investigated a convolutional neural network (CNN)-based framework for the estimation of the best-corrected visual acuity (BCVA) from fundus images. First, we collected 53,318 fundus photographs from the Gyeongsang National University Changwon Hospital, where each fundus photograph is categorized into 11 levels by retrospective medical chart review. Then, we designed 4 BCVA estimation schemes using transfer learning with pre-trained ResNet-18 and EfficientNet-B0 models where both regression and classification-based prediction are taken into account. According to the results of the study, the predicted BCVA by CNN-based schemes is close to the actual value such that 94.37% of prediction accuracy can be achieved when 3 levels of difference can be tolerated during prediction. The mean squared error and R 2 score were measured as 0.028 and 0.654, respectively. These results indicate that the BCVA can be predicted accurately for extreme cases, i.e., the level of BCVA is close to either 0.0 or 1.0. Moreover, using the Guided Grad-CAM, we confirmed that the macula and the blood vessel surrounding the macula are mainly utilized in the prediction of BCVA, which validates the rationality of the CNN-based BCVA estimation schemes since the same area is also exploited during the retrospective medical chart review. Finally, we applied the t-distributed stochastic neighbor embedding to examine the characteristics of CNN-based BCVA estimation schemes. The developed BCVA estimation schemes can be employed to obtain the objective measurement of BVCA as well as the medical screening of people with poor access to medical care through smartphone-based fundus imaging. [ABSTRACT FROM AUTHOR]

Comparison of two ultra-widefield (UWF) color-fundus (CF) imaging devices in diabetic patients for visualization of retinal periphery and detection of early microvascular lesions. The total gradable areas (TGA) seen on non-mydriatic CF-images of two UWF-imaging devices (Optos Daytona P200T; Zeiss Clarus 700) were compared and differences in projected area measured. Retinal periphery outside the 7 standard fields (7SF) was divided into: F3 temporal, F4 superotemporal, F5 inferotemporal, F6 superonasal, F7 inferonasal. DR stage was evaluated in the 7SF and the TGA on images of both devices and compared using Cohens κ. 67 eyes of 67 patients (52.5 ± 15.3 years) were analysed. DR stages in the 7SF were no (n = 36 Optos, n = 35 Clarus), mild (n = 16 Optos, n = 17 Clarus), and moderate DR (n = 15). Optos depicted significantly more area in F3 (median [interquartile range]; 2.41% [1.06–4.11] vs 0% [0–0], P < 0.001) and Clarus in F7 (3.29% [0–7.69] vs 0% [0–3.27], P = 0.002). In 4 eyes DR-stage was higher using Optos due to peripheral lesions not seen on the Clarus. Interrater reliability of DR-stage on both devices was almost perfect in the 7SF (κ = 0.975) and the TGA (κ = 0.855). Reliability in detecting signs of early DR is high on both devices. Clarus allowed for better visualization of the inferonasal field, Optos of the temporal field. [ABSTRACT FROM AUTHOR]

We investigated the effects of lacking TNFα on the development and regression of Argon‐laser‐induced choroidal neovascularization (CNV) in mice. We lasered ocular fundus for induction of CNV in both wild‐type (WT) and TNFα‐null (KO) mice. Fluorescence angiography was performed to examine the size of CNV lesions. Gene expression pattern of wound healing‐related components was examined. The effects of exogenous TNFα on apoptosis of human retinal microvascular endothelial cells (HRMECs) and on the tube‐like structure of the cells were investigated in vitro. The results showed that Argon‐laser irradiation‐induced CNV was significantly larger in KO mice than WT mice on Day 21, but not at other timepoints. Lacking TNFα increased neutrophil population in the lesion. The distribution of cleaved caspase3‐labelled apoptotic cells was more frequently observed in the laser‐irradiated tissue in a WT mouse as compared with a KO mouse. Exogenous TNFα induced apoptosis of HRMECs and accelerated regression of tube‐like structure of HRMECs in cell culture. Taken together, TNFα gene knockout delays the regression of laser‐induced CNV in mice. The mechanism underlying the phenotype might include the augmentation of neutrophil population in the treated tissue and attenuation of vascular endothelial cell apoptosis. [ABSTRACT FROM AUTHOR]

Objective: Visual impairment is a common non-motor symptom (NMS) in patients with Parkinson’s disease (PD) and its implications for cognitive impairment remain controversial. We wished to survey the prevalence of visual impairment in Chinese Parkinson’s patients based on the Visual Impairment in Parkinson’s Disease Questionnaire (VIPD-Q), identify the pathogens that lead to visual impairment, and develop a predictive model for cognitive impairment risk in Parkinson’s based on ophthalmic parameters. Methods: A total of 205 patients with Parkinson’s disease and 200 age-matched controls completed the VIPD-Q and underwent neuro-ophthalmologic examinations, including ocular fundus photography and optical coherence tomography. We conducted nomogram analysis and the predictive model was summarized using the multivariate logistic and LASSO regression and verified via bootstrap validation. Results: One or more ophthalmologic symptoms were present in 57% of patients with Parkinson’s disease, compared with 14% of the controls (χ2-test; p < 0.001). The visual impairment questionnaire showed good sensitivity and specificity (area under the curve [AUC] = 0.918, p < 0.001) and a strong correlation with MoCA scores (Pearson r = −0.4652, p < 0.001). Comparing visual impairment scores between pre- and post-deep brain stimulation groups showed that DBS improved visual function (U-test, p < 0.001). The thickness of the retinal nerve fiber layer and vessel percentage area predicted cognitive impairment in PD. Interpretation: The study findings provide novel mechanistic insights into visual impairment and cognitive decline in Parkinson’s disease. The results inform an effective tool for predicting cognitive deterioration in Parkinson’s based on ophthalmic parameters. [ABSTRACT FROM AUTHOR]

Diabetic retinopathy is a serious eye condition that can cause blindness and visual loss. Diabetic retinopathy is a complication in blood sugar levels that affects the fundus of the eye. We have devised an approach that is based on the classification of probable diseases such as hemorrhage and exudates, followed by feature extraction from the pixel level result and a machine learning method to predict the severity of diabetic retinopathy. Anatomical structures in retinal pictures for instance blood vessels, exudates, and micro aneurysms are segmented, and images are identified as standard or DR images using characteristics extracted from these structures and the Gray Level Co-occurrence Matrix in our research (GLCM). The Support Vector Machine classifier's issue area is these extracted candidates. The Support Vector Machine classifier sorts the images to identify whether the candidate extraction conclusions are microaneurysms or not. The algorithms have been simulated, and the results have been presented. The classifier employed is the Support Vector Machine (SVM), which has a 96 percent accuracy rate. [ABSTRACT FROM AUTHOR]

We previously identified that NO derived from neuronal cells acts on glial cells and causes vasodilation in the healthy rat retina via the release of epoxyeicosatrienoic acids (EETs) and prostaglandins (PGs) by activation of the arachidonic acid cascade. However, it is not clear which PG types are involved in these responses. The aim of the present study was to identify prostanoid receptors involved in glial cell-derived vasodilation induced by NO in rat retina. Male Wistar rats were used to examine the effects of intravitreal pretreatment with indomethacin, a cyclooxygenase inhibitor; PF-04418948, a prostanoid EP2 receptor antagonist; and CAY10441, a prostanoid IP receptor antagonist, on the changes in the retinal arteriolar diameter induced by intravitreal administration of NOR3, an NO donor. Retinal arteriolar diameters were measured using ocular fundus images captured with a high-resolution digital camera in vivo. The increase in the retinal arteriolar diameter induced by intravitreal injection of NOR3 was significantly suppressed by intravitreal pretreatment with indomethacin and PF-04418948, but not by CAY10441. The dose of PF-04418948 and CAY10441 injected intravitreally in the present study significantly reduced the increase in the retinal arteriolar diameter induced by prostaglandin E2 (PGE2) and prostaglandin I2 (PGI2), respectively. These results suggest that activation of the arachidonic acid cascade and subsequent stimulation of prostanoid EP2 receptors are involved in rat retinal vasodilatory responses evoked by NO-induced glial cell stimulation. Therefore, glial cell-derived PGE2, similar to EETs, may play an important role in retinal vasodilatory mechanisms. [ABSTRACT FROM AUTHOR]

Recent advances in retinal imaging pathophysiology have shown a new function for biomarkers in Alzheimer's disease diagnosis and prognosis. The significant improvements in Optical coherence tomography (OCT) retinal imaging have led to significant clinical translation, particularly in Alzheimer's disease detection. This systematic review will provide a comprehensive overview of retinal imaging in clinical applications, with a special focus on biomarker analysis for use in Alzheimer's disease detection. Articles on OCT retinal imaging in Alzheimer's disease diagnosis were identified in PubMed, Google Scholar, IEEE Xplore, and Research Gate databases until March 2021. Those studies using simultaneous retinal imaging acquisition were chosen, while those using sequential techniques were rejected. "Alzheimer's disease" and "Dementia" were searched alone and in combination with "OCT" and "retinal imaging". Approximately 1000 publications were searched, and after deleting duplicate articles, 145 relevant studies focused on the diagnosis of Alzheimer's disease utilizing retinal imaging were chosen for study. OCT has recently been demonstrated to be a valuable technique in clinical practice as according to this survey, 57% of the researchers employed optical coherence tomography, 19% used ocular fundus imaging, 13% used scanning laser ophthalmoscopy, and 11% have used multimodal imaging to diagnose Alzheimer disease. Retinal imaging has become an important diagnostic technique for Alzheimer's disease. Given the scarcity of available literature, it is clear that future prospective trials involving larger and more homogeneous groups are necessary, and the work can be expanded by evaluating its significance utilizing a machine-learning platform rather than simply using statistical methodologies. [ABSTRACT FROM AUTHOR]

432 Gochberg, R. I Useful objects: museums, science, and literature in nineteenth-century America i 428 Harris, S. J. I Roots to seeds. 430 Beinart, W. & Dubow, S. I The scientific imagination in South Africa: 1700 to the present i 225 I Contributions to Herpetology i 430 Driver, F., Nesbitt, M. & Cornish, C. (editors). [Extracted from the article]

Casey Albert Wood's The fundus oculi of birds, published in 1917, was the culmination of his decade-long study of the eyes of about a hundred bird species across the avian phylogeny. Wood was a professional ophthalmologist who, during his spare time, was drawn to the study of birds' eyes because of their exceptional visual acuity. His stated goal was to inform taxonomy but that turned out to be pointless. With the assistance of an artist, Arthur William Head, Wood described and illustrated in colour the retina in these birds, with particular attention to the number, size, structure, and position of the pecten. Since the function and evolution of the avian pecten is still poorly known, Wood's book continues to provide a useful point of departure for the study of birds' eyes. [ABSTRACT FROM AUTHOR]

Micro-aneurysms, hemorrhages, and hard exudates are the early lesions of diabetic retinopathy, with micro-aneurysms and small hemorrhages appearing as small and multi-size objects in the retinal fundus image. Though it is essentially a promising technique for object classification in images, the deep learning method needs specific investigation for dealing with retinal fundus images. To this, we propose an inception deconvolutional network, dubbed ID-Net, for multi-class object classification. The ID-Net consists of two inception modules, one with a series of convolutional filters used for extracting multi-scale features and the other with a stack of deconvolutional filters for recovering the features and thus increasing the feature representation capability. As a result, the proposed network succeeds in overcoming the under-fitting and representational bottlenecks, two challenges caused by imbalanced data of retinal fundus images. Experimental results show that the ID-Net can accurately classify early lesions, and achieves higher sensitivity and accuracy than the state-of-the-art evaluation on the public database. [ABSTRACT FROM AUTHOR]

To quantify retinochoroidal vascular parameters using swept-source optical coherence tomography (SS-OCTA) in quiescent posterior and panuveitis. In this cross-sectional study, subjects with quiescent posterior and panuveitis underwent fundus imaging using SS-OCTA (DRI Triton®, Topcon, Japan). The metrics calculated were fractal dimension (FD), foveal avascular zone (FAZ) area, retinal vascularity index (capillary density index-CDI), and choroidal vascularity index (CVI). We included 38 eyes of 20 patients, 9 males aged 34.7 ± 10.5 years, 30 eyes of 30 age- and gender-matched healthy controls, 10 females aged 33.6 ± 8.5 years. Comparing patients with controls, we found a lower FD (p <.001), larger FAZ (p >.001), lower CDI in the superficial plexus (p =.019), and lower CVI (p <.001). We also found lower retinal and choroidal and thicknesses (p <.001 and p =.025, respectively). Patients with quiescent posterior and panuveitis have a significantly reduced retinochoroidal vascular density compared to healthy control subjects. [ABSTRACT FROM AUTHOR]

Diabetic Retinopathy (DR) is the condition caused due to uncontrolled diabetes that can lead to vision impairment. It greatly affects the retinal blood vessels and diminishes the fundus light-sensitive inner coating. Early diagnosis and regular screening of this disease are essential for prompt processing through artificial intelligence techniques. This paper targets assessing the latest techniques for screening and diagnosing DR, including 94 articles based on the Detection and grading of DR. For every analyzed approach, tables are summarized detailing imaging procedure used, datasets, performance metrics used. The research gaps are also highlighted in this paper. Despite the consistent progression and methods actualized in this field, a couple of issues actually should be centered on. The noise and contrast of the image in Image enhancement are still in the infancy stage for high resolution. This study covers a review of existing image techniques, the gold standard and private datasets available, performance measures used for detection and grading of DR. Now the future research focuses on the amalgamation of the dataset as well as techniques to make the generalized technique for detecting the lesion in DR through an automated system. Moreover, various research gaps have also been taken into account for further research. This review is beneficial to the researchers working in the field of medical imaging to screen and diagnose diseases. [ABSTRACT FROM AUTHOR]

One of the complications of Diabetes Mellitus, namely Diabetic Retinopathy (DR) damages the retina of the eye and has five levels of severity: Normal, Mild, Medium, Severe and Proliferate. If not detected and treated, this complication can lead to blindness. Detection and classification of this disease is still done manually by an ophthalmologist using an image of the patient's eye fundus. Manual detection has the disadvantage that it requires an expert in the field and the process is difficult. This research was conducted by detecting and classifying DR disease using Convolutional Neural Network (CNN). The CNN model was built based on the VGG-16 architecture to study the characteristics of the eye fundus images of DR patients. The model was trained using 4750 images which were rescaled to 256 X 256 size and converted to grayscale using the BT-709 (HDTV) method. The CNN-based software with VGG-16 architecture developed resulted in an accuracy of 62% for the detection and classification of 100 test images based on five DR severity classes. This software produces the highest Sensitivity value in the Normal class at 90% and the largest Specificity value in the Mild class at 97.5%. [ABSTRACT FROM AUTHOR]

Introduction: Foveal hypoplasia is defined as a developmental disorder of the macula with a relatively preserved neuroretina. The condition may cause reduced visual acuity and other coexisting ocular disorders. On ophthalmoscopic examination, macular reflexes in the eyes with foveal hypoplasia are either absent or diminished. Morphological changes in the fovea can be visualized by optical coherence tomography (OCT). Four grades of foveal hypoplasia have been distinguished. The aim of the study was to perform an ophthalmoscopic, imaging (OCT), and functional assessment of the retinal macula in children with foveal hypoplasia. Material and methods: The study group consisted of eight pediatric patients (four boys and four girls), aged between 6 and 18 years, who were diagnosed with foveal hypoplasia. The children underwent ophthalmic examinations including the assessment of visual acuity and eye fundus, and macular OCT. Results: Visual acuity was impaired in one or both eyes in seven children, ranging from the sense of light (in the eye with coexisting optic nerve pathologies) to 5/6. In the majority of children, macular reflexes were found to be absent or diminished either in one or both eyes. In all the patients, foveal hypoplasia was diagnosed on the basis of OCT findings and graded. Conclusions: Abnormal ophthalmoscopic appearance of the macula, exhibiting anomalous light reflexes, is an indication for a more detailed diagnostic approach. Our studies show that unexplained reduced visual acuity with preserved macular reflexes also justifies performing a non-invasive OCT examination of the macula. Macular OCT imaging is necessary for making the diagnosis of foveal hypoplasia and grading the severity of the condition. Severe foveal hypoplasia reduces visual acuity and may impair other visual functions. [ABSTRACT FROM AUTHOR]