Clara I. Sánchez

Retinopathy Online Challenge: Automatic Detection of Microaneurysms in Digital Color Fundus Photographs

The detection of microaneurysms in digital color fundus photographs is a critical first step in automated screening for diabetic retinopathy (DR), a common complication of diabetes. To accomplish this detection numerous methods have been published in the past but none of these was compared with each other on the same data. In this work we present the results of the first international microaneurysm detection competition, organized in the context of the Retinopathy Online Challenge (ROC), a multiyear online competition for various aspects of DR detection. For this competition, we compare the results of five different methods, produced by five different teams of researchers on the same set of data. The evaluation was performed in a uniform manner using an algorithm presented in this work. The set of data used for the competition consisted of 50 training images with available reference standard and 50 test images where the reference standard was withheld by the organizers (M. Niemeijer, B. van Ginneken, and M. D. AbrA¿moff). The results obtained on the test data was submitted through a website after which standardized evaluation software was used to determine the performance of each of the methods. A human expert detected microaneurysms in the test set to allow comparison with the performance of the automatic methods. The overall results show that microaneurysm detection is a challenging task for both the automatic methods as well as the human expert. There is room for improvement as the best performing system does not reach the performance of the human expert. The data associated with the ROC microaneurysm detection competition will remain publicly available and the website will continue accepting submissions.

Analysis of regularity in the EEG background activity of Alzheimer's disease patients with Approximate entropy

OBJECTIVEnThe aim of this study was to analyse the regularity of the EEG background activity of Alzheimers disease (AD) patients to test the hypothesis that the irregularity of the AD patients EEG is lower than that of age-matched controls.nnnMETHODSnWe recorded the EEG from 19 scalp electrodes in 10 AD patients and 8 age-matched controls and estimated the Approximate Entropy (ApEn). ApEn is a non-linear statistic that can be used to quantify the irregularity of a time series. Larger values correspond to more complexity or irregularity. A spectral analysis was also performed.nnnRESULTSnApEn was significantly lower in the AD patients at electrodes P3 and P4 (P < 0.01), indicating a decrease of irregularity. We obtained 70% sensitivity and 100% specificity at P3, and 80% sensitivity and 75% specificity at P4. Results seemed to be complementary to spectral analysis.nnnCONCLUSIONSnThe decreased irregularity found in the EEG of AD patients in the parietal region leads us to think that EEG analysis with ApEn could be a useful tool to increase our insight into brain dysfunction in AD. However, caution should be applied due to the small sample size.nnnSIGNIFICANCEnThis article represents a first step in demonstrating the feasibility of ApEn for recognition of EEG changes in AD.

Retinal image analysis based on mixture models to detect hard exudates.

Diabetic Retinopathy is one of the leading causes of blindness in developed countries. Hard exudates have been found to be one of the most prevalent earliest clinical signs of retinopathy. Thus, automatic detection of hard exudates from retinal images is clinically significant. In this study, an automatic method to detect hard exudates is proposed. The algorithm is based on mixture models to dynamically threshold the images in order to separate exudates from background. A postprocessing technique, based on edge detection, is applied to distinguish hard exudates from cotton wool spots and other artefacts. We prospectively assessed the algorithm performance using a database of 80 retinal images with variable colour, brightness, and quality. The algorithm obtained a sensitivity of 90.2% and a positive predictive value of 96.8% using a lesion-based criterion. The image-based classification accuracy is also evaluated obtaining a sensitivity of 100% and a specificity of 90%.

Neural network based detection of hard exudates in retinal images

Diabetic retinopathy (DR) is an important cause of visual impairment in developed countries. Automatic recognition of DR lesions in fundus images can contribute to the diagnosis of the disease. The aim of this study is to automatically detect one of these lesions, hard exudates (EXs), in order to help ophthalmologists in the diagnosis and follow-up of the disease. We propose an algorithm which includes a neural network (NN) classifier for this task. Three NN classifiers were investigated: multilayer perceptron (MLP), radial basis function (RBF) and support vector machine (SVM). Our database was composed of 117 images with variable colour, brightness, and quality. 50 of them (from DR patients) were used to train the NN classifiers and 67 (40 from DR patients and 27 from healthy retinas) to test the method. Using a lesion-based criterion, we achieved a mean sensitivity (SE(l)) of 88.14% and a mean positive predictive value (PPV(l)) of 80.72% for MLP. With RBF we obtained SE(l)=88.49% and PPV(l)=77.41%, while we reached SE(l)=87.61% and PPV(l)=83.51% using SVM. With an image-based criterion, a mean sensitivity (SE(i)) of 100%, a mean specificity (SP(i)) of 92.59% and a mean accuracy (AC(i)) of 97.01% were obtained with MLP. Using RBF we achieved SE(i)=100%, SP(i)=81.48% and AC(i)=92.54%. With SVM the image-based results were SE(i)=100%, SP(i)=77.78% and AC(i)=91.04%.

Retinal image analysis to detect and quantify lesions associated with diabetic retinopathy

An automatic method to detect hard exudates, a lesion associated with diabetic retinopathy, is proposed. The algorithm found on their color, using a statistical classification, and their sharp edges, applying an edge detector, to localize them. A sensitivity of 79.62% with a mean number of 3 false positives per image is obtained in a database of 20 retinal image with variable color, brightness and quality. In that way, we evaluate the robustness of the method in order to make adequate to a clinical environment. Further efforts will be done to improve its performance.

Variability, regularity, and complexity of time series generated by schizophrenic patients and control subjects

We analyzed time series generated by 20 schizophrenic patients and 20 sex- and age-matched control subjects using three nonlinear methods of time series analysis as test statistics: central tendency measure (CTM) from the scatter plots of first differences of data, approximate entropy (ApEn), and Lempel-Ziv (LZ) complexity. We divided our data into a training set (10 patients and 10 control subjects) and a test set (10 patients and 10 control subjects). The training set was used for algorithm development and optimum threshold selection. Each method was assessed prospectively using the test dataset. We obtained 80% sensitivity and 90% specificity with LZ complexity, 90% sensitivity, and 60% specificity with ApEn, and 70% sensitivity and 70% specificity with CTM. Our results indicate that there exist differences in the ability to generate random time series between schizophrenic subjects and controls, as estimated by the CTM, ApEn, and LZ. This finding agrees with most previous results showing that schizophrenic patients are characterized by less complex neurobehavioral and neuropsychologic measurements.

Regional Analysis of Spontaneous MEG Rhythms in Patients with Alzheimer's Disease Using Spectral Entropies

Alzheimer’s disease (AD) is the most common form of dementia. Ageing is the greatest known risk factor for this disorder. Therefore, the prevalence of AD is expected to increase in western countries due to the rise in life expectancy. Nowadays, a low diagnosis accuracy is reached, but an early and accurate identification of AD should be attempted. In this sense, only a few studies have focused on the magnetoencephalographic (MEG) AD patterns. This work represents a new effort to explore the ability of three entropies from information theory to discriminate between spontaneous MEG rhythms from 20 AD patients and 21 controls. The Shannon (SSE), Tsallis (TSE), and Rényi (RSE) spectral entropies were calculated from the time-frequency distribution of the power spectral density (PSD). The entropies provided statistically significant lower values for AD patients than for controls in all brain regions (pxa0<xa00.0005). This fact suggests a significant loss of irregularity in AD patients’ MEG activity. Maximal accuracy of 87.8% was achieved by both the TSE and RSE (90.0%, sensitivity; 85.7%, specificity). The statistically significant results obtained by both the extensive (SSE and RSE) and non-extensive (TSE) spectral entropies suggest that AD could disturb long and short-range interactions causing an abnormal brain function.

Mixture Model-based Clustering and Logistic Regression for Automatic Detection of Microaneurysms in Retinal Images

Diabetic Retinopathy is one of the leading causes of blindness and vision defects in developed countries. An early detection and diagnosis is crucial to avoid visual complication. Microaneurysms are the first ocular signs of the presence of this ocular disease. Their detection is of paramount importance for the development of a computer-aided diagnosis technique which permits a prompt diagnosis of the disease. However, the detection of microaneurysms in retinal images is a difficult task due to the wide variability that these images usually present in screening programs. We propose a statistical approach based on mixture model-based clustering and logistic regression which is robust to the changes in the appearance of retinal fundus images. The method is evaluated on the public database proposed by the Retinal Online Challenge in order to obtain an objective performance measure and to allow a comparative study with other proposed algorithms.

Detection of Hard Exudates in Retinal Images Using a Radial Basis Function Classifier

Diabetic retinopathy (DR) is one of the most important causes of visual impairment. Automatic recognition of DR lesions, like hard exudates (EXs), in retinal images can contribute to the diagnosis and screening of the disease. The aim of this study was to automatically detect these lesions in fundus images. To achieve this goal, each image was normalized and the candidate EX regions were segmented by a combination of global and adaptive thresholding. Then, a group of features was extracted from image regions and the subset which best discriminated between EXs and retinal background was selected by means of logistic regression (LR). This optimal subset was subsequently used as input to a radial basis function (RBF) neural network. To improve the performance of the proposed algorithm, some noisy regions were eliminated by an innovative postprocessing of the image. The main novelty of the paper is the use of LR in conjunction with RBF and the proposed postprocessing technique. Our database was composed of 117 images with variable color, brightness and quality. The database was divided into a training set of 50 images (from DR patients) and a test set of 67 images (40 from DR patients and 27 from healthy retinas). Using a lesion-based criterion (pixel resolution), a mean sensitivity of 92.1% and a mean positive predictive value of 86.4% were obtained. With an image-based criterion, a mean sensitivity of 100%, mean specificity of 70.4% and mean accuracy of 88.1% were achieved. These results suggest that the proposed method could be a diagnostic aid for ophthalmologists in the screening for DR.

Feature Extraction and Selection for the Automatic Detection of Hard Exudates in Retinal Images

Diabetic Retinopathy (DR) is a common cause of visual impairment among people of working age in industrialized countries. Automatic recognition of DR lesions, like hard exudates (HEs), in fundus images can contribute to the diagnosis and screening of this disease. In this study, we extracted a set of features from image regions and selected the subset which best discriminates between HEs and the retinal background. The selected features were then used as inputs to a multilayer perceptron (MLP) classifier to obtain a final segmentation of HEs in the image. Our database was composed of 100 images with variable color, brightness, and quality. 50 of them were used to train the MLP classifier and the remaining 50 to assess the performance of the method. Using a lesion- based criterion, we achieved a mean sensitivity of 84.4% and a mean positive predictive value of 62.7%. With an image-based criterion, our approach reached a 100% mean sensitivity, 84.0% mean specificity and 92.0% mean accuracy.