Region-growing segmentation algorithms are useful for remote sensing image segmentation. These algorithms need the user to supply control parameters, which control the quality of the resulting segmentation. This letter proposes an objective function for selecting suitable parameters for region-growing algorithms to ensure best quality results. It considers that a segmentation has two desirable properties: each of the resulting segments should be internally homogeneous and should be distinguishable from its neighbourhood. The measure combines a spatial autocorrelation indicator that detects separability between regions and a variance indicator that expresses the overall homogeneity of the regions.

BackgroundThe prevalence of type 2 diabetes mellitus is increasing substantially worldwide, leading to serious economic effects, complications and deaths. This study evaluated the effectiveness of an empowerment program providing support for psychosocial, behavioral, and clinical aspects of diabetes to help Brazilian users of public health services obtain metabolic control of this condition.MethodsIn this cluster randomized trial, participants aged 30–80 diagnosed with type 2 diabetes were recruited from ten Brazilian public health units in 2014 and 2015. Five units were randomly assigned to receive the empowerment program based on a behavior change protocol, and five continued to receive only conventional treatment. The primary outcome was the biochemical and anthropometric parameters, and the secondary outcomes were self-care, attitude, knowledge and empowerment related to diabetes. The effect of the experiment was defined as the percentage variation between the values at the initial and final periods. To evaluate this effect and to compare it in the two groups, tests were used for paired and independent samples, respectively.ResultsThere were 238 participants: 127 and 111 in the intervention and control group, respectively. For glycated hemoglobin, the mean effect in the control and intervention groups was 3.93 and −5.13, respectively (p < 0.001). Levels of glycated hemoglobin and other metabolic indicators, as well as the most part of the secondary outcomes showed a significant difference in the experimental group compared to the control group.ConclusionsThe empowerment program improved metabolic control of type 2 diabetes in Brazilian users.Trial registration NCT02132338 - April 22, 2014.

BackgroundIn Brazil, lethality from visceral leishmaniasis (VL) is high and few studies have addressed prognostic factors. This historical cohort study was designed to investigate the prognostic factors for death from VL in Belo Horizonte (Brazil).MethodologyThe analysis was based on data of the Reportable Disease Information System-SINAN (Brazilian Ministry of Health) relating to the clinical manifestations of the disease. During the study period (2002–2009), the SINAN changed platform from a Windows to a Net-version that differed with respect to some of the parameters collected. Multivariate logistic regression models were performed to identify variables associated with death from VL, and these were included in prognostic score.Principal FindingsModel 1 (period 2002–2009; 111 deaths from VL and 777 cured patients) included the variables present in both SINAN versions, whereas Model 2 (period 2007–2009; 49 deaths from VL and 327 cured patients) included variables common to both SINAN versions plus the additional variables included in the Net version. In Model 1, the variables significantly associated with a greater risk of death from VL were weakness (OR 2.9; 95%CI 1.3–6.4), Leishmania-HIV co-infection (OR 2.4; 95%CI 1.2–4.8) and age ≥60 years (OR 2.5; 95%CI 1.5–4.3). In Model 2, the variables were bleeding (OR 3.5; 95%CI 1.2–10.3), other associated infections (OR 3.2; 95%CI 1.3–7.8), jaundice (OR 10.1; 95%CI 3.7–27.2) and age ≥60 years (OR 3.1; 95%CI 1.4–7.1). The prognosis score was developed using the variables associated with death from VL of the latest version of the SINAN (Model 2). The predictive performance of which was evaluated by sensitivity (71.4%), specificity (73.7%), positive and negative predictive values (28.9% and 94.5%) and area under the receiver operating characteristic curve (75.6%).ConclusionsKnowledge regarding the factors associated with death from VL may improve clinical management of patients and contribute to lower mortality.

Objective: To analyze the association between the time of disease and the onset of diabetes mellitus complications and to describe the characteristics of the diabetics' population of a mid-sized city located in the Midwest of the state of Minas Gerais. Methods: Cross-sectional study conducted with 1320 patients with diabetes mellitus. The data were obtained from the registration system of Hypertensive and diabetic patients and the following variables were evaluated: sociodemographic characteristics, duration of disease and diabetes complications. Results: Among patients who have the diagnosis of the disease for more than 10 years, the percentage of those that present complications 156 (32.2%) is higher than among those with the diagnosis of the disease for less than 10 years 45 (12.1%). Conclusion:The results showed that the onset of diabetes-related complications might be associated with the duration of disease. ResumoObjetivo: Analisar a associação entre o tempo da doença e o aparecimento de complicações do diabetes mellitus e descrever as características da população de diabéticos de um município de médio porte do Centro Oeste mineiro. Métodos: Estudo transversal realizado com 1320 usuários com diabetes mellitus. Os dados foram obtidos do sistema de cadastramento de Hipertensos e Diabéticos e foram avaliadas as variáveis: características sociodemográficas, duração da doença e complicações do diabetes. Resultados: Entre os usuários que possuem o diagnóstico da doença há mais de 10 anos, o percentual daqueles que apresentam complicações 156 (32,2%) é maior do que entre os que possuem o diagnóstico da doença há menos de 10 anos 45 (12,1%). Conclusão: Os resultados apontaram que a presença de complicações relacionadas ao diabetes pôde ser associada ao tempo de duração da doença.

In this paper, we present spatial analysis of the association between all incidents cases of human Visceral Leishmaniasis and seropositive dogs, from 1994 to 1997