Automatic segmentation of digital images applied in cardiac medical images

The digital image processing has been applied in several areas, especially where it is necessary use tools for feature extraction and to get patterns of the studied images. In an initial stage, the segmentation is used to separate the image in parts that represents a interest object, that may be used in a specific study. There are several methods that intends to perform such task, but is difficult to find a method that can easily adapt to different type of images, that often are very complex or specific. To resolve this problem, this project aims to presents a adaptable segmentation method, that can be applied to different type of images, providing an better segmentation. The proposed method is based in a model of automatic multilevel thresholding and considers techniques of group histogram quantization, analysis of the histogram slope percentage and calculation of maximum entropy to define the threshold. The technique was applied to segment the cell core and potential rejection of tissue in myocardial images of biopsies from cardiac transplant. The results are significant in comparison with those provided by one of the best known segmentation methods available in the literature. © 2010 IEEE.

Tridimensional modeling of the cardiac wall

The advance in the graphic computer's techniques and computer's capacity of processing made possible applications like the human anatomic structures modeling, in order to investigate diseases, surgical planning or even provide images for training of Computer Aided Diagnosis (CAD). On this context, this work exhibits an anatomical model of cardiac structures represented in a tridimensional environment. The model was represented with geometrical elements and has anatomical details, as the different tunics that compose the cardiac wall and measures that preserves the characteristics found on real structures. The validation of the anatomical model was made through quantitative comparations with real structures measures, available on specialized literature. The results obtained, evaluated by two specialists, are compatible with real anatomies, respecting the anatomical particularities. This degree of representation will allow the verification of the influence of radiological parameters, morphometric peculiarities and stage of the cardiac diseases on the quality of the images, as well as on the performance of the CAD. © 2010 IEEE.

Assessment of structural cardiac abnormalities and diastolic function in women with gestational diabetes mellitus

Background: The main manifestation of hyperglycaemia during pregnancy is gestational diabetes mellitus. It can herald diabetes mellitus type 2 and its deleterious long-term effects, such as hypertension and cardiovascular disease. The aim of this study was to assess diastolic function in women with gestational diabetes mellitus, one of the first signs of future cardiovascular disease.Methods: A total of 21 women with gestational diabetes mellitus and 23 healthy pregnant women (control group) between 34 and 37weeks of gestation underwent echocardiographic assessment. The diagnosis of gestational diabetes mellitus was made in agreement with the American Diabetes Association criteria. Echocardiographic images obtained were analysed according to the criteria of the American Society of Echocardiography. Data were analysed using Pearson correlation coefficient, analysis of variance and Student's t-test.Results: Women with gestational diabetes mellitus had higher posterior wall and interventricular septum thickness, increased left ventricular mass and left ventricular mass index, lower early diastolic annular velocity and early diastolic annular velocity/late diastolic annular velocity ratio. There was a positive correlation between left ventricular mass index and fasting glucose and pregnancy body mass index.Conclusion: Patients with gestational diabetes mellitus seem to have a different diastolic profile as well as a mildly dysfunctional pattern on echocardiogram, which may show a need for greater glycaemic control.