Noelia Barreira

Retinal verification using a feature points-based biometric pattern

Biometrics refer to identity verification of individuals based on some physiologic or behavioural characteristics. The typical authentication process of a person consists in extracting a biometric pattern of him/her and matching it with the stored pattern for the authorised user obtaining a similarity value between patterns. In this work an efficient method for persons authentication is showed. The biometric pattern of the system is a set of feature points representing landmarks in the retinal vessel tree. The pattern extraction and matching is described. Also, a deep analysis of similarity metrics performance is presented for the biometric system. A database with samples of retina images from users on different moments of time is used, thus simulating a hard and real environment of verification. Even in this scenario, the system allows to establish a wide confidence band for the metric threshold where no errors are obtained for training and test sets.

Sirius: A web-based system for retinal image analysis

PURPOSE Retinal image analysis can lead to early detection of several pathologies such as hypertension or diabetes. Screening processes require the evaluation of a high amount of visual data and, usually, the collaboration between different experts and different health care centers. These usual routines demand new fast and automatic solutions to deal with these situations. This work introduces Sirius (System for the Integration of Retinal Images Understanding Services), a web-based system for image analysis in the retinal imaging field. METHODS Sirius provides a framework for ophthalmologists or other experts in the field to collaboratively work using retinal image-based applications in a distributed, fast and reliable environment. Sirius consists of three main components: the web client that users interact with, the web application server that processes all client requests and the service module that performs the image processing tasks. In this work, we present a service for the analysis of retinal microcirculation using a semi-automatic methodology for the computation of the arteriolar-to-venular ratio (AVR). RESULTS Sirius has been evaluated in different real environments, involving health care systems, to test its performance. First, the AVR service was validated in terms of precision and efficiency and then, the framework was evaluated in different real scenarios of medical centers. CONCLUSIONS Sirius is a web-based application providing a fast and reliable work environment for retinal experts. The system allows the sharing of images and processed results between remote computers and provides automated methods to diminish inter-expert variability in the analysis of the images.

Personal verification based on extraction and characterisation of retinal feature points

This paper describes a methodology of verification of individuals based on a retinal biometric pattern. The pattern consists in feature points of the retinal vessel tree, namely bifurcations and crossovers. These landmarks are detected and characterised adding semantic information to the biometric pattern. The typical authentication process of a person once extracted the biometric pattern includes matching it with the stored pattern for the authorised user obtaining a similarity value between them. A matching algorithm and a deep analysis of similarity metrics performance is presented. The semantic information added for the feature points allows to reduce the computation load in the matching process as only points classified equally can be matched. The system is capable of establishing a safe confidence band in the similarity measure space between scores for patterns of the same individual and between different individuals.

Genetic approaches for topological active nets optimization

The topological active nets (TANs) model is a deformable model used for image segmentation. It integrates features of region-based and edge-based segmentation techniques so it is able to fit the contours of the objects and model their inner topology. Also, topological changes in its structure allow the detection of concave and convex contours, holes, and several objects in the scene. Since the model deformation is based on the minimization of an energy functional, the adjustment depends on the minimization algorithm. This paper presents two evolutionary approaches to the energy minimization problem in the TAN model. The first proposal is a genetic algorithm with ad hoc operators whereas the second approach is a hybrid model that combines genetic and greedy algorithms. Both evolutionary approaches improve the accuracy of the segmentation even though only the hybrid model allows topological changes in the model structure.

On the Automatic Computation of the Arterio-Venous Ratio in Retinal Images: Using Minimal Paths for the Artery/Vein Classification

Abnormalities in the retinal vessel tree are associated with different pathologies. Usually, they affect arteries and veins differently. In this regard, the arteriovenous ratio(AVR) is a measure of retinal vessel caliber, widely used in medicine to study the influence of these irregularities in disease evolution. Hence, the development of an automatic tool for AVR computation as well as any other tool for diagnosis support need an objective, reliable and fast artery/vein classifier. This paper proposes a technique to improve the retinal vessel classification in an AVR computation framework. The proposed methodology combines a color clustering strategy and a vessel tracking procedure based on minimal path approaches. The tests performed with 58 images manually labeled by three experts show promising results.

Localization and extraction of the optic disc using the fuzzy circular hough transform

This paper presents an algorithm for automatic extraction of the optic disc in retinal images. The developed system consists of two main parts. Firstly, the localization of the region containing the optic disc is performed by means of a clustering algorithm. Then, in order to extract the optic disc, the fuzzy circular Hough transform is applied to the edges of the region. The optic disc might not be extracted since there are vessels in the inside of the optic disc. To avoid this, a crease extraction algorithm is applied to the retinal image. The vessels are extracted and the vessel edge points contained in the edge image are removed. The final system was tested by ophthalmologists. The localization of the region of interest is correct in 100% of the cases and the extraction of the optic disc is obtained in 98% of the cases.

Topological active volumes

The topological active volumes (TAVs) model is a general model for 3D image segmentation. It is based on deformable models and integrates features of region-based and boundary-based segmentation techniques. Besides segmentation, it can also be used for surface reconstruction and topological analysis of the inside of detected objects. The TAV structure is flexible and allows topological changes in order to improve the adjustment to objects local characteristics, find several objects in the scene, and identify and delimit holes in detected structures. This paper describes the main features of the TAV model and shows its ability to segment volumes in an automated manner.

Improvements in retinal vessel clustering techniques: towards the automatic computation of the arterio venous ratio

Retinal blood vessel structure is an important indicator for diagnosis of several diseases such as diabetes, hypertension, arteriosclerosis, or stroke. These pathologies cause early alterations in the blood vessels that affect veins and arteries differently. In this sense, the arterio venous ratio is a measurement that evaluates these alterations and, consequently, the condition of the patient. Thus, a precise identification of both types of vessels is necessary in order to develop an automatic diagnosis system, to quantify the seriousness of disease, or to monitor the therapy. The classification of vessels into veins and arteries is difficult due to the inhomogeneity in the retinal image lightness and the similarity of both structures. In this paper, several image feature sets have been combined with three clustering strategies in order to find a suitable characterization methodology. The best strategy has managed to classify correctly the 86.34% of the vessels improving the results obtained with previous techniques.

Automatic classification of the interferential tear film lipid layer using colour texture analysis

The tear film lipid layer is heterogeneous among the population. Its classification depends on its thickness and can be done using the interference pattern categories proposed by Guillon. This papers presents an exhaustive study about the characterisation of the interference phenomena as a texture pattern, using different feature extraction methods in different colour spaces. These methods are first analysed individually and then combined to achieve the best results possible. The principal component analysis (PCA) technique has also been tested to reduce the dimensionality of the feature vectors. The proposed methodologies have been tested on a dataset composed of 105 images from healthy subjects, with a classification rate of over 95% in some cases.

Using retinex image enhancement to improve the artery/vein classification in retinal images

A precise characterization of the retinal vessels into veins and arteries is necessary to develop automatic tools for diagnosis support. As medical experts, most of the existing methods use the vessel lightness or color for the classification, since veins are darker than arteries. However, retinal images often suffer from inhomogeneity problems in lightness and contrast, mainly due to the image capturing process and the curved retina surface. This fact and the similarity between both types of vessels make difficult an accurate classification, even for medical experts. In this paper, we propose an automatic approach for the retinal vessel classification that combines an image enhancement procedure based on the retinex theory and a clustering process performed in several overlapped areas within the retinal image. Experimental results prove the accuracy of our approach in terms of miss-classified and unclassified vessels.