Optic Nerve Head and Retinal Abnormalities Associated with Congenital Fibrosis of the Extraocular Muscles.

Congenital fibrosis of the extraocular muscles (CFEOM) is a congenital cranial dysinnervation disorder caused by developmental abnormalities affecting cranial nerves/nuclei innervating the extraocular muscles. Autosomal dominant CFEOM arises from heterozygous missense mutations of KIF21A or TUBB3. Although spatiotemporal expression studies have shown KIF21A and TUBB3 expression in developing retinal ganglion cells, it is unclear whether dysinnervation extends beyond the oculomotor system. We aimed to investigate whether dysinnervation extends to the visual system by performing high-resolution optical coherence tomography (OCT) scans characterizing retinal ganglion cells within the optic nerve head and retina. Sixteen patients with CFEOM were screened for mutations in KIF21A, TUBB3, and TUBB2B. Six patients had apparent optic nerve hypoplasia. OCT showed neuro-retinal rim loss. Disc diameter, rim width, rim area, and peripapillary nerve fiber layer thickness were significantly reduced in CFEOM patients compared to controls (p < 0.005). Situs inversus of retinal vessels was seen in five patients. Our study provides evidence of structural optic nerve and retinal changes in CFEOM. We show for the first time that there are widespread retinal changes beyond the retinal ganglion cells in patients with CFEOM. This study shows that the phenotype in CFEOM extends beyond the motor nerves.

Author Correction: Mobile Real-Time Grasshopper Detection and Data Aggregation Framework.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

Mobile Real-Time Grasshopper Detection and Data Aggregation Framework.

Insects of the family Orthoptera: Acrididae including grasshoppers and locust devastate crops and eco-systems around the globe. The effective control of these insects requires large numbers of trained extension agents who try to spot concentrations of the insects on the ground so that they can be destroyed before they take flight. This is a challenging and difficult task. No automatic detection system is yet available to increase scouting productivity, data scale and fidelity. Here we demonstrate MAESTRO, a novel grasshopper detection framework that deploys deep learning within RBG images to detect insects. MAESTRO uses a state-of-the-art two-stage training deep learning approach. The framework can be deployed not only on desktop computers but also on edge devices without internet connection such as smartphones. MAESTRO can gather data using cloud storge for further research and in-depth analysis. In addition, we provide a challenging new open dataset (GHCID) of highly variable grasshopper populations imaged in Inner Mongolia. The detection performance of the stationary method and the mobile App are 78 and 49 percent respectively; the stationary method requires around 1000 ms to analyze a single image, whereas the mobile app uses only around 400 ms per image. The algorithms are purely data-driven and can be used for other detection tasks in agriculture (e.g. plant disease detection) and beyond. This system can play a crucial role in the collection and analysis of data to enable more effective control of this critical global pest.

Exudates Segmentation using Fully Convolutional Neural Network and Auxiliary Codebook.

Diabetic retinopathy (DR) is an asymptotic complication of diabetes and the leading cause of preventable blindness in the working-age population. Early detection and treatment of DR is critical to avoid vision loss. Exudates are one of the earliest and most prevalent signs of DR. In this work, we propose a novel two-stage method for the detection and segmentation of exudates in fundus photographs. In the first stage, a fully convolutional neural network architecture is trained to segment exudates using small image patches. Next, an auxilary codebook is built from network's intermediate layer output using incremental principal component analysis. Finally, outputs of both systems are combined to produce final result. Compared to other methods, the proposed algorithm does not require computation of candidate regions or removal of other anatomical structures. Furthermore, a transfer learning approach was applied to improve the performance of the system. The proposed method was evaluated using publicly available E-Ophtha datasets. It achieved better results than the state-of-the-art methods in terms of sensitivity and specificity metrics. The proposed method accomplished better results using a diseased//not diseased evaluation scenario which indicates its applicability for screening purposes. Simplicity, performance, efficiency and robustness of the proposed method demonstrate its suitability for diabetic retinopathy screening applications.

DISCERN: Generative Framework for Vessel Segmentation using Convolutional Neural Network and Visual Codebook.

This paper presents a novel two-stage vessel segmentation framework applied to retinal fundus images. In the first stage a convolutional neural network (CNN) is used to correlate an image patch with a corresponding groundtruth reduced using Totally Random Trees Embedding. In the second stage training patches are forward propagated through CNN to create a visual codebook. The codebook is used to build a generative nearest neighbour search space that can be queried by feature vectors created through forward propagating previously-unseen patches through CNN. The proposed framework is able to generate segmentation patches that were not seen during training. Evaluated using publicly available datasets (DRIVE, STARE) demonstrated better performance than state-of-the-art methods in terms of multiple evaluation metrics. The accuracy, robustness, speed and simplicity of the proposed framework demonstrates its suitability for automated vessel segmentation.

Microaneurysm detection using fully convolutional neural networks.

BACKROUND AND OBJECTIVES: Diabetic retinopathy is a microvascular complication of diabetes that can lead to sight loss if treated not early enough. Microaneurysms are the earliest clinical signs of diabetic retinopathy. This paper presents an automatic method for detecting microaneurysms in fundus photographies. METHODS: A novel patch-based fully convolutional neural network with batch normalization layers and Dice loss function is proposed. Compared to other methods that require up to five processing stages, it requires only three. Furthermore, to the best of the authors' knowledge, this is the first paper that shows how to successfully transfer knowledge between datasets in the microaneurysm detection domain. RESULTS: The proposed method was evaluated using three publicly available and widely used datasets: E-Ophtha, DIARETDB1, and ROC. It achieved better results than state-of-the-art methods using the FROC metric. The proposed algorithm accomplished highest sensitivities for low false positive rates, which is particularly important for screening purposes. CONCLUSIONS: Performance, simplicity, and robustness of the proposed method demonstrates its suitability for diabetic retinopathy screening applications.

A fluid-dynamic based approach to reconnect the retinal vessels in fundus photography.

This paper introduces the use of fluid-dynamic modeling to determine the connectivity of overlapping venous and arterial vessels in fundus images. Analysis of the retinal vascular network may provide information related to systemic and local disorders. However, the automated identification of the vascular trees in retinal images is a challenging task due to the low signal-to-noise ratio, nonuniform illumination and the fact that fundus photography is a projection on to the imaging plane of three-dimensional retinal tissue. A zero-dimensional model was created to estimate the hemodynamic status of candidate tree configurations. Simulated annealing was used to search for an optimal configuration. Experimental results indicate that simulated annealing was very efficient on test cases that range from small to medium size networks, while ineffective on large networks. Although for large networks the nonconvexity of the cost function and the large solution space made searching for the optimal solution difficult, the accuracy (average success rate = 98.35%), and simplicity of our novel approach demonstrate its potential effectiveness in segmenting retinal vascular trees.

A new unified framework for the early detection of the progression to diabetic retinopathy from fundus images.

Human retina is a diverse and important tissue, vastly studied for various retinal and other diseases. Diabetic retinopathy (DR), a leading cause of blindness, is one of them. This work proposes a novel and complete framework for the accurate and robust extraction and analysis of a series of retinal vascular geometric features. It focuses on studying the registered bifurcations in successive years of progression from diabetes (no DR) to DR, in order to identify the vascular alterations. Retinal fundus images are utilised, and multiple experimental designs are employed. The framework includes various steps, such as image registration and segmentation, extraction of features, statistical analysis and classification models. Linear mixed models are utilised for making the statistical inferences, alongside the elastic-net logistic regression, boruta algorithm, and regularised random forests for the feature selection and classification phases, in order to evaluate the discriminative potential of the investigated features and also build classification models. A number of geometric features, such as the central retinal artery and vein equivalents, are found to differ significantly across the experiments and also have good discriminative potential. The classification systems yield promising results with the area under the curve values ranging from 0.821 to 0.968, across the four different investigated combinations.

Spatial distribution of early red lesions is a risk factor for development of vision-threatening diabetic retinopathy.

AIMS/HYPOTHESIS: Diabetic retinopathy is characterised by morphological lesions related to disturbances in retinal blood flow. It has previously been shown that the early development of retinal lesions temporal to the fovea may predict the development of treatment-requiring diabetic maculopathy. The aim of this study was to map accurately the area where lesions could predict progression to vision-threatening retinopathy. METHODS: The predictive value of the location of the earliest red lesions representing haemorrhages and/or microaneurysms was studied by comparing their occurrence in a group of individuals later developing vision-threatening diabetic retinopathy with that in a group matched with respect to diabetes type, age, sex and age of onset of diabetes mellitus who did not develop vision-threatening diabetic retinopathy during a similar observation period. RESULTS: The probability of progression to vision-threatening diabetic retinopathy was higher in a circular area temporal to the fovea, and the occurrence of the first lesions in this area was predictive of the development of vision-threatening diabetic retinopathy. The calculated peak value showed that the risk of progression was 39.5% higher than the average. There was no significant difference in the early distribution of lesions in participants later developing diabetic maculopathy or proliferative diabetic retinopathy. CONCLUSIONS/INTERPRETATION: The location of early red lesions in diabetic retinopathy is predictive of whether or not individuals will later develop vision-threatening diabetic retinopathy. This evidence should be incorporated into risk models used to recommend control intervals in screening programmes for diabetic retinopathy.

Summarising the retinal vascular calibres in healthy, diabetic and diabetic retinopathy eyes.

Retinal vessel calibre has been found to be an important biomarker of several retinal diseases, including diabetic retinopathy (DR). Quantifying the retinal vessel calibres is an important step for estimating the central retinal artery and vein equivalents. In this study, an alternative method to the already established branching coefficient (BC) is proposed for summarising the vessel calibres in retinal junctions. This new method combines the mean diameter ratio with an alternative to Murray׳s cube law exponent, derived by the fractal dimension,experimentally, and the branch exponent of cerebral vessels, as has been suggested in previous studies with blood flow modelling. For the above calculations, retinal images from healthy, diabetic and DR subjects were used. In addition, the above method was compared with the BC and was also applied to the evaluation of arteriovenous ratio as a biomarker of progression from diabetes to DR in four consecutive years, i.e. three/two/one years before the onset of DR and the first year of DR. Moreover, the retinal arteries and veins around the optic nerve head were also evaluated. The new approach quantifies the vessels more accurately. The decrease in terms of the mean absolute percentage error was between 0.24% and 0.49%, extending at the same time the quantification beyond healthy subjects.

A new tool to connect blood vessels in fundus retinal images.

This paper presents a novel tool that allows a user to reconstruct the retinal vascular network from fundus images. The retinal vasculature consists of trees of arteries and veins. Common segmentation algorithms are not able to completely segment out the blood vessels in fundus images. This failure results in a set of disconnected or broken up vascular segments. Reconstructing the whole network has crucial importance because it can offer insight into global features not considered so far, including retinal fluid dynamics. This tool uses implicit neural cost functions to join vessel segments. Results have shown that the quality of the segmentation affects the outcome of connectivity algorithms and by enhancing the segmentation the connectivity can be improved.

Evaluation of geometric features as biomarkers of diabetic retinopathy for characterizing the retinal vascular changes during the progression of diabetes.

Diabetic retinopathy (DR) has been widely studied and characterized. However, until now, it is unclear how different features, extracted from the retinal vasculature, can be associated with the progression of diabetes and therefore become biomarkers of DR. In this study, a comprehensive analysis is presented, in which four groups were created, using eighty fundus images from twenty patients, who have progressed to DR and they had no history of any other diseases (e.g. hypertension or glaucoma). The significance of the following features was evaluated: widths, angles, branching coefficient (BC), angle-to-BC ratio, standard deviations, means and medians of widths and angles, fractal dimension (FD), lacunarity and FD-to-lacunarity ratio, using a mixed model analysis of variance (ANOVA) design. All the features were measured from the same junctions of each patient, using an automated tool. The discriminative power of these features was evaluated, using decision trees and random forests classifiers. Cross validation and out-of-bag error were used to evaluate the classifiers' performance, calculating the area under the ROC curve (AUC) and the classification error. Widths, FD and FD-to-Lacunarity ratio were found to differ significantly. Random forests had a superior performance of 0.768 and 0.737 in the AUC for the two cases of classification, namely three-years-pre-DR/post-DR and two-years-pre-DR/post-DR respectively.

The association between retinal vascular geometry changes and diabetic retinopathy and their role in prediction of progression--an exploratory study.

BACKGROUND: The study describes the relationship of retinal vascular geometry (RVG) to severity of diabetic retinopathy (DR), and its predictive role for subsequent development of proliferative diabetic retinopathy (PDR). METHODS: The research project comprises of two stages. Firstly, a comparative study of diabetic patients with different grades of DR. (No DR: Minimal non-proliferative DR: Severe non-proliferative DR: PDR) (10:10: 12: 19). Analysed RVG features including vascular widths and branching angles were compared between patient cohorts. A preliminary statistical model for determination of the retinopathy grade of patients, using these features, is presented. Secondly, in a longitudinal predictive study, RVG features were analysed for diabetic patients with progressive DR over 7 years. RVG at baseline was examined to determine risk for subsequent PDR development. RESULTS: In the comparative study, increased DR severity was associated with gradual vascular dilatation (p = 0.000), and widening of the bifurcating angle (p = 0.000) with increase in smaller-child-vessel branching angle (p = 0.027). Type 2 diabetes and increased diabetes duration were associated with increased vascular width (p = <0.05 In the predictive study, at baseline, reduced small-child vascular width (OR = 0.73 (95% CI 0.58-0.92)), was predictive of future progression to PDR. CONCLUSIONS: The study findings suggest that RVG alterations can act as novel markers indicative of progression of DR severity and establishment of PDR. RVG may also have a potential predictive role in determining the risk of future retinopathy progression.

Validating retinal fundus image analysis algorithms: issues and a proposal.

This paper concerns the validation of automatic retinal image analysis (ARIA) algorithms. For reasons of space and consistency, we concentrate on the validation of algorithms processing color fundus camera images, currently the largest section of the ARIA literature. We sketch the context (imaging instruments and target tasks) of ARIA validation, summarizing the main image analysis and validation techniques. We then present a list of recommendations focusing on the creation of large repositories of test data created by international consortia, easily accessible via moderated Web sites, including multicenter annotations by multiple experts, specific to clinical tasks, and capable of running submitted software automatically on the data stored, with clear and widely agreed-on performance criteria, to provide a fair comparison.

Manual measurement of retinal bifurcation features.

This paper introduces a new computerized tool for accurate manual measurement of features of retinal bifurcation geometry, designed for use in investigating correlations between measurement features and clinical conditions. The tool uses user-placed rectangles to measure the vessel width, and lines placed along vessel center lines to measure the angles. An analysis is presented of measurements taken from 435 bifurcations. These are compared with theoretical predictions based on optimality principles presented in the literature. The new tool shows better agreement with the theoretical predictions than a simpler manual method published in the literature, but there remains a significant discrepancy between current theory and measured geometry.

Automated analysis of retinal vascular network connectivity.

This paper describes an algorithm that forms a retinal vessel graph by analysing the potential connectivity of segmented retinal vessels. Self organizing feature maps (SOFMs) are used to model implicit cost functions for the junction geometry. The algorithm uses these cost functions to resolve the configuration of local sets of segment ends, thus determining the network connectivity. The system includes specialized algorithms to handle overlapping vessels. The algorithm is tested on junctions drawn from the public-domain DRIVE database.

An active contour model for segmenting and measuring retinal vessels.

This paper presents an algorithm for segmenting and measuring retinal vessels, by growing a "Ribbon of Twins" active contour model, which uses two pairs of contours to capture each vessel edge, while maintaining width consistency. The algorithm is initialized using a generalized morphological order filter to identify approximate vessels centerlines. Once the vessel segments are identified the network topology is determined using an implicit neural cost function to resolve junction configurations. The algorithm is robust, and can accurately locate vessel edges under difficult conditions, including noisy blurred edges, closely parallel vessels, light reflex phenomena, and very fine vessels. It yields precise vessel width measurements, with subpixel average width errors. We compare the algorithm with several benchmarks from the literature, demonstrating higher segmentation sensitivity and more accurate width measurement.

REVIEW - a reference data set for retinal vessel profiles.

This paper describes REVIEW, a new retinal vessel reference dataset. This dataset includes 16 images with 193 vessel segments, demonstrating a variety of pathologies and vessel types. The vessel edges are marked by three observers using a special drawing tool. The paper also describes the algorithm used to process these segments to produce vessel profiles, against which vessel width measurement algorithms can be assessed. Recommendations are given for use of the dataset in performance assessment. REVIEW can be downloaded from http://ReviewDB.lincoln.ac.uk.