Francesco Calivá

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.

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

Aims/hypothesisDiabetic 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.MethodsThe 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.ResultsThe 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/interpretationThe 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.

Automated detection of retinal landmarks for the identification of clinically relevant regions in fundus photography

Automatic, quick and reliable identification of retinal landmarks from fundus photography is key for measurements used in research, diagnosis, screening and treating of common diseases affecting the eyes. This study presents a fast method for the detection of the centre of mass of the vascular arcades, optic nerve head (ONH) and fovea, used in the definition of five clinically relevant areas in use for screening programmes for diabetic retinopathy (DR). Thirty-eight fundus photographs showing 7203 DR lesions were analysed to find the landmarks manually by two retina-experts and automatically by the proposed method. The automatic identification of the ONH and fovea were performed using template matching based on normalised cross correlation. The centre of mass of the arcades was obtained by fitting an ellipse on sample coordinates of the main vessels. The coordinates were obtained by processing the image with hessian filtering followed by shape analyses and finally sampling the results. The regions obtained manually and automatically were used to count the retinal lesions falling within, and to evaluate the method. 92.7% of the lesions were falling within the same regions based on the landmarks selected by the two experts. 91.7% and 89.0% were counted in the same areas identified by the method and the first and second expert respectively. The inter-repeatability of the proposed method and the experts is comparable, while the 100% intra-repeatability makes the algorithm a valuable tool in tasks like analyses in real-time, of large datasets and of intra-patient variability.

Exudate segmentation using fully convolutional neural networks and inception modules

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.

Microaneurysm detection using deep learning and interleaved freezing.

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 demonstrate its suitability for diabetic retinopathy screening applications.

Learning deep similarity in fundus photography

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.