Search

nsects 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 storage 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.

Diabetic retinopathy (DR) is a chronic progressive sight-threatening disease of the retinal microvasculature associated with prolonged high elevated blood sugar levels (hyperglycemia) as well as other linked conditions such as hypertension. DR can be asymptomatic for long periods and as the disease progresses, patients can experience mild sight impairments. However, late stages of the disease can lead to severe sight- threatening conditions and potential blindness, if untreated. Vision loss can occur secondary to either leak in the center of the retina (macula)—leading to diabetic macular edema—or due to the development of new vessels that can bleed inside the eye. DR can manifest in forms of blurred and/or fluctuating vision, dark spots fluctuating during saccades, empty vision areas, and reduced vision. From a clinical perspective, DR can be classified as a nonproliferative stage (NPDR) or as a more ad- vanced proliferative stage (PDR). In NPDR, damages occur in the inner retinal blood vessels, which leak of fluids onto the retina, resulting in edema and swelling [1]. In this scenario, Frank [2] defines lesions as the major sign of retinopathy, and clusters them as microaneurysms (MAs), hemorrhages (HMs), hard and soft exudates (EXs), intraretinal microvascular abnormalities (IRMA), and venous beading (VB). NPDR can be graded as mild, moderate, or severe. Mild NPDR occurs with at least one MA. Moderate NPDR occurs with scattered retinal deep dot and blot HMs, and/or cotton wool spots CWS (soft exudates) and IRMAs but not as extensive as severe NPDR. The diagnosis of severe NPDR is based on the 4:2:1 rule of the ETDRS [2a]. Furthermore, IRMA can be present in each quadrant. With respect to PDR, abnormal development and angiogenesis of new vessels are the main representative character- istics of the disease: new blood vessels can grow in different areas of retinal surface or at the surface of the optic disc. The former are defined as New Vessels Elsewhere (NVE), the

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.

Diabetic retinopathy is an eye disease associated with diabetes mellitus and also it is the leading cause of preventable blindness in working-age population. Early detection and treatment of DR is essential to prevent vision loss. Exudates are one of the earliest signs of diabetic retinopathy. This paper proposes an automatic method for the detection and segmentation of exudates in fundus photographies. A novel fully convolutional neural network architecture with Inception modules is proposed. Compared to other methods it does not require the removal of other anatomical structures. Furthermore, a transfer learning approach is applied between small datasets of different modalities from the same domain. To the best of authors’ knowledge, it is the first time that such approach has been used in the exudate segmentation domain. 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 algorithm 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.

Diabetes affects one in eleven adults. Diabetic retinopathy is a microvascular complication of diabetes and the leading cause of blindness in the working-age population. Microaneurysms are the earliest clinical signs of diabetic retinopathy. This paper proposes an automatic method for detecting microaneurysms in fundus photographies. A novel patch-based fully convolutional neural network for detection of microaneurysms is proposed. Compared to other methods that require five processing stages, it requires only two. Furthermore, a novel network fine-tuning scheme called Interleaved Freezing is presented. This procedure significantly reduces the amount of time needed to re-train a network and produces competitive results. The proposed method was evaluated using publicly available and widely used datasets: E-Ophtha and ROC. It outperforms the state-of-the-art methods in terms of free-response receiver operatic characteristic (FROC) metric. Simplicity, performance, efficiency and robustness of the proposed method demonstrates its suitability for diabetic retinopathy screening applications.

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.

Similarity learning is one of the most fundamental tasks in image analysis. The ability to extract similar images in the medical domain as part of content-based image retrieval (CBIR) systems has been researched for many years. The vast majority of methods used in CBIR systems are based on hand-crafted feature descriptors. The approximation of a similarity mapping for medical images is difficult due to the big variety of pixel-level structures of interest. In fundus photography (FP) analysis, a subtle difference in e.g. lesions and vessels shape and size can result in a different diagnosis. In this work, we demonstrated how to learn a similarity function for image patches derived directly from FP image data without the need of manually designed feature descriptors. We used a convolutional neural network (CNN) with a novel architecture adapted for similarity learning to accomplish this task. Furthermore, we explored and studied multiple CNN architectures. We show that our method can approximate the similarity between FP patches more efficiently and accurately than the state-of- the-art feature descriptors, including SIFT and SURF using a publicly available dataset. Finally, we observe that our approach, which is purely data-driven, learns that features such as vessels calibre and orientation are important discriminative factors, which resembles the way how humans reason about similarity. To the best of authors knowledge, this is the first attempt to approximate a visual similarity mapping in FP. © (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.

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.

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.

Purpose: Several studies have established, using various measurement modalities, that progression from diabetes to diabetic retinopathy is associated with changes in haemodynamics or measurable vascular geometry. In this study we take vessel measurements from standard fundus images, and estimate haemodynamic parameters (which are not directly observable) using a simple haemodynamic model. We show that there are statistically significant changes in some estimated haemodynamic parameters associated with the development of DR. Methods: A longitudinal study of twenty-four subjects was conducted. For each subject four fundus images were used, taken annually during the three years before the appearance of DR and in the first year of DR. A venous and arterial vascular bifurcation, each of which consisted of a parent vessel and two child branches was extracted, and at the branching nodes a zero dimensional model estimated the fluid dynamic conditions in terms of volumetric blood flow, blood flow velocity, nodal pressure, wall shear stress and Reynolds number. These features were statistically analyzed using linear mixed models. Results: A number of parameters, primarily venous, showed significant change with the development of DR, including early change two years before the onset of DR. A large proportion of overall variance is accounted for by individual patient differences, making progressive study essential. Conclusion: This is the first paper to demonstrate that haemodynamic feature estimates extracted from standard fundus images are sensitive to progression from diabetes to DR. In our future work, we aim to test whether the variations in haemodynamic conditions are predictive of progression prior to the appearance of retinal lesions.