Sandra Morales

Automatic Detection of Optic Disc Based on PCA and Mathematical Morphology

The algorithm proposed in this paper allows to automatically segment the optic disc from a fundus image. The goal is to facilitate the early detection of certain pathologies and to fully automate the process so as to avoid specialist intervention. The method proposed for the extraction of the optic disc contour is mainly based on mathematical morphology along with principal component analysis (PCA). It makes use of different operations such as generalized distance function (GDF), a variant of the watershed transformation, the stochastic watershed, and geodesic transformations. The input of the segmentation method is obtained through PCA. The purpose of using PCA is to achieve the grey-scale image that better represents the original RGB image. The implemented algorithm has been validated on five public databases obtaining promising results. The average values obtained (a Jaccards and Dices coefficients of 0.8200 and 0.8932, respectively, an accuracy of 0.9947, and a true positive and false positive fractions of 0.9275 and 0.0036) demonstrate that this method is a robust tool for the automatic segmentation of the optic disc. Moreover, it is fairly reliable since it works properly on databases with a large degree of variability and improves the results of other state-of-the-art methods.

Retinal Disease Screening through Local Binary Patterns

This paper investigates discrimination capabilities in the texture of fundus images to differentiate between pathological and healthy images. For this purpose, the performance of local binary patterns (LBP) as a texture descriptor for retinal images has been explored and compared with other descriptors such as LBP filtering and local phase quantization. The goal is to distinguish between diabetic retinopathy (DR), age-related macular degeneration (AMD), and normal fundus images analyzing the texture of the retina background and avoiding a previous lesion segmentation stage. Five experiments (separating DR from normal, AMD from normal, pathological from normal, DR from AMD, and the three different classes) were designed and validated with the proposed procedure obtaining promising results. For each experiment, several classifiers were tested. An average sensitivity and specificity higher than 0.86 in all the cases and almost of 1 and 0.99, respectively, for AMD detection were achieved. These results suggest that the method presented in this paper is a robust algorithm for describing retina texture and can be useful in a diagnosis aid system for retinal disease screening.

Computer-Aided Diagnosis Software for Hypertensive Risk Determination Through Fundus Image Processing

The goal of the software proposed in this paper is to assist ophthalmologists in diagnosis and disease prevention, helping them to determine cardiovascular risk or other diseases where the vessels can be altered, as well as to monitor the pathology progression and response to different treatments. The performance of the tool has been evaluated by means of a double-blind study where its sensitivity, specificity, and reproducibility to discriminate between health fundus (without cardiovascular risk) and hypertensive patients has been calculated in contrast to an expert ophthalmologist opinion obtained through a visual inspection of the fundus image. An improvement of almost 20% has been achieved comparing the system results with the clinical visual classification.

BRAIM: A computer-aided diagnosis system for neurodegenerative diseases and brain lesion monitoring from volumetric analyses

BACKGROUND AND OBJECTIVE This paper presents BRAIM, a computer-aided diagnosis (CAD) system to help clinicians in diagnosing and treatment monitoring of brain diseases from magnetic resonance image processing. BRAIM can be used for early diagnosis of neurodegenerative diseases such as Parkinson, Alzheimer or Multiple Sclerosis and also for brain lesion diagnosis and monitoring. METHODS The developed CAD system includes different user-friendly tools for segmenting and determining whole brain and brain structure volumes in an easy and accurate way. Specifically, three types of measurements can be performed: (1) total volume of white, gray matter and cerebrospinal fluid; (2) brain structure volumes (volume of putamen, thalamus, hippocampus and caudate nucleus); and (3) brain lesion volumes. RESULTS As a proof of concept, some study cases were analyzed with the presented system achieving promising results. In addition to be used to quantify treatment effectiveness in patients with brain lesions, it was demonstrated that BRAIM is able to classify a subject according to the brain volume measurements using as reference a healthy control database created for this purpose. CONCLUSIONS The CAD system presented in this paper simplifies the daily work of clinicians and provides them with objective and quantitative volume data for prospective and retrospective analyses.

Glaucoma diagnosis by means of optic cup feature analysis in color fundus images

Glaucoma is an asymptomatic eye disease and one of the major causes of irreversible blindness worldwide. For this reason, there have been significant advances in automatic screening tools for early detection. In this paper, an automatic glaucoma diagnosis algorithm based on retinal fundus image is presented. This algorithm uses anatomical characteristics such as the position of the vessels and the cup within the optic nerve. Using several color spaces and the Stochastic Watershed transformation, different characteristics of the optic nerve were analyzed in order to distinguish between a normal and a glaucomatous fundus. The proposed algorithm was evaluated on 53 images (24 normal and 29 glaucomatous images). The specificity and sensitivity obtained by the proposed algorithm are 0.81 and 0.87 using Luv color space, which means considerable performance in diagnosis systems.

Detection of diabetic retinopathy and age-related macular degeneration from fundus images through local binary patterns and random forests

This work focuses on differentiating between pathological and healthy fundus images. The goal is to distinguish between diabetic retinopathy (DR), age-related macular degeneration (AMD) and normal images by analysing the texture of the retina background. Local Binary Patterns (LBP) are used as texture descriptors. The two class problems DR vs. normal and AMD vs. normal, as well as the three class problem of DR, AMD, and normal, have been tested and have obtained promising results. An average sensitivity and specificity higher than 0.86 in all the cases and almost of 0.96 for AMD detection were achieved with a random forest classifier. These results suggest that LBP is a robust texture descriptor for retinal images and the method proposed in this paper, analysing the retina background directly and avoiding difficult lesion segmentation, can be useful for diagnostic aid.

Significant point characterization in fundus images

This paper describes a new approach to identify significant points in retinal images. Significant points such as bifurcations and crossovers define and characterize the retinal vascular network. This approach is based on using hit-or-miss transformation to detect terminal, bifurcation and simple crossing points and performs a post-processing stage to identify complex intersections. The post-processing focuses on the idea that the intersection of two vessels creates a sort of close loop formed by the vessels and this effect can be used to differentiate a bifurcation and a crossover. Experimental results show quantitative improvements if the proposed method is compared with other state-of-the-art work by reducing the number of false positives and negatives in the significant point detection. Therefore, the result of this work is an effective significant point detection algorithm and can be useful for cardiovascular disease diagnosis, biometrics and image registration.

Determination of Bifurcation Angles of the Retinal Vascular Tree through Multiple Orientation Estimation based on Regularized Morphological Openings

This paper describes a new approach to compute bifurcation angles in retinal images. This approach is based on the estimation of multiple orientations at each pixel of a gray retinal image. The main orientations are provided by directional openings whose outputs are regularized in order to extend the orientation information to the whole image. The detection of vessel bifurcations is based on the coexistence of two or more than two different main orientations at the same pixel. Once the bifurcations and crossovers has been identified, bifurcation angles are calculated. The proposed procedure of computing bifurcation angles by means of orientation estimation at all pixels of the gray level image is much more stable than those methods which are based on the skeleton of the vascular tree, since a slight variation of a pixel of the skeleton can produce a significant change in the angle value.

Probability density function of object contours using regional regularized stochastic watershed

In this paper, a probability density function of object contours based on the stochastic watershed transform is carried out. The watershed transform produces an over-segmentation of the image due to noise, illumination problems, low contrast, etc., because each regional minimum of the image gives place to a region in the output image. To solve this problem, the efforts are focused on the definition of markers to impose new minima in the image, and enhancing the gradient image. The stochastic watershed performs a probability density function (pdf) of the object contours based on a MonteCarlo simulation of random markers. A variation of the method for defining this pdf based on regional regularization of the image is carried out. The objective is to obtain a pdf of the object contours with less noise and better contrast than that produced by the stochastic watershed to use it as a new gradient image for segmentation purposes.

Feature extraction for retinal vascular network classification

The analysis of retinal blood vessels provides useful information for medical diagnosis of several diseases such as cardiovascular risk or diabetic and hypertensive retinopathy. These diseases affect retinal vessels so that an abnormal calibre of veins or arteries could indicate the presence of some of them. So, before analysing vessel calibres, it is interesting to distinguish between vein and artery. This paper is focused on studying the appearance of the retinal vascular network in different color spaces (RGB and HSV) to extract the most discriminant vessel features and classify the retinal vascular network as venous or arterial. The method for vessel classification has been evaluated on a public image database which facilitates further comparison with other state-of-the-art algorithms. The classification results are promising: 0.861 and 0.862 of sensitivity for vein and artery discrimination, respectively, which improve previous results of the literature. Once the vascular network has been classified, it would be possible to obtain different measures as the arterio-venous ratio (AVR), an essential parameter in the diagnosis of many diseases.