Search

Correct diagnostics of autoimmune disorders is important for a treatment planning as many of such diseases demonstrate similar symptoms. Owing to ANA HEp-2 medical test it is possible to distinguish among such autoimmune disease as lupus erythematosus, scleroderma and Sjogren’s syndrome. It is known that manual disease classification performing based on analysis of indirect immunofluorescent images obtained in the course of this test is error-prone. Here, we present an automatic method for classification of ANA HEp-2 images that performs separation of the individual cell on pre-segmented slide images and subsequent cell and slide image classification. The method uses morphological properties of the stained patterns located inside the cell nucleus for an individual cell classification and a voting scheme for a classification of the whole ANA HEp-2 slide image. [ABSTRACT FROM AUTHOR]

Abstract: The ANA HEp-2 medical test is a powerful tool in autoimmune disease diagnostics. The last step of this test, the interpretation of immunofluorescent images by trained experts, represents a potential source of errors and could theoretically be replaced by automated methods. Here we present a fully automatic method for recognition of types of immunofluorescent images produced by the ANA HEp-2 medical test. The proposed method makes use of the difference in number, size, shape and localization of cell regions that are targeted by the antinuclear antibodies – the humoral components of immune system that bind human antigens as a result of the immune system malfunction. The method extracts morphological properties of stained cell regions using a combination of thresholding-based and thresholding-less approaches and applies a conventional machine-learning algorithm for image classification. [Copyright &y& Elsevier]

The importance of 3D protein structure in proteolytic processing is well known. However, despite the plethora of existing methods for predicting proteolytic sites, only a few of them utilize the structural features of potential substrates as predictors. Moreover, to our knowledge, there is currently no method available for predicting the structural susceptibility of protein regions to proteolysis. We developed such a method using data from CutDB, a database that contains experimentally verified proteolytic events. For prediction, we utilized structural features that have been shown to influence proteolysis in earlier studies, such as solvent accessibility, secondary structure, and temperature factor. Additionally, we introduced new structural features, including length of protruded loops and flexibility of protein termini. To maximize the prediction quality of the method, we carefully curated the training set, selected an appropriate machine learning method, and sampled negative examples to determine the optimal positive-to-negative class size ratio. We demonstrated that combining our method with models of protease primary specificity can outperform existing bioinformatics methods for the prediction of proteolytic sites. We also discussed the possibility of utilizing this method for bioinformatics prediction of other post-translational modifications. [ABSTRACT FROM AUTHOR]

This paper presents the evaluation results of the methods submitted to Challenge US: Biometric Measurements from Fetal Ultrasound Images, a segmentation challenge held at the IEEE International Symposium on Biomedical Imaging 2012. The challenge was set to compare and evaluate current fetal ultrasound image segmentation methods. It consisted of automatically segmenting fetal anatomical structures to measure standard obstetric biometric parameters, from 2D fetal ultrasound images taken on fetuses at different gestational ages (21 weeks, 28 weeks, and 33 weeks) and with varying image quality to reflect data encountered in real clinical environments. Four independent sub-challenges were proposed, according to the objects of interest measured in clinical practice: abdomen, head, femur, and whole fetus. Five teams participated in the head sub-challenge and two teams in the femur sub-challenge, including one team who tackled both. Nobody attempted the abdomen and whole fetus sub-challenges. The challenge goals were two-fold and the participants were asked to submit the segmentation results as well as the measurements derived from the segmented objects. Extensive quantitative (region-based, distance-based, and Bland–Altman measurements) and qualitative evaluation was performed to compare the results from a representative selection of current methods submitted to the challenge. Several experts (three for the head sub-challenge and two for the femur sub-challenge), with different degrees of expertise, manually delineated the objects of interest to define the ground truth used within the evaluation framework. For the head sub-challenge, several groups produced results that could be potentially used in clinical settings, with comparable performance to manual delineations. The femur sub-challenge had inferior performance to the head sub-challenge due to the fact that it is a harder segmentation problem and that the techniques presented relied more on the femur's appearance. [ABSTRACT FROM AUTHOR]

Bioinformatics-based prediction of protease substrates can help to elucidate regulatory proteolytic pathways that control a broad range of biological processes such as apoptosis and blood coagulation. The majority of published predictive models are position weight matrices (PWM) reflecting specificity of proteases toward target sequence. These models are typically derived from experimental data on positions of hydrolyzed peptide bonds and show a reasonable predictive power. New emerging techniques that not only register the cleavage position but also measure catalytic efficiency of proteolysis are expected to improve the quality of predictions or at least substantially reduce the number of tested substrates required for confident predictions. The main goal of this study was to develop new prediction models based on such data and to estimate the performance of the constructed models. We used data on catalytic efficiency of proteolysis measured for eight major human matrix metalloproteinases to construct predictive models of protease specificity using a variety of regression analysis techniques. The obtained results suggest that efficiency-based (quantitative) models show a comparable performance with conventional PWM-based algorithms, while less training data are required. The derived list of candidate cleavage sites in human secreted proteins may serve as a starting point for experimental analysis. Unlabelled Image • Protease specificity models can be built from quantitative protease profiling data. • Regression methods is applicable for the building of such predictive models. • These models perform at least as well as traditional quantitative PWMs. • Significantly smaller number of peptide substrates are required for training data. [ABSTRACT FROM AUTHOR]