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.

a b s t r a c tThe 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.

Since the discovery of the role of the APOBEC enzymes in human cancers, the mechanisms of this type of mutagenesis remain little understood. Theoretically, targeting of single-stranded DNA by the APOBEC enzymes could occur during cellular processes leading to the unwinding of DNA double-stranded structure. Some evidence points to the importance of replication in the APOBEC mutagenesis, while the role of transcription is still underexplored. Here, we analyzed gene expression and whole genome sequencing data from five types of human cancers with substantial APOBEC activity to estimate the involvement of transcription in the APOBEC mutagenesis and compare its impact with that of replication. Using the TCN motif as the mutation signature of the APOBEC enzymes, we observed a correlation of active APOBEC mutagenesis with gene expression, confirmed the increase of APOBEC-induced mutations in early-replicating regions and estimated the relative impact of transcription and replication on the APOBEC mutagenesis. We also found that the known effect of higher density of APOBEC-induced mutations on the lagging strand was highest in middle-replicating regions and observed higher APOBEC mutation density on the sense strand, the latter bias positively correlated with the gene expression level.

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.