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.

Introduction: Sepsis is a leading cause of admission to non-cardiological intensive care units (ICUs) and the second leading cause of death among ICU patients. We present the first extensive dataset on the epidemiology of severe sepsis treated in ICUs in Spain. Methods: We conducted a prospective, observational, multicentre cohort study, carried out over two 3-month periods in 2002. Our aims were to determine the incidence of severe sepsis among adults in ICUs in a specific area in Spain, to determine the early (48 h) ICU and hospital mortality rates, as well as factors associated with the risk of death. Results: A total of 4,317 patients were admitted and 2,619 patients were eligible for the study; 311 (11.9%) of these presented at least 1 episode of severe sepsis, and 324 (12.4%) episodes of severe sepsis were recorded. The estimated accumulated incidence for the population was 25 cases of severe sepsis attended in ICUs per 100,000 inhabitants per year. The mean logistic organ dysfunction system (LODS) upon admission was 6.3; the mean sepsis-related organ failure assessment (SOFA) score on the first day was 9.6. Two or more organ failures were present at diagnosis in 78.1% of the patients. A microbiological diagnosis of the infection was reached in 209 episodes of sepsis (64.5%) and the most common clinical diagnosis was pneumonia (42.8%). A total of 169 patients (54.3%) died in hospital, 150 (48.2%) of these in the ICU. The mortality in the first 48 h was 14.8%. Factors associated with early death were haematological failure and liver failure at diagnosis, acquisition of the infection prior to ICU admission, and total LODS score on admission. Factors associated with death in the hospital were age, chronic alcohol abuse, increased McCabe score, higher LODS on admission, ΔSOFA 3-1 (defined as the difference in the total SOFA scores on day 3 and on day 1), and the difference of the area under the curve of the SOFA score throughout the first 15 days. Conclusions: We found a high incidence of severe sepsis attended in the ICU and high ICU and hospital mortality rates. The high prevalence of multiple organ failure at diagnosis and the high mortality in the first 48 h suggests delays in diagnosis, in initial resuscitation, and/or in initiating appropriate antibiotic treatment.

We introduce a new method for performing clustering with the aim of fitting clusters with different scatters and weights. It is designed by allowing to handle a proportion α of contaminating data to guarantee the robustness of the method. As a characteristic feature, restrictions on the ratio between the maximum and the minimum eigenvalues of the groups scatter matrices are introduced. This makes the problem to be well defined and guarantees the consistency of the sample solutions to the population ones. The method covers a wide range of clustering approaches depending on the strength of the chosen restrictions. Our proposal includes an algorithm for approximately solving the sample problem.