Color Fundus Images Research Articles

Retinal Vascular Network Topology Reconstruction and Artery/Vein Classification via Dominant Set Clustering.

The estimation of vascular network topology in complex networks is important in understanding the relationship between vascular changes and a wide spectrum of diseases. Automatic classification of the retinal vascular trees into arteries and veins is of direct assistance to the ophthalmologist in terms of diagnosis and treatment of eye disease. However, it is challenging due to their projective ambiguity and subtle changes in appearance, contrast, and geometry in the imaging process. In this paper, we propose a novel method that is capable of making the artery/vein (A/V) distinction in retinal color fundus images based on vascular network topological properties. To this end, we adapt the concept of dominant set clustering and formalize the retinal blood vessel topology estimation and the A/V classification as a pairwise clustering problem. The graph is constructed through image segmentation, skeletonization, and identification of significant nodes. The edge weight is defined as the inverse Euclidean distance between its two end points in the feature space of intensity, orientation, curvature, diameter, and entropy. The reconstructed vascular network is classified into arteries and veins based on their intensity and morphology. The proposed approach has been applied to five public databases, namely INSPIRE, IOSTAR, VICAVR, DRIVE, and WIDE, and achieved high accuracies of 95.1%, 94.2%, 93.8%, 91.1%, and 91.0%, respectively. Furthermore, we have made manual annotations of the blood vessel topologies for INSPIRE, IOSTAR, VICAVR, and DRIVE datasets, and these annotations are released for public access so as to facilitate researchers in the community.

Predictive Diagnosis of Glaucoma Based on Analysis of Focal Notching along the Neuro-Retinal Rim Using Machine Learning

Automatic evaluation of the retinal fundus image is regarded as one of the most important future tools for early detection and treatment of progressive eye diseases like glaucoma. Glaucoma leads to progressive degeneration of vision which is characterized by shape deformation of the optic cup associated with focal notching, wherein the degeneration of the blood vessels results in the formation of a notch along the neuroretinal rim. In this study, we have developed a methodology for automated prediction of glaucoma based on feature analysis of the focal notching along the neuroretinal rim and cup to disc ratio values. This procedure has three phases: the first phase segments the optic disc and cup by suppressing the blood vessels with dynamic thresholding; the second phase computes the neuroretinal rim width to detect the presence and direction of notching by the conventional ISNT rule apart from calculating the cup-to-disc ratio from the color fundus image (CFI); the third phase uses linear support vector based machine learning algorithm by integrating extracted parameters as features for classification of CFIs into glaucomatous or normal. The algorithm outputs have been evaluated on a freely available database of 101 images, each marked with decision of five glaucoma expert ophthalmologists, thereby returning an accuracy rate of 87.128%.

Automatic optic disc detection in colour fundus images by means of multispectral analysis and information content.

The optic disc (OD) in retinal fundus images is widely used as a reference in computer-based systems for the measurement of the severity of retinal disease. A number of algorithms have been published in the past 5 years to locate and measure the OD in digital fundus images. Our proposed algorithm, automatically: (i) uses the three channels (RGB) of the digital colour image to locate the region of interest (ROI) where the OD lies, (ii) measures the Shannon information content per channel in the ROI, to decide which channel is most appropriate for searching for the OD centre using the circular Hough transform. A series of evaluations were undertaken to test our hypothesis that using the three channels gives a better performance than a single channel. Three different databases were used for evaluation purposes with a total of 2,371 colour images giving a misdetection error of 3% in the localisation of the centre of the OD. We find that the area determined by our algorithm which assumes that the OD is circular, is similar to that found by other algorithms that detected the shape of the OD. Five metrics were measured for comparison with other recent studies. Combining the two databases where expert delineation of the OD is available (1,240 images), the average results for our multispectral algorithm are: TPR = 0.879, FPR = 0.003, Accuracy = 0.994, Overlap = 80.6% and Dice index = 0.878.

Spectrum of Disease Severity and Phenotype in Choroideremia Carriers

To characterize and bring awareness to the disease spectrum of female choroideremia patients, as severity can vary from mild to severe disease, comparable to that observed in male patients. Retrospective cohort study. Twelve female carriers of disease-causing variants in the CHM gene confirmed by molecular genetic sequencing were characterized clinically and imaged with short-wave fundus autofluorescence (SW-FAF), spectral-domain optical coherence tomography (OCT), and color fundus imaging. Twelve unrelated female patients with a clinical and genetic diagnosis of choroideremia carriers were included in this study. Disease severity among these phenotypes ranged from mild to severe, resembling the typical presentation of choroideremia in male patients. Mild disease presented with retinal pigment epithelium mottling, a patchy pattern of hypoautofluorescent speckles on SW-FAF, and intact retinal layers on spectral-domain OCT. Severe disease presented with widespread chorioretinal atrophy as shown by SW-FAF and spectral-domain OCT. Each of the identified genetic variants in CHM was predicted to be disease-causing according to insilico prediction software. Disease progression analysis of 4 patients with follow-up showed a decline in visual acuity for 2 patients, with progression observed on spectral-domain OCT in 1 of the patients. No significant disease progression on SW-FAF was observed for any of the patients. Female carriers of choroideremia can present with a wide range of clinical phenotypes and disease severity, from mild to severe disease, similar to male subjects. Symptomatic female subjects should be considered for current and upcoming gene replacement therapy clinical trials.

Detection of microaneurysms using ant colony algorithm in the early diagnosis of diabetic retinopathy

Microaneurysms are lesions in the shape of small circular dilations which result from thinning in peripheral retinal blood vessels due to diabetes and increasing intra-retinal blood pressure. Because it is considered as the most important clinical finding in the diagnosis of diabetic retinopathy, accurate detection of these lesions bear utmost importance in the early diagnosis of diabetic retinopathy. The present study aims to accurately, effectively and automatically detect microaneurysms which are difficult to detect in color fundus images in early stage. To this aim, ant colony algorithm, which is an important optimization method, was used instead of conventional image processing techniques. First, retinal vascular structure was extracted from color fundus images in Messidor and DiaretDB1 data sets. Afterwards, the segmentation of microaneurysms was effectively carried out using ant colony algorithm. The same procedure was also applied to five different image processing and clustering algorithms (watershed, random walker, k-means, maximum entropy and region growing) in order to compare the performance of the proposed method with other methods. Microaneurysm images manually detected by a specialist eye doctor were used to measure the performances of above-mentioned methods. The similarities among microaneurysms which were automatically and manually segmented were tested using Dice and Jaccard similarity index values. Dice index values obtained from the study vary between 0.52 and 0.98 in maximum entropy, 0.55 and 0.88 in watershed, 0.75 and 0.86 in region growing, 0.55 and 0.78 in k-means, and 0.66 and 0.83 in random walker, and 0.81 and 0.9 in ant colony. Similar performance values were also obtained in Jaccard index. The results show that different performances were observed in the conventional segmentation of microaneurysms depending on the image quality. On the other hand, the ant colony based method proposed in this paper displays a more stabilized and higher performance irrespective of image contrast. Therefore, it is evident that the proposed method successfully detects microaneurysms even in low quality images, thus helping specialists diagnose them in an easier way.

Retinal image synthesis from multiple-landmarks input with generative adversarial networks

BackgroundMedical datasets, especially medical images, are often imbalanced due to the different incidences of various diseases. To address this problem, many methods have been proposed to synthesize medical images using generative adversarial networks (GANs) to enlarge training datasets for facilitating medical image analysis. For instance, conventional methods such as image-to-image translation techniques are used to synthesize fundus images with their respective vessel trees in the field of fundus image.MethodsIn order to improve the image quality and details of the synthetic images, three key aspects of the pipeline are mainly elaborated: the input mask, architecture of GANs, and the resolution of paired images. We propose a new preprocessing pipeline named multiple-channels-multiple-landmarks (MCML), aiming to synthesize color fundus images from a combination of vessel tree, optic disc, and optic cup images. We compared both single vessel mask input and MCML mask input on two public fundus image datasets (DRIVE and DRISHTI-GS) with different kinds of Pix2pix and Cycle-GAN architectures. A new Pix2pix structure with ResU-net generator is also designed, which has been compared with the other models.Results and conclusionAs shown in the results, the proposed MCML method outperforms the single vessel-based methods for each architecture of GANs. Furthermore, we find that our Pix2pix model with ResU-net generator achieves superior PSNR and SSIM performance than the other GANs. High-resolution paired images are also beneficial for improving the performance of each GAN in this work. Finally, a Pix2pix network with ResU-net generator using MCML and high-resolution paired images are able to generate good and realistic fundus images in this work, indicating that our MCML method has great potential in the field of glaucoma computer-aided diagnosis based on fundus image.

COMPARING FUNDUS FLUORESCEIN ANGIOGRAPHY AND SWEPT-SOURCE OPTICAL COHERENCE TOMOGRAPHY ANGIOGRAPHY IN THE EVALUATION OF DIABETIC MACULAR PERFUSION.

To compare fundus fluorescein angiography (FFA) and swept-source optical coherence tomography angiography (SS-OCTA) in the evaluation of macular perfusion in diabetic patients. Forty-one eyes (21 diabetic patients) seen at Moorfields Eye Hospital (London) over a 1-month interval underwent color fundus photography, FFA, and SS-OCTA imaging of the capillary superficial plexus using 2 different protocols: 3 × 3 mm and 4.5 × 4.5 mm. Quantitative assessment (foveal avascular zone diameters and area), qualitative analysis (macroscopic and microscopic levels) and Early Treatment Diabetic Retinopathy Study diabetic macular ischemia grading were performed. Artifacts were recorded. Intraclass correlation coefficients and weighted kappa values were calculated. Mean (SD) foveal avascular zone area was 0.695 (0.52) mm on FFA, 0.627 (0.54) mm on SS-OCTA 3 × 3 and 0.701 (0.54) mm on SS-OCTA 4.5 × 4.5 protocol. Intraclass correlation coefficients showed good agreement between FFA and SS-OCTA for both vertical diameter and foveal avascular zone area measurements. The agreement between SS-OCTA 3 × 3 and 4.5 × 4.5 was good for all quantitative measurements. Weighted kappa for diabetic macular ischemia grading showed low to fair agreement between FFA and SS-OCTA, whereas the agreement was good between two different SS-OCTA protocols. Swept-source OCTA is a reproducible technique in the assessment of macular perfusion in diabetic patients with special regards to foveal avascular zone analysis. The agreement with FFA is limited especially for diabetic macular ischemia grading. Fundus fluorescein angiography is more sensitive in identifying microaneurysms.

Artificial intelligence using deep learning to screen for referable and vision-threatening diabetic retinopathy in Africa: a clinical validation study

Radical measures are required to identify and reduce blindness due to diabetes to achieve the Sustainable Development Goals by 2030. Therefore, we evaluated the accuracy of an artificial intelligence (AI) model using deep learning in a population-based diabetic retinopathy screening programme in Zambia, a lower-middle-income country. We adopted an ensemble AI model consisting of a combination of two convolutional neural networks (an adapted VGGNet architecture and a residual neural network architecture) for classifying retinal colour fundus images. We trained our model on 76 370 retinal fundus images from 13 099 patients with diabetes who had participated in the Singapore Integrated Diabetic Retinopathy Program, between 2010 and 2013, which has been published previously. In this clinical validation study, we included all patients with a diagnosis of diabetes that attended a mobile screening unit in five urban centres in the Copperbelt province of Zambia from Feb 1 to June 31, 2012. In our model, referable diabetic retinopathy was defined as moderate non-proliferative diabetic retinopathy or worse, diabetic macular oedema, and ungradable images. Vision-threatening diabetic retinopathy comprised severe non-proliferative and proliferative diabetic retinopathy. We calculated the area under the curve (AUC), sensitivity, and specificity for referable diabetic retinopathy, and sensitivities of vision-threatening diabetic retinopathy and diabetic macular oedema compared with the grading by retinal specialists. We did a multivariate analysis for systemic risk factors and referable diabetic retinopathy between AI and human graders. A total of 4504 retinal fundus images from 3093 eyes of 1574 Zambians with diabetes were prospectively recruited. Referable diabetic retinopathy was found in 697 (22·5%) eyes, vision-threatening diabetic retinopathy in 171 (5·5%) eyes, and diabetic macular oedema in 249 (8·1%) eyes. The AUC of the AI system for referable diabetic retinopathy was 0·973 (95% CI 0·969-0·978), with corresponding sensitivity of 92·25% (90·10-94·12) and specificity of 89·04% (87·85-90·28). Vision-threatening diabetic retinopathy sensitivity was 99·42% (99·15-99·68) and diabetic macular oedema sensitivity was 97·19% (96·61-97·77). The AI model and human graders showed similar outcomes in referable diabetic retinopathy prevalence detection and systemic risk factors associations. Both the AI model and human graders identified longer duration of diabetes, higher level of glycated haemoglobin, and increased systolic blood pressure as risk factors associated with referable diabetic retinopathy. An AI system shows clinically acceptable performance in detecting referable diabetic retinopathy, vision-threatening diabetic retinopathy, and diabetic macular oedema in population-based diabetic retinopathy screening. This shows the potential application and adoption of such AI technology in an under-resourced African population to reduce the incidence of preventable blindness, even when the model is trained in a different population. National Medical Research Council Health Service Research Grant, Large Collaborative Grant, Ministry of Health, Singapore; the SingHealth Foundation; and the Tanoto Foundation.

Bin loss for hard exudates segmentation in fundus images

Diabetic retinopathy is one of the leading reasons that causes blindness. And the segmentation of hard exudates in color fundus images is crucial for early diagnosis of diabetic retinopathy, which is a difficult task due to its uncertainty in size, shape and contrast. Class-balanced cross entropy (CBCE) loss is the most popular objective function for image segmentation task to solve the class-unbalance problem. However, we show that background pixels tend to be misclassified to hard exudates in CBCE since the loss for a misclassified background pixels is much smaller than that for a misclassified hard exudate pixel, which is called loss-unbalance problem here. A top-k loss is proposed in this paper, which considers the cases of both class-unbalance and loss-unbalance by focusing more over the hard-to-classify pixels. Moreover, a fast version of the top-k loss, named bin loss, is implemented for efficiency, which reduces the time complexity from O(nlog n) of top-k loss to O(n), where n is the number of background pixels. We evaluated the proposed bin loss over two public datasets for hard exudates segmentation task, including e-ophtha EX and IDRiD. Furthermore, three popular models for image segmentation, HED, DeepLab v2, and FCRN, were used to evaluate the versatility of bin loss. Extensive experiments show that each model with the proposed bin loss performs better than that with CBCE loss, which demonstrates bin loss is versatile so that it can be applied to different models for performance improvement. Specially, for DeepLab over e-ophtha EX, the F-score increases 5.2 percentage points, and the area under the SE-PPV curve (AUC) increases 10.6 percentage points. Moreover, the AUC increases more than 4 percentage points over IDRiD dataset for both DeepLab and FCRN. The source code of bin loss is available at: https://github.com/guomugong/bin_loss.

Mathematical morphology for microaneurysm detection in fundus images.

Fundus image analysis is the basis for the better understanding of retinal diseases which are found due to diabetes. Detection of earlier markers such as microaneurysms that appear in fundus images combined with treatment proves beneficial to prevent further complications of diabetic retinopathy with an increased risk of sight loss. The proposed algorithm consists of three modules: (1) image enhancement through morphological processing; (2) the extraction and removal of red structures, such as blood vessels preceded by detection and removal of bright artefacts; (3) finally, the true microaneurysm candidate selection among other structures based on feature extraction set. The proposed strategy is successfully evaluated on two publicly available databases containing both normal and pathological images. The sensitivity of 89.22%, specificity of 91% and accuracy of 92% achieved for the detection of microaneurysms for Diaretdb1 database images. The algorithm evaluation for microaneurysm detection has a sensitivity of 83% and specificity 82% for e-ophtha database. In automated detection system, the successful detection of the number of microaneurysms correlates with the stages of the retinal diseases and its early diagnosis. The results for true microaneurysm detection indicates it as a useful tool for screening colour fundus images, which proves time saving for counting of microaneurysms to follow Diabetic Retinopathy Grading Criteria.

The Fluorescein Angiographic Signs of Aggressive Posterior Retinopathy of Prematurity

The purposeis to study the fluorescence angiographic signs of posterior aggressive retinopathy of prematurity.Patients and methods. A prospective study of 83 infants with aggressive posterior retinopathy of prematurity (APROP), who were on treatment in the neonatal center in 2012–2018 years. Gestational age was between 22 and 30 weeks. Depending on the diagnostic methods, patients were divided into two groups: 1 (main) — 51 (61.4 %) children who, in addition to standard ophthalmic examination methods, received 132 series of FA using a pediatric retinal camera RetCam3; 2 (control) — 32 (38.6 %) children without FA. After the procedure, the somatic state of the child was monitored for 24 hours for the registration of drug dye side effects.Results. Angiographic predictors of the disease and objective signs of APROP manifestation were presented in group 1 children a week earlier than in the group 2. This made laser treatment possible on 2.0 ± 0.5 weeks earlier in the group 1 (32.8 ± 1.2 weeks) compared to group 2 (34.8 ± 1.7 weeks) (p < 0.05) and to increase its efficiency by 8.2 % (86.3 and 78.1 % respectively).Conclusion. Comparative analysis of angiograms and color fundus images obtained with RetCam3 in the studied groups of children demonstrates the advantages and safety FA for the detection angiographic predictors of APROP, early objective signs of disease manifestation, it provides timely and effective laser treatment of complicated categories of very premature infants.

Entropy Rate Superpixel Classification for Automatic Red Lesion Detection in Fundus Images

Diabetic retinopathy (DR) is the main cause of blindness in the working-age population in developed countries. Digital color fundus images can be analyzed to detect lesions for large-scale screening. Thereby, automated systems can be helpful in the diagnosis of this disease. The aim of this study was to develop a method to automatically detect red lesions (RLs) in retinal images, including hemorrhages and microaneurysms. These signs are the earliest indicators of DR. Firstly, we performed a novel preprocessing stage to normalize the inter-image and intra-image appearance and enhance the retinal structures. Secondly, the Entropy Rate Superpixel method was used to segment the potential RL candidates. Then, we reduced superpixel candidates by combining inaccurately fragmented regions within structures. Finally, we classified the superpixels using a multilayer perceptron neural network. The used database contained 564 fundus images. The DB was randomly divided into a training set and a test set. Results on the test set were measured using two different criteria. With a pixel-based criterion, we obtained a sensitivity of 81.43% and a positive predictive value of 86.59%. Using an image-based criterion, we reached 84.04% sensitivity, 85.00% specificity and 84.45% accuracy. The algorithm was also evaluated on the DiaretDB1 database. The proposed method could help specialists in the detection of RLs in diabetic patients.

Retinal Layer Thicknesses in Early Age-Related Macular Degeneration: Results From the German AugUR Study.

PurposeTo systematically analyze thicknesses of retinal layers in an older population and their link to early age-related macular degeneration (AMD).MethodsIn the AugUR baseline survey from a population aged ≥70 years, we conducted multimodal retinal imaging, including spectral-domain optical coherence tomography. Autosegmentation of eight distinct retinal layers was followed by manual correction of segmentation errors. AMD status was graded on color fundus images according to the Three Continent AMD Consortium Severity Scale. We tested the association of early AMD on retinal layer thicknesses by using linear mixed models and replicated significant results in independent data also from the AugUR platform.ResultsWhen comparing layer thicknesses between early AMD and no AMD (822 eyes, 449 participants), the retinal pigment epithelium/Bruch's membrane complex demonstrated a statistically significant thickening (e.g., P = 6.41 × 10−92 for severe early versus no AMD) and photoreceptor layers showed a significant thinning. Autosegmented retinal layer thicknesses revealed similar associations as manually corrected values but underestimated some effects. Independent replication analysis in 1026 eyes (546 participants) confirmed associations (e.g., P = 9.38 × 10−36 for retinal pigment epithelium/Bruch's membrane complex, severe early versus no AMD).ConclusionsThis first population-based study on spectral-domain optical coherence tomography-derived retinal layer thicknesses in a total of ∼1000 individuals provides insights into the reliability of autosegmentation and layer-specific reference values for an older population. Our findings show a difference in thicknesses between early AMD and no AMD for some retinal layers, suggesting these as potential imaging biomarkers. The thinning of photoreceptor layers substantiates a photoreceptor cell loss/damage already occurring in early AMD.

The computer based method to diabetic retinopathy assessment in retinal images: a review

Diabetic retinopathy accounts for a considerable amount of the blindness especially among the patients who are between 20 to 60 years. The early detection of this disease plays an important role in preventing vision damages and appropriate follow-up care of diabetic eye. Manual investigation of color fundus images to check morphological changes in dark and bright lesions is tedious work and very time-consuming that can be made easily with the help of computer-aided diagnosis system. Many techniques were proposed for early detection of the abnormalities in the retinal images help the ophthalmologists recognize the retinopathy earlier. This paper presents a review of various automated algorithms that have been used for the detection of diabetic retinopathy.

RETINAL FLECKS IN STARGARDT DISEASE REVEAL CHARACTERISTIC FLUORESCENCE LIFETIME TRANSITION OVER TIME.

Stargardt disease is the most common inherited juvenile macular dystrophy and is characterized by yellowish flecks across the posterior pole. The purpose of this study was to investigate fluorescence lifetime changes of retinal flecks over time using fluorescence lifetime imaging ophthalmoscopy. Longitudinal fluorescence lifetime data of 12 patients with Stargardt disease (mean age ± SEM, 42.25 ± 2.1 years; range, 28-58 years) were acquired using a fluorescence lifetime imaging ophthalmoscope based on a Heidelberg Engineering Spectralis system. Retinal autofluorescence was excited with a 470-nm laser. The emitted fluorescence was detected in two wavelength channels: a short spectral channel (498-560 nm) and a long spectral channel (560-720 nm). The mean retinal autofluorescence lifetimes were calculated and further analyzed with corresponding color fundus images, autofluorescence intensity images, and spectral domain optical coherence tomography. Patients were classified into three subtypes. All patients with Stargardt disease displayed characteristic autofluorescence lifetime patterns. Mean fluorescence lifetime values within areas of yellow flecks were significantly prolonged (long spectral channel 484 ps) compared with the surrounding tissue (long spectral channel 297 ps). In 91.6% of the eyes, flecks with short fluorescence lifetimes (long spectral channel 255 ps) were identified. Short lifetime flecks progressed to flecks with characteristic long lifetimes in 75.1% of eyes within a mean interval of 29.2 months (range 3-45 months). Between baseline and follow-up, the rate of newly developed short lifetime flecks (number/per year) based on subtypes was 2.62 in Group 1, 1.43 in Group 2, and 0.81 in Group 3. Recent onset flecks in Stargardt disease display short fluorescence lifetimes and convert into longer fluorescence lifetime flecks over time. This transition may represent a change in the composition of retinal deposits with accumulation of lipofuscin and retinoid by-products from the visual cycle. With emerging treatment options, these findings may prove useful to monitor disease progression and therapeutic effects.

Automatic Detection of Microaneurysms in Diabetic Retinopathy Using Python

This paper discusses the detection of microaneurysms(MAs) from colour fundus images using image processing. In this paper, we present a web application to detect MAs from fundus image more efficiently and on real-time purpose. This paper includes a unique method to detect and mask the optic disc (OD) and blob detection to detect MAs. To examine the accuracy of the system, we processed 63 colour fundus images and got an accuracy for 95% accuracy for optic disc elimination and 56% accuracy for microaneurysms detection.

A Discriminative Colour-to-Grayscale Representation for Retinal Vessel Segmentation

Structural changes in retinal blood vessels are important indicators for many ocular diseases including diabetic retinopathy (DR), glaucoma, and hypertension. An automated vessel segmentation process almost always begins with acquired color fundus image, containing three layers of images (red, green and blue), and then quickly converted them to a single grayscale image. However, grayscale conversion is not unique and more than one grayscale representation can be obtained for a given color image. For the many currently existing automated vessel extraction methods, the green channel of the RGB color fundus image is routinely used as an input grey-scale representation to a pipeline of the segmentation process for the reason that it provides the best contrast among all three channels, namely red, green and blue. We hypothesize that vessel information contained in dropped channels, red and blue, will add to result in improved segmentation performance. In this paper, we propose a linear combination framework to utilize all three channels of the color fundus image based on their importance level rather than completely discarding some channels. We devised a Principal Component Analysis (PCA) method that provides appropriate weights for each color channel to realize a more discriminative grey-scale representation. The added information made available through PCA-based grayscale representation results in improved performance for Modautomated vessel segmentation algorithms. The performance of the framework is analyzed on two publically available databases (DRIVE, STARE) of fundus images quantifying improvements in all three aspects called accuracy, sensitivity, and specificity.

Differential Artery-Vein Analysis Improves the Performance of OCTA Staging of Sickle Cell Retinopathy.

PurposeWe test if differential artery–vein analysis can increase the performance of optical coherence tomography angiography (OCTA) detection and classification of sickle cell retinopathy (SCR).MethodThis observational case series was conducted in a tertiary-retina practice. Color fundus and OCTA images were collected from 20 control and 48 SCR subjects. Fundus data were collected from fundus imaging devices, and SD-OCT and corresponding OCTA data were acquired using a spectral-domain OCT (SD-OCT) angiography system. For each patient, color fundus image-guided artery–vein classification was conducted in the OCTA image. Traditional mean blood vessel tortuosity (m-BVT) and mean blood vessel caliber (m-BVC) in OCTA images were quantified for control and SCR groups. Artery BVC (a-BVC), vein BVC (v-BVC), artery BVT (a-BVT), and vein BVT (v-BVT) were calculated; and then the artery–vein ratio of BVC (AVR–BVC) and artery–vein ratio of BVT (AVR–BVT) were quantified for comparative analysis.ResultsWe evaluated 40 control and 85 SCR images in this study. The color fundus image-guided artery–vein classification had 97.02% accuracy for differentiating arteries and veins in OCTA. Differential artery–vein analysis provided significant improvement (P < 0.05) in detecting and classifying SCR stages compared to traditional mean blood vessel analysis. AVR–BVT and AVR–BVC showed significant (P < 0.001) correlation with SCR severity.ConclusionsDifferential artery–vein analysis can significantly improve the performance of OCTA detection and classification of SCR. AVR–BVT is the most sensitive feature that can classify control and mild SCR.Translational RelevanceSCR and other retinovascular diseases result in changes to the caliber and tortuosity appearance of arteries and veins separately. Differential artery–vein analysis can improve the performance of SCR detection and stage classification.

Analysis of Inherited Optic Neuropathies.

Inherited optic neuropathies (IONs) cover a spectrum of clinically and genetically heterogenic conditions. Genetic evaluation of patients with IONs may enable their better clinico-diagnostic assessment and management of the disease. The aim of the present study was to determine the genetic condition related to the phenotype in patients with diverse inherited optic neuropathies. A retrospective study was performed in 12 adults and 8 children of 8 non-related families. Clinical phenotyping, supported by color fundus, FAF, and OCT imaging, was performed. Genetic testing was obtained for all family members suspected for ION. Identification of pathogenic mutations in eight non-related families helped to confirm the diagnosis of ION. Affected from ION were ten patients (eight adults and two children; four women and six men). Bilateral Leber's hereditary optic neuropathy (LHON) was linked to the m.11778G>A mutation in two families (two affected and five carriers). Secondary homoplasmic LHON mutations in MT-ND1 (m.4216T>C) and MT-CO3 genes (m.9804G>A) were confirmed in two families (each one subject, three eyes affected), without detection of a primary LHON mutation. One member presented a picture of right-sited optic neuropathy associated with a c.220C>G mutation in the ACO2 gene and a heterozygous c.185C>T mutation in the LDLR gene. Autosomal dominant optic atrophy was confirmed in three non-related families (five subjects with bilateral ION), where molecular genetic analyses confirmed four different heterozygous mutations in OPA1: c.1847+1G>T; c.2497-1G>A, 297A>G and c.(2983+1_2984-1)_(c.*3211) (2 splicing mutations, 1 missense mutation, and 1 gross deletion encompassing exons 30 and 31). Combining clinics and molecular genetics when evaluating patients with IONs helps in characterizing disease and, therefore, is strongly recommended for such patients.

Evaluation of deep convolutional neural networks for glaucoma detection

To investigate the performance of deep convolutional neural networks (DCNNs) for glaucoma discrimination using color fundus images STUDY DESIGN: A retrospective study PATIENTS AND METHODS: To investigate the discriminative ability of 3 DCNNs, we used a total of 3312 images consisting of 369 images from glaucoma-confirmed eyes, 256 images from glaucoma-suspected eyes diagnosed by a glaucoma expert, and 2687 images judged to be nonglaucomatous eyes by a glaucoma expert. We also investigated the effects of image size on the discriminative ability and heatmap analysis to determine which parts of the image contribute to the discrimination. Additionally, we used 465 poor-quality images to investigate the effect of poor image quality on the discriminative ability. Three DCNNs showed areas under the curve (AUCs) of 0.9 or more. The AUC of the DCNN using glaucoma-confirmed eyes against nonglaucomatous eyes was higher than that using glaucoma-suspected eyes against nonglaucomatous eyes by approximately 0.1. The image size did not affect the discriminative ability. Heatmap analysis showed that the optic disc area was the most important area for the discrimination of glaucoma. The image quality affected the discriminative ability, and the inclusion of poor-quality images in the analysis reduced the AUC by 0.1 to 0.2. DCNNs may be a useful tool for detecting glaucoma or glaucoma-suspected eyes by use of fundus color images. Proper preprocessing and collection of qualified images are essential to improving the discriminative ability.