Search

This study tested if a high-resolution, multi-modal, multi-scale retinal imaging instrument can provide novel information about structural abnormalities in vivo. The study examined 11 patients with very mild to moderate non-proliferative diabetic retinopathy (NPDR) and 10 healthy subjects using fundus photography, optical coherence tomography (OCT), OCT angiography (OCTA), adaptive optics scanning laser ophthalmoscopy (AO-SLO), adaptive optics OCT and OCTA (AO-OCT(A)). Of 21 eyes of 11 patients, 11 had very mild NPDR, 8 had mild NPDR, 2 had moderate NPDR, and 1 had no retinopathy. Using AO-SLO, capillary looping, inflections and dilations were detected in 8 patients with very mild or mild NPDR, and microaneurysms containing hyperreflective granular elements were visible in 9 patients with mild or moderate NPDR. Most of the abnormalities were seen to be perfused in the corresponding OCTA scans while a few capillary loops appeared to be occluded or perfused at a non-detectable flow rate, possibly because of hypoperfusion. In one patient with moderate NPDR, non-perfused capillaries, also called ghost vessels, were identified by alignment of corresponding en face AO-OCT and AO-OCTA images. The combination of multiple non-invasive imaging methods could identify prominent microscopic abnormalities in diabetic retinopathy earlier and more detailed than conventional fundus imaging devices. [ABSTRACT FROM AUTHOR]

Optical coherence tomography angiography (OCTA) is widely used for non-invasive retinal vascular imaging, but the OCTA methods used to assess retinal perfusion vary. We evaluated the different methods used to assess retinal perfusion between OCTA studies. MEDLINE and Embase were searched from 2014 to August 2021. We included prospective studies including ≥ 50 participants using OCTA to assess retinal perfusion in either global retinal or systemic disorders. Risk of bias was assessed using the National Institute of Health quality assessment tool for observational cohort and cross-sectional studies. Heterogeneity of data was assessed by Q statistics, Chi-square test, and I2 index. Of the 5974 studies identified, 191 studies were included in this evaluation. The selected studies employed seven OCTA devices, six macula volume dimensions, four macula subregions, nine perfusion analyses, and five vessel layer definitions, totalling 197 distinct methods of assessing macula perfusion and over 7000 possible combinations. Meta-analysis was performed on 88 studies reporting vessel density and foveal avascular zone area, showing lower retinal perfusion in patients with diabetes mellitus than in healthy controls, but with high heterogeneity. Heterogeneity was lowest and reported vascular effects strongest in superficial capillary plexus assessments. Systematic review of OCTA studies revealed massive heterogeneity in the methods employed to assess retinal perfusion, supporting calls for standardisation of methodology. [ABSTRACT FROM AUTHOR]

Previous studies have demonstrated that the visual system adapts to the specific aberration pattern of an individual's eye. Alterations to this pattern can lead to reduced visual performance, even when the Root Mean Square (RMS) of the wavefront error remains constant. However, it is well-established that ocular aberrations are dynamic and can change with factors such as pupil size and accommodation. This raises an intriguing question: can the neural system adapt to continuously changing aberration patterns? To address this question, we measured the ocular aberrations in four subjects under various natural viewing conditions, which included changes in accommodative state and pupil size. We subsequently computed the associated Point Spread Functions (PSFs). For each subject, we examined the stability in the orientation of the PSFs and analyzed the cross-correlation between different PSFs. These findings were then compared to the characteristics of a distribution featuring PSF shapes akin to random variations. Our results indicate that the changes observed in the PSFs are not substantial enough to produce a PSF shape distribution resembling random variations. This lends support to the notion that neural adaptation is indeed a viable mechanism even in response to continuously changing aberration patterns. [ABSTRACT FROM AUTHOR]

Diabetes mellitus (DM) is a prevalent chronic metabolic disorder linked to increased morbidity and mortality. With a significant portion of cases remaining undiagnosed, particularly in the Middle East North Africa (MENA) region, more accurate and accessible diagnostic methods are essential. Current diagnostic tests like fasting plasma glucose (FPG), oral glucose tolerance tests (OGTT), random plasma glucose (RPG), and hemoglobin A1c (HbA1c) have limitations, leading to misclassifications and discomfort for patients. The aim of this study is to enhance diabetes diagnosis accuracy by developing an improved predictive model using retinal images from the Qatari population, addressing the limitations of current diagnostic methods. This study explores an alternative approach involving retinal images, building upon the DiaNet model, the first deep learning model for diabetes detection based solely on retinal images. The newly proposed DiaNet v2 model is developed using a large dataset from Qatar Biobank (QBB) and Hamad Medical Corporation (HMC) covering wide range of pathologies in the the retinal images. Utilizing the most extensive collection of retinal images from the 5545 participants (2540 diabetic patients and 3005 control), DiaNet v2 is developed for diabetes diagnosis. DiaNet v2 achieves an impressive accuracy of over 92%, 93% sensitivity, and 91% specificity in distinguishing diabetic patients from the control group. Given the high prevalence of diabetes and the limitations of existing diagnostic methods in clinical setup, this study proposes an innovative solution. By leveraging a comprehensive retinal image dataset and applying advanced deep learning techniques, DiaNet v2 demonstrates a remarkable accuracy in diabetes diagnosis. This approach has the potential to revolutionize diabetes detection, providing a more accessible, non-invasive and accurate method for early intervention and treatment planning, particularly in regions with high diabetes rates like MENA. [ABSTRACT FROM AUTHOR]

Microperimetry (MP) is a psychometric examination combining retinal imaging and functional sensitivity testing with an increasing importance due to its potential use as clinical study outcome. We investigated the repeatability of pointwise retinal sensitivity (PWS) on the most advanced commercially available MP devices under their standard setting in a healthy aging population. Two successive MP examinations on both MP-3 (NIDEK CO., Ltd., Gamagori, Japan) and MAIA (CenterVue S.p.A. (iCare), Padova, Italy) were performed on healthy aging subjects in a randomized order. PWS repeatability was analysed for different macular regions and age groups using Bland-Altmann coefficients of repeatability (CoR). A total of 3600 stimuli from 20 healthy individuals with a mean age of 70 (11) years were included. Mean CoR in dB were ±4.61 for MAIA and ±4.55 for MP-3 examinations. A lower repeatability (p=0.005) was detected in the central millimetre on MAIA examinations. Higher subject age was associated with a lower repeatability of PWS on both devices (both p=0.003). Intra-device correlation was good (MAIA: 0.79 [0.76–0.81]; MP-3: 0.72 [0.68–0.76]) whereas a moderate mean inter-device correlation (0.6 [0.55–0.65]) could be detected. In conclusion, older subjects and the foveal region are associated with a worse pointwise repeatability. [ABSTRACT FROM AUTHOR]

One significant ocular symptom of neuro-ophthalmic disorders of the optic disk (OD) is optic disk edema (ODE). The etiologies of ODE are broad, with various symptoms and effects. Early detection of ODE can prevent potential vision loss and fatal vision problems. The texture of edematous OD significantly differs from the non-edematous OD in retinal images. As a result, techniques that usually work for non-edematous cases may not work well for edematous cases. We propose a fully automatic OD classification of edematous and non-edematous OD on fundus image collections containing a mixture of edematous and non-edematous ODs. The proposed algorithm involved localization, segmentation, and classification of edematous and non-edematous OD. The factorized gradient vector flow (FGVF) was used to segment the ODs. The OD type was classified using a linear support vector machine (SVM) based on 27 features extracted from the vessels, GLCM, color, and intensity line profile. The proposed method was tested on 295 images with 146 edematous cases and 149 non-edematous cases from three datasets. The segmentation achieves an average precision of 88.41%, recall of 89.35%, and F1-Score of 86.53%. The average classification accuracy is 99.40% and outperforms the state-of-the-art method by 3.43%. [ABSTRACT FROM AUTHOR]

Ultra-widefield retinal imaging is increasingly used in ophthalmology and optometry practices to image patients identifying peripheral abnormalities. However, the clinical relevance of these peripheral retinal abnormalities is unclear. This cross-sectional study aims to firstly validate a new grading system, secondly, assess the prevalence of peripheral retinal abnormalities in retinal patients, and finally understand how peripheral findings may associate with retinal disease. Ultra-widefield pseudocolor fundus images were taken from the eyes of clinic patients. Demographic data and clinical diagnosis for each patient was noted. The grading system was validated using masked retinal specialists. Logistic regression identified associations between retinal disease and peripheral retinal findings. Using the grading system, inter-observer agreement was 76.1% with Cohen's Kappa coefficient 0.542 (p < 0.0001) and the test–retest agreement was 95.1% with Kappa 0.677(p < 0.0001). 971 images were included, with 625 eyes (64.4%) having peripheral abnormalities. Peripheral drusen was the most common abnormality (n = 221, 22.76%) and correlated with age-related macular degeneration (p < 0.001). Novel correlations were also identified between diabetic retinopathy and retinal pigmentation as well as pigmentary degeneration. This study provides a validated system for identifying peripheral abnormalities and adds to literature highlighting peripheral retinal associations with retinal disease which would benefit from further study. [ABSTRACT FROM AUTHOR]

Deep neural networks have been increasingly proposed for automated screening and diagnosis of retinal diseases from optical coherence tomography (OCT), but often provide high-confidence predictions on out-of-distribution (OOD) cases, compromising their clinical usage. With this in mind, we performed an in-depth comparative analysis of the state-of-the-art uncertainty estimation methods for OOD detection in retinal OCT imaging. The analysis was performed within the use-case of automated screening and staging of age-related macular degeneration (AMD), one of the leading causes of blindness worldwide, where we achieved a macro-average area under the curve (AUC) of 0.981 for AMD classification. We focus on a few-shot Outlier Exposure (OE) method and the detection of near-OOD cases that share pathomorphological characteristics with the inlier AMD classes. Scoring the OOD case based on the Cosine distance in the feature space from the penultimate network layer proved to be a robust approach for OOD detection, especially in combination with the OE. Using Cosine distance and only 8 outliers exposed per class, we were able to improve the near-OOD detection performance of the OE with Reject Bucket method by ≈ 10% compared to without OE, reaching an AUC of 0.937. The Cosine distance served as a robust metric for OOD detection of both known and unknown classes and should thus be considered as an alternative to the reject bucket class probability in OE approaches, especially in the few-shot scenario. The inclusion of these methodologies did not come at the expense of classification performance, and can substantially improve the reliability and trustworthiness of the resulting deep learning-based diagnostic systems in the context of retinal OCT. [ABSTRACT FROM AUTHOR]

Vascular pulsation at the optic nerve head (ONH) reflects vessel properties. Reduction in the stimulated retinal vasodilatory capacity has been reported in diabetes, but its relation with vascular pulsation is unknown. Here we report a new retinal imaging system for correlative assessment of ONH vascular pulsation and stimulated retinal vasodilation. Retinal reflectance images were acquired before and during light flicker stimulation to quantify arterial and venous vasodilation (DAR, DVR) in subjects with and without diabetic retinopathy (N = 25). ONH vascular pulsation amplitude and frequency (PA, PF), were quantified by curve fitting of periodic intensity waveforms acquired in retinal vasculature (RV) and ONH tissue (ONHT) regions. The relationships between pulsation metrics, heart rate (HR), intraocular pressure (IOP), and vasodilatory responses were evaluated. Pulsation metrics were not significantly different between regions (p ≥ 0.70). In RV, inter-image variabilities of PA and PF were 10% and 6%, whereas inter-observer variabilities were 7% and 2% respectively. In both regions, PF was correlated with HR (p ≤ 0.001). PA was associated with DAR in both regions (p ≤ 0.03), but only with DVR in RV (p ≤ 0.05). Overall, ONH vascular pulsation was associated with stimulated retinal vasodilation, suggesting diabetes may have concomitant effects on retinal vasculature compliance and neurovascular coupling. [ABSTRACT FROM AUTHOR]

Deep neural networks have been increasingly proposed for automated screening and diagnosis of retinal diseases from optical coherence tomography (OCT), but often provide high-confidence predictions on out-of-distribution (OOD) cases, compromising their clinical usage. With this in mind, we performed an in-depth comparative analysis of the state-of-the-art uncertainty estimation methods for OOD detection in retinal OCT imaging. The analysis was performed within the use-case of automated screening and staging of age-related macular degeneration (AMD), one of the leading causes of blindness worldwide, where we achieved a macro-average area under the curve (AUC) of 0.981 for AMD classification. We focus on a few-shot Outlier Exposure (OE) method and the detection of near-OOD cases that share pathomorphological characteristics with the inlier AMD classes. Scoring the OOD case based on the Cosine distance in the feature space from the penultimate network layer proved to be a robust approach for OOD detection, especially in combination with the OE. Using Cosine distance and only 8 outliers exposed per class, we were able to improve the near-OOD detection performance of the OE with Reject Bucket method by ≈ 10% compared to without OE, reaching an AUC of 0.937. The Cosine distance served as a robust metric for OOD detection of both known and unknown classes and should thus be considered as an alternative to the reject bucket class probability in OE approaches, especially in the few-shot scenario. The inclusion of these methodologies did not come at the expense of classification performance, and can substantially improve the reliability and trustworthiness of the resulting deep learning-based diagnostic systems in the context of retinal OCT. [ABSTRACT FROM AUTHOR]

Spectral imaging holds great promise for the non-invasive diagnosis of retinal diseases. However, to acquire a spectral datacube, conventional spectral cameras require extensive scanning, leading to a prolonged acquisition. Therefore, they are inapplicable to retinal imaging because of the rapid eye movement. To address this problem, we built a coded aperture snapshot spectral imaging fundus camera, which captures a large-sized spectral datacube in a single exposure. Moreover, to reconstruct a high-resolution image, we developed a robust deep unfolding algorithm using a state-of-the-art spectral transformer in the denoising network. We demonstrated the performance of the system through various experiments, including imaging standard targets, utilizing an eye phantom, and conducting in vivo imaging of the human retina. [ABSTRACT FROM AUTHOR]

Independent validation studies of automatic diabetic retinopathy screening systems have recently shown a drop of screening performance on external data. Beyond diabetic retinopathy, this study investigates the generalizability of deep learning (DL) algorithms for screening various ocular anomalies in fundus photographs, across heterogeneous populations and imaging protocols. The following datasets are considered: OPHDIAT (France, diabetic population), OphtaMaine (France, general population), RIADD (India, general population) and ODIR (China, general population). Two multi-disease DL algorithms were developed: a Single-Dataset (SD) network, trained on the largest dataset (OPHDIAT), and a Multiple-Dataset (MD) network, trained on multiple datasets simultaneously. To assess their generalizability, both algorithms were evaluated whenever training and test data originate from overlapping datasets or from disjoint datasets. The SD network achieved a mean per-disease area under the receiver operating characteristic curve (mAUC) of 0.9571 on OPHDIAT. However, it generalized poorly to the other three datasets (mAUC < 0.9). When all four datasets were involved in training, the MD network significantly outperformed the SD network (p = 0.0058), indicating improved generality. However, in leave-one-dataset-out experiments, performance of the MD network was significantly lower on populations unseen during training than on populations involved in training (p < 0.0001), indicating imperfect generalizability. [ABSTRACT FROM AUTHOR]

Retinal disease accounts significantly for visual impairment and blindness. An important role in the pathophysiology of retinal disease and aging is attributed to lipofuscin, a complex of fluorescent metabolites. Fundus autofluorescence (AF) imaging allows non-invasive mapping of lipofuscin and is a key technology to diagnose and monitor retinal disease. However, currently used short-wavelength (SW) excitation light has several limitations, including glare and discomfort during image acquisition, reduced image quality in case of lens opacities, limited visualization of the central retina, and potential retinal light toxicity. Here, we establish a novel imaging modality which uses red excitation light (R-AF) and overcomes these drawbacks. R-AF images are high-quality, high-contrast fundus images and image interpretation may build on clinical experience due to similar appearance of pathology as on SW-AF images. Additionally, R-AF images may uncover disease features that previously remained undetected. The R-AF signal increases with higher abundance of lipofuscin and does not depend on photopigment bleaching or on the amount of macular pigment. Improved patient comfort, limited effect of cataract on image quality, and lack of safety concerns qualify R-AF for routine clinical monitoring, e.g. for patients with age-related macular degeneration, Stargardt disease, or for quantitative analysis of AF signal intensity. [ABSTRACT FROM AUTHOR]

Age-related Macular Degeneration (AMD), a retinal disease that affects the macula, can be caused by aging abnormalities in number of different cells and tissues in the retina, retinal pigment epithelium, and choroid, leading to vision loss. An advanced form of AMD, called exudative or wet AMD, is characterized by the ingrowth of abnormal blood vessels beneath or into the macula itself. The diagnosis is confirmed by either fundus auto-fluorescence imaging or optical coherence tomography (OCT) supplemented by fluorescein angiography or OCT angiography without dye. Fluorescein angiography, the gold standard diagnostic procedure for AMD, involves invasive injections of fluorescent dye to highlight retinal vasculature. Meanwhile, patients can be exposed to life-threatening allergic reactions and other risks. This study proposes a scale-adaptive auto-encoder-based model integrated with a deep learning model that can detect AMD early by automatically analyzing the texture patterns in color fundus imaging and correlating them to the vasculature activity in the retina. Moreover, the proposed model can automatically distinguish between AMD grades assisting in early diagnosis and thus allowing for earlier treatment of the patient's condition, slowing the disease and minimizing its severity. Our model features two main blocks, the first is an auto-encoder-based network for scale adaption, and the second is a convolutional neural network (CNN) classification network. Based on a conducted set of experiments, the proposed model achieves higher diagnostic accuracy compared to other models with accuracy, sensitivity, and specificity that reach 96.2%, 96.2%, and 99%, respectively. [ABSTRACT FROM AUTHOR]

Diabetic retinopathy (DR) is a diabetes complication that can cause vision loss among patients due to damage to blood vessels in the retina. Early retinal screening can avoid the severe consequences of DR and enable timely treatment. Nowadays, researchers are trying to develop automated deep learning-based DR segmentation tools using retinal fundus images to help Ophthalmologists with DR screening and early diagnosis. However, recent studies are unable to design accurate models due to the unavailability of larger training data with consistent and fine-grained annotations. To address this problem, we propose a semi-supervised multitask learning approach that exploits widely available unlabelled data (i.e., Kaggle-EyePACS) to improve DR segmentation performance. The proposed model consists of novel multi-decoder architecture and involves both unsupervised and supervised learning phases. The model is trained for the unsupervised auxiliary task to effectively learn from additional unlabelled data and improve the performance of the primary task of DR segmentation. The proposed technique is rigorously evaluated on two publicly available datasets (i.e., FGADR and IDRiD) and results show that the proposed technique not only outperforms existing state-of-the-art techniques but also exhibits improved generalisation and robustness for cross-data evaluation. [ABSTRACT FROM AUTHOR]

Fixating a small dot is a universal technique for stabilizing gaze in vision and eye movement research, and for clinical imaging of normal and diseased retinae. During fixation, microsaccades and drifts occur that presumably benefit vision, yet microsaccades compromise image stability and usurp task attention. Previous work suggested that microsaccades and smooth pursuit catch-up saccades are controlled by similar mechanisms. This, and other previous work showing fewer catch-up saccades during smooth pursuit of peripheral targets suggested that a peripheral target might similarly mitigate microsaccades. Here, human observers fixated one of three stimuli: a small central dot, the center of a peripheral, circular array of small dots, or a central/peripheral stimulus created by combining the two. The microsaccade rate was significantly lower with the peripheral array than with the dot. However, inserting the dot into the array increased the microsaccade rate to single-dot levels. Drift speed also decreased with the peripheral array, both with and without the central dot. Eye position variability was higher with the array than with the composite stimulus. The results suggest that analogous to the foveal pursuit, foveating a stationary target engages the saccadic system likely compromising retinal-image stability. In contrast, fixating a peripheral stimulus improves stability, thereby affording better retinal imaging and releasing attention for experimental tasks. [ABSTRACT FROM AUTHOR]

Real-time fundus images captured to detect multiple diseases are prone to different quality issues like illumination, noise, etc., resulting in less visibility of anomalies. So, enhancing the retinal fundus images is essential for a better prediction rate of eye diseases. In this paper, we propose Lab color space-based enhancement techniques for retinal image enhancement. Existing research works does not consider the relation between color spaces of the fundus image in selecting a specific channel to perform retinal image enhancement. Our unique contribution to this research work is utilizing the color dominance of an image in quantifying the distribution of information in the blue channel and performing enhancement in Lab space followed by a series of steps to optimize overall brightness and contrast. The test set of the Retinal Fundus Multi-disease Image Dataset is used to evaluate the performance of the proposed enhancement technique in identifying the presence or absence of retinal abnormality. The proposed technique achieved an accuracy of 89.53 percent. [ABSTRACT FROM AUTHOR]

Cynomolgus monkeys (Macaca fascicularis) are commonly used in pre-clinical ocular studies. However, studies that report the morphological features of the macaque retina are based only on minimal sample sizes; therefore, little is known about the normal distribution and background variation. This study was conducted using optical coherence tomography (OCT) imaging to investigate the variations in retinal volumes of healthy cynomolgus monkeys and the effects of sex, origin, and eye side on the retinal volumes to establish a comprehensive reference database. A machine-learning algorithm was employed to segment the retina within the OCT data (i.e., generated pixel-wise labels). Furthermore, a classical computer vision algorithm has identified the deepest point in a foveolar depression. The retinal volumes were determined and analyzed based on this reference point and segmented retinal compartments. Notably, the overall foveolar mean volume in zone 1, which is the region of the sharpest vision, was 0.205 mm3 (range 0.154–0.268 mm3), with a relatively low coefficient of variation of 7.9%. Generally, retinal volumes exhibit a relatively low degree of variation. However, significant differences in the retinal volumes due to the monkey's origin were identified. Additionally, sex had a significant impact on the paracentral retinal volume. Therefore, the origin and sex of cynomolgus monkeys should be considered when evaluating the macaque retinal volumes based on this dataset. [ABSTRACT FROM AUTHOR]

This cross-sectional study aimed to investigate the hypothesis that permanent capillary damage may underlie the long-term COVID-19 sequela by quantifying the retinal vessel integrity. Participants were divided into three subgroups; Normal controls who had not been affected by COVID-19, mild COVID-19 cases who received out-patient care, and severe COVID-19 cases requiring intensive care unit (ICU) admission and respiratory support. Patients with systemic conditions that may affect the retinal vasculature before the diagnosis of COVID-19 infection were excluded. Participants underwent comprehensive ophthalmologic examination and retinal imaging obtained from Spectral-Domain Optical Coherence Tomography (SD-OCT), and vessel density using OCT Angiography. Sixty-one eyes from 31 individuals were studied. Retinal volume was significantly decreased in the outer 3 mm of the macula in the severe COVID-19 group (p = 0.02). Total retinal vessel density was significantly lower in the severe COVID-19 group compared to the normal and mild COVID-19 groups (p = 0.004 and 0.0057, respectively). The intermediate and deep capillary plexuses in the severe COVID-19 group were significantly lower compared to other groups (p < 0.05). Retinal tissue and microvascular loss may be a biomarker of COVID-19 severity. Further monitoring of the retina in COVID-19-recovered patients may help further understand the COVID-19 sequela. [ABSTRACT FROM AUTHOR]

One of the most important retinal diseases is Diabetic Retinopathy (DR) which can lead to serious damage to vision if remains untreated. Red-lesions are from important demonstrations of DR helping its identification in early stages. The detection and verification of them is helpful in the evaluation of disease severity and progression. In this paper, a novel image processing method is proposed for extracting red-lesions from fundus images. The method works based on finding and extracting the unique morphological features of red-lesions. After quality improvement of images, a pixel-based verification is performed in the proposed method to find the ones which provide a significant intensity change in a curve-like neighborhood. In order to do so, a curve is considered around each pixel and the intensity changes around the curve boundary are considered. The pixels for which it is possible to find such curves in at least two directions are considered as parts of red-lesions. The simplicity of computations, the high accuracy of results, and no need to post-processing operations are the important characteristics of the proposed method endorsing its good performance. [ABSTRACT FROM AUTHOR]

The aim of this study was to assess the relationship of clinical characteristics to the rate of retinal thinning in eyes with diabetic macular edema (DME) treated with anti-vascular endothelial growth factor (VEGF) therapy. We analyzed subjects with a long-term follow-up (≥ 3 years) and evidence of resolved DME after the initiation of anti-VEGF therapy (baseline visit). To measure the long-term rate of retinal thinning during treatment, a second visit (first visit with evidence of resolved DME after 3 years) was also considered. A longitudinal quantitative topographical assessment of the inner and outer retinal thicknesses was provided. Clinical characteristics were associated with the rate of longitudinal retinal thinning. We included 56 eyes (50 patients) in the analysis. A significant longitudinal thinning in the inner and outer retina was detected in all the analyzed regions (p values between 0.027 and < 0.0001). In the multivariable analysis, type of diabetes (type 2 vs. type 1) was associated with increased foveal inner retinal thinning (p = 0.019). A higher number of subfoveal neuroretinal detachment during follow-up (p = 0.006) was associated with faster rates of foveal outer retinal thinning. Type of diabetes (p < 0.0001), higher age (p = 0.033) and cystoid macular edema phenotype (p = 0.040) were associated with increased parafoveal inner retinal thinning. Gender (p = 0.003) and diabetic retinopathy stage (p = 0.013) were associated with faster rates of perifoveal inner retinal thinning, while diabetic retinopathy stage (p = 0.036) was associated with increased perifoveal outer retinal thinning. In conclusion, clinical factors, including DME phenotypes, were associated with the rates of retinal thinning in patients undergoing anti-VEGF treatment. [ABSTRACT FROM AUTHOR]

One of the most salient diseases of retina is Diabetic Retinopathy (DR) which may lead to irreparable damages to eye vision in the advanced phases. A large number of the people infected with diabetes experience DR. The early identification of DR signs facilitates the treatment process and prevents from blindness. Hard Exudates (HE) are bright lesions appeared in retinal fundus images of DR patients. Thus, the detection of HEs is an important task preventing the progress of DR. However, the detection of HEs is a challenging process due to their different appearance features. In this paper, an automatic method for the identification of HEs with various sizes and shapes is proposed. The method works based on a pixel-wise approach. It considers several semi-circular regions around each pixel. For each semi-circular region, the intensity changes around several directions and non-necessarily equal radiuses are computed. All pixels for which several semi-circular regions include considerable intensity changes are considered as the pixels located in HEs. In order to reduce false positives, an optic disc localization method is proposed in the post-processing phase. The performance of the proposed method has been evaluated on DIARETDB0 and DIARETDB1 datasets. The experimental results confirm the improved performance of the suggested method in term of accuracy. [ABSTRACT FROM AUTHOR]

Many studies have assessed structure–function relations in glaucoma, but most without topographical comparison across the central 30°. We present a method for assessing structure–function relations with en face images of retinal nerve fiber layer (RNFL) bundles allowing topographical comparison across much of this retinal area. Forty-four patients with glaucoma (median age 61 years) were recruited and tested with Optical Coherence Tomography (OCT) and perimetry. Six rectangular volume scans were gathered, and then montaged to provide en face views of the RNFL bundles. We calculated the proportion of locations showing a perimetric defect that also showed an en face RNFL defect; and the proportion of locations falling on an RNFL defect that also showed a perimetric defect. A perimetric defect for a location was defined as a total deviation (TD) value equal to or deeper than -4 dB. We found that the median (IQR) number of locations with abnormal RNFL bundle reflectance that also had abnormal TD was 78% (60%) and for locations with abnormal TD that also had abnormal RNFL bundle reflectance was 75% (44%). We demonstrated a potential approach for structure–function assessment in glaucoma by presenting a topographic reflectance map, confirming results of previous studies and including larger retinal regions. [ABSTRACT FROM AUTHOR]

In the retina, several molecules involved in metabolism, the visual cycle, and other roles exhibit intrinsic fluorescence. The overall properties of retinal fluorescence depend on changes to the composition of these molecules and their environmental interactions due to transient functional shifts, especially in disease. This behooves the understanding of the origins and deviations of these properties within the multilayered retina at high lateral and axial resolution. Of particular interest is the fluorescence lifetime, a potential biomarker of function and disease independent of fluorescence intensity that can be measured in the retina with adaptive optics fluorescence lifetime ophthalmoscopy (AOFLIO). This work demonstrates the utility of the phasor method of analysis, an alternate approach to traditional multiexponential fitting, to evaluate photoreceptor two-photon excited AOFLIO data and separate them based on functional differences. Phasor analysis on fluorescence lifetime decay data allowed the repeatable segregation of S from M/L cones, likely from differences in functional or metabolic demands. Furthermore, it is possible to track the lifetime changes in S cones after photodamage. Phasor analysis increases the sensitivity of AOFLIO to functional differences between cells and has the potential to improve our understanding of pathways involved in normal and diseased conditions at the cellular scale throughout the retina. [ABSTRACT FROM AUTHOR]

Diabetic retinopathy (DR) at risk of vision loss (referable DR) needs to be identified by retinal screening and referred to an ophthalmologist. Existing automated algorithms have mostly been developed from images acquired with high cost mydriatic retinal cameras and cannot be applied in the settings used in most low- and middle-income countries. In this prospective multicentre study, we developed a deep learning system (DLS) that detects referable DR from retinal images acquired using handheld non-mydriatic fundus camera by non-technical field workers in 20 sites across India. Macula-centred and optic-disc-centred images from 16,247 eyes (9778 participants) were used to train and cross-validate the DLS and risk factor based logistic regression models. The DLS achieved an AUROC of 0.99 (1000 times bootstrapped 95% CI 0.98–0.99) using two-field retinal images, with 93.86 (91.34–96.08) sensitivity and 96.00 (94.68–98.09) specificity at the Youden's index operational point. With single field inputs, the DLS reached AUROC of 0.98 (0.98–0.98) for the macula field and 0.96 (0.95–0.98) for the optic-disc field. Intergrader performance was 90.01 (88.95–91.01) sensitivity and 96.09 (95.72–96.42) specificity. The image based DLS outperformed all risk factor-based models. This DLS demonstrated a clinically acceptable performance for the identification of referable DR despite challenging image capture conditions. [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]

Optical Coherence Tomography (OCT) is a useful imaging modality facilitating the capturing process from retinal layers. In the salient diseases of retina, cysts are formed in retinal layers. Therefore, the identification of cysts in the retinal layers is of great importance. In this paper, a new method is proposed for the rapid detection of cystic OCT B-scans. In the proposed method, a Hidden Markov Model (HMM) is used for mathematically modelling the existence of cyst. In fact, the existence of cyst in the image can be considered as a hidden state. Since the existence of cyst in an OCT B-scan depends on the existence of cyst in the previous B-scans, HMM is an appropriate tool for modelling this process. In the first phase, a number of features are extracted which are Harris, KAZE, HOG, SURF, FAST, Min-Eigen and feature extracted by deep AlexNet. It is shown that the feature with the best discriminating power is the feature extracted by AlexNet. The features extracted in the first phase are used as observation vectors to estimate the HMM parameters. The evaluation results show the improved performance of HMM in terms of accuracy. [ABSTRACT FROM AUTHOR]

Hemorrhage segmentation in retinal images is challenging because the sizes and shapes vary for each hemorrhage, the intensity is close to the blood vessels and macula, and the intensity is often nonuniform, especially for large hemorrhages. Hemorrhage segmentation in mobile-phone retinal images is even more challenging because mobile-phone retinal images usually have poorer contrast, more shadows, and uneven illumination compared to those obtained from the table-top ophthalmoscope. In this work, the proposed KMMRC-INRG method enhances the hemorrhage segmentation performance with nonuniform intensity in poor lighting conditions on mobile-phone images. It improves the uneven illumination of mobile-phone retinal images using a proposed method, K-mean multiregion contrast enhancement (KMMRC). It also enhances the boundary segmentation of the hemorrhage blobs using a novel iterative NICK thresholding region growing (INRG) method before applying an SVM classifier based on hue, saturation, and brightness features. This approach can achieve as high as 80.18%, 91.26%, 85.36%, and 80.08% for recall, precision, F1-measure, and IoU, respectively. The F1-measure score improves up to 19.02% compared to a state-of-the-art method DT-HSVE tested on the same full dataset and as much as 58.88% when considering only images with large-size hemorrhages. [ABSTRACT FROM AUTHOR]

Fifty million people worldwide are affected by dementia, a heterogeneous neurodegenerative condition encompassing diseases such as Alzheimer's, vascular dementia, and Parkinson's. For them, cognitive decline is often the first marker of the pathology after irreversible brain damage has already occurred. Researchers now believe that structural and functional alterations of the brain vasculature could be early precursors of the diseases and are looking at how functional imaging could provide an early diagnosis years before irreversible clinical symptoms. In this preclinical pilot study, we proposed using functional ultrasound (fUS) on the retina to assess neurovascular alterations non-invasively, bypassing the skull limitation. We demonstrated for the first time the use of functional ultrasound in the retina and applied it to characterize the retinal hemodynamic response function in vivo in rats following a visual stimulus. We then demonstrated that retinal fUS could measure robust neurovascular coupling alterations between wild-type rats and TgF344-AD rat models of Alzheimer's disease. We observed an average relative increase in blood volume of 21% in the WT versus 37% for the TG group (p = 0.019). As a portable, non-invasive and inexpensive technique, rfUS is a promising functional screening tool in clinics for dementia years before symptoms. [ABSTRACT FROM AUTHOR]

Realistic image synthesis based on deep learning is an invaluable technique for developing high-performance computer aided diagnosis systems while protecting patient privacy. However, training a generative adversarial network (GAN) for image synthesis remains challenging because of the large amounts of data required for training various kinds of image features. This study aims to synthesize retinal images indistinguishable from real images and evaluate the efficacy of the synthesized images having a specific disease for augmenting class imbalanced datasets. The synthesized images were validated via image Turing tests, qualitative analysis by retinal specialists, and quantitative analyses on amounts and signal-to-noise ratios of vessels. The efficacy of synthesized images was verified by deep learning-based classification performance. Turing test shows that accuracy, sensitivity, and specificity of 54.0 ± 12.3%, 71.1 ± 18.8%, and 36.9 ± 25.5%, respectively. Here, sensitivity represents correctness to find real images among real datasets. Vessel amounts and average SNR comparisons show 0.43% and 1.5% difference between real and synthesized images. The classification performance after augmenting synthesized images outperforms every ratio of imbalanced real datasets. Our study shows the realistic retina images were successfully generated with insignificant differences between the real and synthesized images and shows great potential for practical applications. [ABSTRACT FROM AUTHOR]

Microaneurysms (MAs) are pathognomonic signs that help clinicians to detect diabetic retinopathy (DR) in the early stages. Automatic detection of MA in retinal images is an active area of research due to its application in screening processes for DR which is one of the main reasons of blindness amongst the working-age population. The focus of these works is on the automatic detection of MAs in en face retinal images like fundus color and Fluorescein Angiography (FA). On the other hand, detection of MAs from Optical Coherence Tomography (OCT) images has 2 main advantages: first, OCT is a non-invasive imaging technique that does not require injection, therefore is safer. Secondly, because of the proven application of OCT in detection of Age-Related Macular Degeneration, Diabetic Macular Edema, and normal cases, thanks to detecting MAs in OCT, extensive information is obtained by using this imaging technique. In this research, the concentration is on the diagnosis of MAs using deep learning in the OCT images which represent in-depth structure of retinal layers. To this end, OCT B-scans should be divided into strips and MA patterns should be searched in the resulted strips. Since we need a dataset comprising OCT image strips with suitable labels and such large labelled datasets are not yet available, we have created it. For this purpose, an exact registration method is utilized to align OCT images with FA photographs. Then, with the help of corresponding FA images, OCT image strips are created from OCT B-scans in four labels, namely MA, normal, abnormal, and vessel. Once the dataset of image strips is prepared, a stacked generalization (stacking) ensemble of four fine-tuned, pre-trained convolutional neural networks is trained to classify the strips of OCT images into the mentioned classes. FA images are used once to create OCT strips for training process and they are no longer needed for subsequent steps. Once the stacking ensemble model is obtained, it will be used to classify the OCT strips in the test process. The results demonstrate that the proposed framework classifies overall OCT image strips and OCT strips containing MAs with accuracy scores of 0.982 and 0.987, respectively. [ABSTRACT FROM AUTHOR]

The current study aimed to investigate diabetic retinopathy (DR) screening and treatment coverages among diabetic patients evaluated through the Brazilian National Health Insurance from 2014 to 2019. The Brazilian Public Health System Information Database was used as the primary data source. DR screening coverage was calculated as the rate of procedures of clinical dilated fundus exam and color fundus photograph over the number of diabetic patients. DR treatment coverage was calculated as the rate of procedures of intravitreal injection, photocoagulation, and panretinal photocoagulation over the number of diabetic patients presumably in need of DR treatment. The overall screening coverage increased from 12.1% in 2014 to 21.2% in 2019 (p < 0.001) with substantial regional discrepancies so that North region was the only one with no changes along the period. The overall treatment coverage increased from 27.7% in 2014 to 44.1% in 2019, with Southeast and Midwest absorbing the demand for service from the North, Northeast and South. Despite an improvement along the past years, both screening and treatment coverages for DR in diabetes patients are ineffective in Brazil. Public health policies should address resources disparities throughout the country aiming to offer same healthcare conditions to patients regardless their geographic location. [ABSTRACT FROM AUTHOR]

A wide-field fundus camera, which can selectively evaluate the retina and choroid, is desirable for better detection and treatment evaluation of eye diseases. Trans-palpebral illumination has been demonstrated for wide-field fundus photography, but its application for true-color retinal imaging is challenging due to the light efficiency delivered through the eyelid and sclera is highly wavelength dependent. This study is to test the feasibility of true-color retinal imaging using efficiency-balanced visible light illumination, and to validate multiple spectral imaging (MSI) of the retina and choroid. 530 nm, 625 nm, 780 nm and 970 nm light emission diodes (LED)s are used to quantitatively evaluate the spectral efficiency of the trans-palpebral illumination. In comparison with 530 nm illumination, the 625 nm, 780 nm and 970 nm light efficiencies are 30.25, 523.05, and 1238.35 times higher. The light efficiency-balanced 530 nm and 625 nm illumination control can be used to produce true-color retinal image with contrast enhancement. The 780 nm light image enhances the visibility of choroidal vasculature, and the 970 nm image is predominated by large veins in the choroid. Without the need of pharmacological pupillary dilation, a 140° eye-angle field of view (FOV) is demonstrated in a snapshot fundus image. In coordination with a fixation target, the FOV can be readily expanded over the equator of the eye to visualize vortex ampullas. [ABSTRACT FROM AUTHOR]

Optical coherence tomography angiography (OCTA) is an emerging non-invasive technique for imaging the retinal vasculature. While there are many promising clinical applications for OCTA, determination of image quality remains a challenge. We developed a deep learning-based system using a ResNet152 neural network classifier, pretrained using ImageNet, to classify images of the superficial capillary plexus in 347 scans from 134 patients. Images were also manually graded by two independent graders as a ground truth for the supervised learning models. Because requirements for image quality may vary depending on the clinical or research setting, two models were trained—one to identify high-quality images and one to identify low-quality images. Our neural network models demonstrated outstanding area under the curve (AUC) metrics for both low quality image identification (AUC = 0.99, 95%CI 0.98–1.00, κ = 0.90) and high quality image identification (AUC = 0.97, 95%CI 0.96–0.99, κ = 0.81), significantly outperforming machine-reported signal strength (AUC = 0.82, 95%CI 0.77–0.86, κ = 0.52 and AUC = 0.78, 95%CI 0.73–0.83, κ = 0.27 respectively). Our study demonstrates that techniques from machine learning may be used to develop flexible and robust methods for quality control of OCTA images. [ABSTRACT FROM AUTHOR]

Retinal imaging has been proposed as a biomarker for neurological diseases such as multiple sclerosis (MS). Recently, a technique for non-invasive assessment of the retinal microvasculature called optical coherence tomography angiography (OCTA) was introduced. We investigated retinal microvasculature alterations in participants with relapsing–remitting MS (RRMS) without history of optic neuritis (ON) and compared them to a healthy control group. The study was performed in a prospective, case–control design, including 58 participants (n = 100 eyes) with RRMS without ON and 78 age- and sex-matched control participants (n = 136 eyes). OCTA images of the superficial capillary plexus (SCP), deep capillary plexus (DCP) and choriocapillaris (CC) were obtained using a commercial OCTA system (Zeiss Cirrus HD-5000 Spectral-Domain OCT with AngioPlex OCTA, Carl Zeiss Meditec, Dublin, CA). The outcome variables were perfusion density (PD) and foveal avascular zone (FAZ) features (area and circularity) in both the SCP and DCP, and flow deficit in the CC. MS group had on average higher intraocular pressure (IOP) than controls (P < 0.001). After adjusting for confounders, MS participants showed significantly increased PD in SCP (P = 0.003) and decreased PD in DCP (P < 0.001) as compared to controls. A significant difference was still noted when large vessels (LV) in the SCP were removed from the PD calculation (P = 0.004). Deep FAZ was significantly larger (P = 0.005) and less circular (P < 0.001) in the eyes of MS participants compared to the control ones. Neither LV, PD or FAZ features in the SCP, nor flow deficits in the CC showed any statistically significant differences between the MS group and control group (P > 0.186). Our study indicates that there are microvascular changes in the macular parafoveal retina of RRMS patients without ON, showing increased PD in SCP and decreased PD in DCP. Further studies with a larger cohort of MS patients and MRI correlations are necessary to validate retinal microvascular changes as imaging biomarkers for diagnosis and screening of MS. [ABSTRACT FROM AUTHOR]

Glaucoma is an eye condition that leads to loss of vision and blindness if not diagnosed in time. Diagnosis requires human experts to estimate in a limited time subtle changes in the shape of the optic disc from retinal fundus images. Deep learning methods have been satisfactory in classifying and segmenting diseases in retinal fundus images, assisting in analyzing the increasing amount of images. Model training requires extensive annotations to achieve successful generalization, which can be highly problematic given the costly expert annotations. This work aims at designing and training a novel multi-task deep learning model that leverages the similarities of related eye-fundus tasks and measurements used in glaucoma diagnosis. The model simultaneously learns different segmentation and classification tasks, thus benefiting from their similarity. The evaluation of the method in a retinal fundus glaucoma challenge dataset, including 1200 retinal fundus images from different cameras and medical centers, obtained a 96.76 ± 0.96 AUC performance compared to an 93.56 ± 1.48 obtained by the same backbone network trained to detect glaucoma. Our approach outperforms other multi-task learning models, and its performance pairs with trained experts using ∼ 3.5 times fewer parameters than training each task separately. The data and the code for reproducing our results are publicly available. [ABSTRACT FROM AUTHOR]

Ocular cranial nerve palsy of presumed ischemic origin (OCNPi) is the most common type of ocular cranial nerve palsy (OCNP) in patients aged ≥ 50 years; however, no definite diagnostic test exists. As diagnostic criteria include clinical improvement, diagnoses are often delayed. Diagnostic biomarkers for OCNPi are required; we hypothesized that cerebral small vessel disease is associated with OCNPi. We analyzed 646 consecutive patients aged ≥ 50 years with isolated unilateral OCNP who underwent work-ups at two referral hospitals. White matter hyperintensities (WMHs), silent infarctions, and cerebral microbleeds (CMBs) were assessed. In multivariate analyses, mild (grades 1–3) and moderate to severe (grades 4–6) WMHs were significantly associated with OCNPi compared to OCNP of other origins (odds ratio [OR] 3.51, 95% confidence interval [CI] 1.91–6.43, P < 0.001; OR 3.47, 95% CI 1.42–8.48, P = 0.006, respectively). Silent infarction and CMBs did not remain associated (OR 0.96, 95% CI 0.54–1.70, P = 0.870; OR 0.55, 95% CI 0.28–1.08, P = 0.080, respectively). Associations between WMH and OCNPi remained after excluding patients with vascular risk factors. In conclusion, the presence of WMH could independently predict ischemic origin in patients with isolated unilateral OCNP at early stage of admission. [ABSTRACT FROM AUTHOR]

Automated fundus screening is becoming a significant programme of telemedicine in ophthalmology. Instant quality evaluation of uploaded retinal images could decrease unreliable diagnosis. In this work, we propose fractal dimension of retinal vasculature as an easy, effective and explainable indicator of retinal image quality. The pipeline of our approach is as follows: utilize image pre-processing technique to standardize input retinal images from possibly different sources to a uniform style; then, an improved deep learning empowered vessel segmentation model is employed to extract retinal vessels from the pre-processed images; finally, a box counting module is used to measure the fractal dimension of segmented vessel images. A small fractal threshold (could be a value between 1.45 and 1.50) indicates insufficient image quality. Our approach has been validated on 30,644 images from four public database. [ABSTRACT FROM AUTHOR]

This study was performed to utilize transnasal Sphenopalatine Ganglion (SPG) block for pain reliving during panretinal photocoagulation (PRP) in diabetic patients with diabetic retinopathy. This pre and post interventional study was performed on 20 patients with proliferative diabetic retinopathy. The first PRP treatment session of all the patients is performed with no transnasal SPG block, but before holding the second session, all the patients underwent transnasal SPG block and pain levels during and after PRP were compared to each other. Before the transnasal SPG block, each nostril of all the cases was inspected for finding any obstruction in each PRP session. Transnasal SPG block was also performed in with 2% lidocaine. The mean age of the included cases was 52.84 ± 8.62 years old (from 36 to 72 years old). All the cases underwent two PRP lasers treatment sessions with the same characteristic (spot size, power and duration) for each patient. In the first and second PRP treatment sessions, the mean NRS scores were obtained immediately after the PRP laser (8.4 vs. 4.2), 15 min (8.2 vs. 4.2), 1 h (8.0 vs. 4.1), and 24 h (5.4 vs. 3.6) after the PRP respectively. The mean NRS scores significantly reduced during the second PRP treatment session compared to the first session (p < 0.001). Transnasal SPG block is a safe and effective strategy used for relieving pain caused by the PRP laser treatment in patients with diabetic retinopathy. [ABSTRACT FROM AUTHOR]

Image quality assessment is essential for retinopathy detection on color fundus retinal image. However, most studies focused on the classification of good and poor quality without considering the different types of poor quality. This study developed an automatic retinal image analysis (ARIA) method, incorporating transfer net ResNet50 deep network with the automatic features generation approach to automatically assess image quality, and distinguish eye-abnormality-associated-poor-quality from artefact-associated-poor-quality on color fundus retinal images. A total of 2434 retinal images, including 1439 good quality and 995 poor quality (483 eye-abnormality-associated-poor-quality and 512 artefact-associated-poor-quality), were used for training, testing, and 10-ford cross-validation. We also analyzed the external validation with the clinical diagnosis of eye abnormality as the reference standard to evaluate the performance of the method. The sensitivity, specificity, and accuracy for testing good quality against poor quality were 98.0%, 99.1%, and 98.6%, and for differentiating between eye-abnormality-associated-poor-quality and artefact-associated-poor-quality were 92.2%, 93.8%, and 93.0%, respectively. In external validation, our method achieved an area under the ROC curve of 0.997 for the overall quality classification and 0.915 for the classification of two types of poor quality. The proposed approach, ARIA, showed good performance in testing, 10-fold cross validation and external validation. This study provides a novel angle for image quality screening based on the different poor quality types and corresponding dealing methods. It suggested that the ARIA can be used as a screening tool in the preliminary stage of retinopathy grading by telemedicine or artificial intelligence analysis. [ABSTRACT FROM AUTHOR]

We present a compact multi-modal and multi-scale retinal imaging instrument with an angiographic functional extension for clinical use. The system integrates scanning laser ophthalmoscopy (SLO), optical coherence tomography (OCT) and OCT angiography (OCTA) imaging modalities and provides multi-scale fields of view. For high resolution, and high lateral resolution in particular, cellular imaging correction of aberrations by adaptive optics (AO) is employed. The entire instrument has a compact design and the scanning head is mounted on motorized translation stages that enable 3D self-alignment with respect to the subject's eye by tracking the pupil position. Retinal tracking, based on the information provided by SLO, is incorporated in the instrument to compensate for retinal motion during OCT imaging. The imaging capabilities of the multi-modal and multi-scale instrument were tested by imaging healthy volunteers and patients. [ABSTRACT FROM AUTHOR]

We sought to predict whether central serous chorioretinopathy (CSC) will persist after 6 months using multiple optical coherence tomography (OCT) images by deep convolutional neural network (CNN). This was a multicenter, retrospective, cohort study. Multiple OCT images, including B-scan and en face images of retinal thickness (RT), mid-retina, ellipsoid zone (EZ) layer, and choroidal layer, were collected from 832 eyes of 832 CSC patients (593 self-resolving and 239 persistent). Each image set and concatenated set were divided into training (70%), validation (15%), and test (15%) sets. Training and validation were performed using ResNet50 CNN architecture for predicting CSC requiring treatment. Model performance was analyzed using the test set. The accuracy of prediction was 0.8072, 0.9200, 0.6480, and 0.9200 for B-scan, RT, mid-retina, EZ, and choroid modalities, respectively. When image sets with high accuracy were concatenated, the accuracy was 0.9520, 0.8800, and 0.9280 for B-scan + RT, B-scan + EZ, and EZ + RT, respectively. OCT B-scan, RT, and EZ en face images demonstrated good performances for predicting the prognosis of CSC using CNN. The performance improved when these sets were concatenated. The results of this study can serve as a reference for choosing an optimal treatment for CSC patients. [ABSTRACT FROM AUTHOR]

Cerebral small vessel disease (CSVD) is an important contributor to cognitive impairment and stroke. Previous research has suggested associations with alterations in single retinal layers. We have assessed changes of all individual retinal layers in CSVD using high-resolution optical coherence tomography (OCT) for the first time. Subjects with recent magnetic resonance imaging (MRI) underwent macular and peripapillary retinal imaging using OCT for this case–control study. Number and volume ratio index (WMRI) of white matter lesions (WML) were determined on MRI. Data were analyzed using multiple linear regression models. 27 CSVD patients and 9 control participants were included. Ganglion cell layer (GCL) volume was significantly reduced in patients with CSVD compared to age-matched controls (p = 0.008). In patients with CSVD, larger foveal outer plexiform layer (OPL) volume and decreased temporal peripapillary retinal nerve fiber layer (RNFL) thickness were significantly associated with a higher WMRI in linear regression when controlling for age (p ≤ 0.033). Decreased foveal GCL volume and temporal-inferior RNFL thickness at Bruch's membrane opening (MRW), and increased temporal MRW were associated with a higher WML burden (p ≤ 0.037). Thus, we identified alterations in several OCT layers in individuals with CSVD (GCL, OPL, MRW and RNFL). Their potential diagnostic value merits further study. [ABSTRACT FROM AUTHOR]

Drusen are a hallmark lesion of age-related macular degeneration (AMD) and changes in their area and/or volume are strongly associated with disease progression. Assessment of longitudinal change in drusen size in clinical practice however is limited to a single commercial tool or manual inspection by clinicians. In this study we analysed change in drusen area in 33 eyes with intermediate AMD across two separate visits using a novel technique known as multispectral pattern recognition for en face retinal images from various imaging modalities (infrared (815 nm), fundus autofluorescence (488 nm) and green (532 nm) scanning laser ophthalmoscopy). We found 91% (30/33 eyes) agreement in the direction of drusen change for multispectral pattern recognition relative to expert graders who graded eyes as having drusen progression, regression or being stable. Multispectral pattern recognition showed 100% sensitivity (22/22 eyes) and 73% specificity (8/11 eyes). In comparison, we found only 70% (23/33 eyes) agreement in the direction of drusen change with a commercially available change analysis software, the Cirrus Advanced RPE Analysis relative to expert graders, with a sensitivity 64% (14/22 eyes) and specificity of 82% (9/11 eyes). Total drusen area or amount of change between visits had no significant effect on agreement. This suggests multispectral pattern recognition can quantify longitudinal change in drusen area from multimodal imaging with greater congruency to expert graders than a commercially available platform based on a single imaging modality. Considering the association of drusen area and disease progression, this method could aid clinical assessment and monitoring of AMD. [ABSTRACT FROM AUTHOR]

This study aimed to evaluate the distribution of retinal pigment epithelium (RPE) melanin in patients with retinitis pigmentosa (RP) using entropy measurements by custom-made polarization-sensitive optical coherence tomography (PS-OCT) images, and compare entropy with the intensity of short-wavelength (SW) and near-infrared (NIR) autofluorescence (AF). We retrospectively reviewed the retinal images, including PS-OCT, SW-AF, and NIR-AF of patients with RP who had a hyperautofluorescent ring on AF. A total of 12 eyes of 12 patients (8 women and 4 men; mean age: 37.9 years) were included. There was a strong positive correlation between entropy value and NIR-AF intensity (r = 0.626, p < 0.001), and there was a very weak negative correlation between entropy value and SW-AF (r = − 0.197, p = 0.001). The mean values of the entropy in the foveal, temporal (2 mm from the fovea), and nasal (2 mm from the fovea) sections were 0.41 (± 0.09), 0.29 (± 0.08), and 0.26 (± 0.08), respectively. The entropy was significantly higher in the foveal section than in the temporal and nasal sections (p = 0.002 and p = 0.003, respectively). There was no significant difference between the entropies values for the temporal and nasal sections (p = 0.157). Age, logMAR best-corrected visual acuity, ellipsoid zone width, and central retinal thickness were not correlated with foveal entropy. We presented RPE melanin imaging in patients with RP using PS-OCT for the first time. PS-OCT can be a useful tool for monitoring patients with RP. [ABSTRACT FROM AUTHOR]

The segmentation of retinal vasculature from eye fundus images is a fundamental task in retinal image analysis. Over recent years, increasingly complex approaches based on sophisticated Convolutional Neural Network architectures have been pushing performance on well-established benchmark datasets. In this paper, we take a step back and analyze the real need of such complexity. We first compile and review the performance of 20 different techniques on some popular databases, and we demonstrate that a minimalistic version of a standard U-Net with several orders of magnitude less parameters, carefully trained and rigorously evaluated, closely approximates the performance of current best techniques. We then show that a cascaded extension (W-Net) reaches outstanding performance on several popular datasets, still using orders of magnitude less learnable weights than any previously published work. Furthermore, we provide the most comprehensive cross-dataset performance analysis to date, involving up to 10 different databases. Our analysis demonstrates that the retinal vessel segmentation is far from solved when considering test images that differ substantially from the training data, and that this task represents an ideal scenario for the exploration of domain adaptation techniques. In this context, we experiment with a simple self-labeling strategy that enables moderate enhancement of cross-dataset performance, indicating that there is still much room for improvement in this area. Finally, we test our approach on Artery/Vein and vessel segmentation from OCTA imaging problems, where we again achieve results well-aligned with the state-of-the-art, at a fraction of the model complexity available in recent literature. Code to reproduce the results in this paper is released. [ABSTRACT FROM AUTHOR]

Accumulation of beta-amyloid in the brain and cognitive decline are considered hallmarks of Alzheimer's disease. Knowing from previous studies that these two factors can manifest in the retina, the aim was to investigate whether a deep learning method was able to predict the cognition of an individual from a RGB image of his retina and metadata. A deep learning model, EfficientNet, was used to predict cognitive scores from the Canadian Longitudinal Study on Aging (CLSA) database. The proposed model explained 22.4% of the variance in cognitive scores on the test dataset using fundus images and metadata. Metadata alone proved to be more effective in explaining the variance in the sample (20.4%) versus fundus images (9.3%) alone. Attention maps highlighted the optic nerve head as the most influential feature in predicting cognitive scores. The results demonstrate that RGB fundus images are limited in predicting cognition. [ABSTRACT FROM AUTHOR]

Many important eye diseases as well as systemic disorders manifest themselves in the retina. Retinal imaging technologies are rapidly growing and can provide ever-increasing amounts of information about the structure, function, and molecular composition of retinal tissue in-vivo. Photoacoustic remote sensing (PARS) is a novel imaging modality based on all-optical detection of photoacoustic signals, which makes it suitable for a wide range of medical applications. In this study, PARS is applied for in-vivo imaging of the retina and estimating oxygen saturation in the retinal vasculature. To our knowledge, this is the first time that a non-contact photoacoustic imaging technique is applied for in-vivo imaging of the retina. Here, optical coherence tomography is also used as a well-established retinal imaging technique to navigate the PARS imaging beams and demonstrate the capabilities of the optical imaging setup. The system is applied for in-vivo imaging of both microanatomy and the microvasculature of the retina. The developed system has the potential to advance the understanding of the ocular environment and to help in monitoring of ophthalmic diseases. [ABSTRACT FROM AUTHOR]

Many important eye diseases as well as systemic disorders manifest themselves in the retina. Retinal imaging technologies are rapidly growing and can provide ever-increasing amounts of information about the structure, function, and molecular composition of retinal tissue in-vivo. Photoacoustic remote sensing (PARS) is a novel imaging modality based on all-optical detection of photoacoustic signals, which makes it suitable for a wide range of medical applications. In this study, PARS is applied for in-vivo imaging of the retina and estimating oxygen saturation in the retinal vasculature. To our knowledge, this is the first time that a non-contact photoacoustic imaging technique is applied for in-vivo imaging of the retina. Here, optical coherence tomography is also used as a well-established retinal imaging technique to navigate the PARS imaging beams and demonstrate the capabilities of the optical imaging setup. The system is applied for in-vivo imaging of both microanatomy and the microvasculature of the retina. The developed system has the potential to advance the understanding of the ocular environment and to help in monitoring of ophthalmic diseases. [ABSTRACT FROM AUTHOR]

Many important eye diseases as well as systemic disorders manifest themselves in the retina. Retinal imaging technologies are rapidly growing and can provide ever-increasing amounts of information about the structure, function, and molecular composition of retinal tissue in-vivo. Photoacoustic remote sensing (PARS) is a novel imaging modality based on all-optical detection of photoacoustic signals, which makes it suitable for a wide range of medical applications. In this study, PARS is applied for in-vivo imaging of the retina and estimating oxygen saturation in the retinal vasculature. To our knowledge, this is the first time that a non-contact photoacoustic imaging technique is applied for in-vivo imaging of the retina. Here, optical coherence tomography is also used as a well-established retinal imaging technique to navigate the PARS imaging beams and demonstrate the capabilities of the optical imaging setup. The system is applied for in-vivo imaging of both microanatomy and the microvasculature of the retina. The developed system has the potential to advance the understanding of the ocular environment and to help in monitoring of ophthalmic diseases. [ABSTRACT FROM AUTHOR]