Manuel Emilio Gegúndez-Arias

A New Supervised Method for Blood Vessel Segmentation in Retinal Images by Using Gray-Level and Moment Invariants-Based Features

This paper presents a new supervised method for blood vessel detection in digital retinal images. This method uses a neural network (NN) scheme for pixel classification and computes a 7-D vector composed of gray-level and moment invariants-based features for pixel representation. The method was evaluated on the publicly available DRIVE and STARE databases, widely used for this purpose, since they contain retinal images where the vascular structure has been precisely marked by experts. Method performance on both sets of test images is better than other existing solutions in literature. The method proves especially accurate for vessel detection in STARE images. Its application to this database (even when the NN was trained on the DRIVE database) outperforms all analyzed segmentation approaches. Its effectiveness and robustness with different image conditions, together with its simplicity and fast implementation, make this blood vessel segmentation proposal suitable for retinal image computer analyses such as automated screening for early diabetic retinopathy detection.

Detecting the Optic Disc Boundary in Digital Fundus Images Using Morphological, Edge Detection, and Feature Extraction Techniques

Optic disc (OD) detection is an important step in developing systems for automated diagnosis of various serious ophthalmic pathologies. This paper presents a new template-based methodology for segmenting the OD from digital retinal images. This methodology uses morphological and edge detection techniques followed by the Circular Hough Transform to obtain a circular OD boundary approximation. It requires a pixel located within the OD as initial information. For this purpose, a location methodology based on a voting-type algorithm is also proposed. The algorithms were evaluated on the 1200 images of the publicly available MESSIDOR database. The location procedure succeeded in 99% of cases, taking an average computational time of 1.67 s. with a standard deviation of 0.14 s. On the other hand, the segmentation algorithm rendered an average common area overlapping between automated segmentations and true OD regions of 86%. The average computational time was 5.69 s with a standard deviation of 0.54 s. Moreover, a discussion on advantages and disadvantages of the models more generally used for OD segmentation is also presented in this paper.

Obtaining optic disc center and pixel region by automatic thresholding methods on morphologically processed fundus images

Development of automatic retinal disease diagnosis systems based on retinal image computer analysis can provide remarkably quicker screening programs for early detection. Such systems are mainly focused on the detection of the earliest ophthalmic signs of illness and require previous identification of fundal landmark features such as optic disc (OD), fovea or blood vessels. A methodology for accurate center-position location and OD retinal region segmentation on digital fundus images is presented in this paper. The methodology performs a set of iterative opening-closing morphological operations on the original retinography intensity channel to produce a bright region-enhanced image. Taking blood vessel confluence at the OD into account, a 2-step automatic thresholding procedure is then applied to obtain a reduced region of interest, where the center and the OD pixel region are finally obtained by performing the circular Hough transform on a set of OD boundary candidates generated through the application of the Prewitt edge detector. The methodology was evaluated on 1200 and 1748 fundus images from the publicly available MESSIDOR and MESSIDOR-2 databases, acquired from diabetic patients and thus being clinical cases of interest within the framework of automated diagnosis of retinal diseases associated to diabetes mellitus. This methodology proved highly accurate in OD-center location: average Euclidean distance between the methodology-provided and actual OD-center position was 6.08, 9.22 and 9.72 pixels for retinas of 910, 1380 and 1455 pixels in size, respectively. On the other hand, OD segmentation evaluation was performed in terms of Jaccard and Dice coefficients, as well as the mean average distance between estimated and actual OD boundaries. Comparison with the results reported by other reviewed OD segmentation methodologies shows our proposal renders better overall performance. Its effectiveness and robustness make this proposed automated OD location and segmentation method a suitable tool to be integrated into a complete prescreening system for early diagnosis of retinal diseases.

Locating the fovea center position in digital fundus images using thresholding and feature extraction techniques.

A new methodology for detecting the fovea center position in digital retinal images is presented in this paper. A pixel is firstly searched for within the foveal region according to its known anatomical position relative to the optic disc and vascular tree. Then, this pixel is used to extract a fovea-containing subimage on which thresholding and feature extraction techniques are applied so as to find fovea center. The methodology was evaluated on 1200 fundus images from the publicly available MESSIDOR database, 660 of which present signs of diabetic retinopathy. In 93.92% of these images, the distance between the methodology-provided and actual fovea center position remained below 1/4 of one standard optic disc radius (i.e., 17, 26, and 27 pixels for MESSIDOR retinas of 910, 1380 and 1455 pixels in size, respectively). These results outperform all the reviewed methodologies available in literature. Its effectiveness and robustness with different illness conditions makes this proposal suitable for retinal image computer analyses such as automated screening for early diabetic retinopathy detection.

A Function for Quality Evaluation of Retinal Vessel Segmentations

Retinal blood vessel assessment plays an important role in the diagnosis of ophthalmic pathologies. The use of digital images for this purpose enables the application of a computerized approach and has fostered the development of multiple methods for automated vascular tree segmentation. Metrics based on contingency tables for binary classification have been widely used for evaluating the performance of these algorithms. Metrics from this family are based on the measurement of a success or failure rate in the detected pixels, obtained by means of pixel-to-pixel comparison between the automated segmentation and a manually-labeled reference image. Therefore, vessel pixels are not considered as a part of a vascular structure with specific features. This paper contributes a function for the evaluation of global quality in retinal vessel segmentations. This function is based on the characterization of vascular structures as connected segments with measurable area and length. Thus, its design is meant to be sensitive to anatomical vascularity features. Comparison of results between the proposed function and other general quality evaluation functions shows that this proposal renders a high matching degree with human quality perception. Therefore, it can be used to enhance quality evaluation in retinal vessel segmentations, supplementing the existing functions. On the other hand, from a general point of view, the applied concept of measuring descriptive properties may be used to design specialized functions aimed at segmentation quality evaluation in other complex structures.

Inter-observer Reliability and Agreement Study on Early Diagnosis of Diabetic Retinopathy and Diabetic Macular Edema Risk

The degree of inter-observer agreement on early diagnosis of diabetic retinopathy (DR) and diabetic macular edema (DME) risk has been assessed in this paper. Three sets of DR and DME risk ratings on 529 diabetic patients were independently built by ophthalmologists of the Andalusian (Spain) Health Service through observation of two macula-centered retinographies from these patients (one image per eye, 1058 images). DR was graded on a 0–3 scale from DR-unrelated to severe DR, while DME risk was graded on a 0–2 scale from no risk to moderate-severe risk. Inter-rater reliability (IRR) assessment was performed by the intra-class correlation (ICC) and two kappa-like statistical variants —Light’s kappa and Fleiss’ kappa. ICC-computed IRR showed excellent agreement between our three coders: values were 0.844 (95 % CI, 0.822–0.865) and 0.833 (95 % CI, 0.805–0.853) for DR and DME ratings, respectively. Kappa index-quantified assessment resulted in substantial agreement, as both kappa indexes rendered values around 0.60 for DR and 0.75 for DME ratings. All computed IRR metrics proved high inter-observer agreement and consistency among DR degree and DME risk diagnoses. Reliable diagnosis provided by human experts supports the generation of reference standards that can be used in the development of automatic DR diagnosis systems.

An exudate detection method for diagnosis risk of diabetic macular edema in retinal images using feature-based and supervised classification

AbstractThe present paper aims at presenting the methodology and first results of a detection system of risk of diabetic macular edema (DME) in fundus images. The system is based on the detection of retinal exudates (Ex), whose presence in the image is clinically used for an early diagnosis of the disease. To do so, the system applies digital image processing algorithms to the retinal image in order to obtain a set of candidate regions to be Ex, which are validated by means of feature extraction and supervised classification techniques. The diagnoses provided by the system on 1058 retinographies of 529 diabetic patients at risk of having DME show that the system can operate at a level of sensitivity comparable to that of ophthalmological specialists: it achieved 0.9000 sensitivity per patient against 0.7733, 0.9133 and 0.9000 of several specialists, where the false negatives were mild clinical cases of the disease. In addition, the level of specificity reached by the system was 0.6939, high enough to screen about 70% of the patients with no evidence of DME. These values show that the system fulfils the requirements for its possible integration into a complete diabetic retinopathy pre-screening tool for the automated management of patients within a screening programme. Graphical AbstractDiagnosis system of risk of diabetic macular edema (DME) based on exudate (Ex) detection in fundus images.

Microaneurysm Candidate Extraction Methodology in Retinal Images for the Integration into Classification-Based Detection Systems

Diabetic Retinopathy (DR) is one of the most common complications of long-term diabetes. It is a progressive disease that causes retina damage. DR is asymptomatic at the early stages and can lead to blindness if it is not treated in time. Thus, patients with diabetes should be routinely evaluated through systemic screening programs using retinal photography. Automated pre-screening systems, aimed at filtering cases of patients not affected by the disease using retinal images, can reduce the specialist’ workload. Since microaneurysms (MAs) appear as a first sign of DR in retina, early detection of this lesion is an essential step in automatic detection of DR. Most of MA detection systems are based on supervised classification and are designed in two stages: MA candidate extraction and further description and classification. This work proposes a method that addresses the first stage. Evaluation of the proposed method on a test dataset of 83 images shows that the method could operate at sensitivities of 74%, 82% and 87% with a number of 92, 140 and 194 false positives per image, respectively. These results show that the methodology detects low contrast MAs with the background and is suitable to be integrated in a complete classification-based MA detection system.

A tool for automated diabetic retinopathy pre-screening based on retinal image computer analysis

AIM This paper presents a methodology and first results of an automatic detection system of first signs of Diabetic Retinopathy (DR) in fundus images, developed for the Health Ministry of the Andalusian Regional Government (Spain). MATERIAL AND METHODS The system detects the presence of microaneurysms and haemorrhages in retinography by means of techniques of digital image processing and supervised classification. Evaluation was conducted on 1058 images of 529 diabetic patients at risk of presenting evidence of DR (an image of each eye is provided). To this end, a ground-truth diagnosis was created based on gradations performed by 3 independent ophthalmology specialists. RESULTS The comparison between the diagnosis provided by the system and the reference clinical diagnosis shows that the system can work at a level of sensitivity that is similar to that achieved by experts (0.9380 sensitivity per patient against 0.9416 sensitivity of several specialists). False negatives have proven to be mild cases. Moreover, while the specificity of the system is significantly lower than that of human graders (0.5098), it is high enough to screen more than half of the patients unaffected by the disease. CONCLUSION Results are promising in integrating this system in DR screening programmes. At an early stage, the system could act as a pre-screening system, by screening healthy patients (with no obvious signs of DR) and identifying only those presenting signs of the disease.

Automated Detection of Diabetic Macular Edema Risk in Fundus Images

This paper is aimed at assessing the initial performance of a computer-based system to detect the risk of diabetic macular edema (DME). The development of this tool was funded by the Health Ministry of the Andalusian Regional Government (Spain) with the purpose of being integrated into a complete system for early diagnosis of diabetic retinopathy (DR).