Image segmentation operation has a great importance in most medical imaging applications, by extracting anatomical structures from medical images. There are many image segmentation techniques available in the literature, each of them having advantages and disadvantages. The extraction of bone contours from X-ray images has received a considerable amount of attention in the literature recently, because they represent a vital step in the computer analysis of this kind of images. The aim of X-ray segmentation is to subdivide the image in various portions, so that it can help doctors during the study of the bone structure, for the detection of fractures in bones, or for planning the treatment before surgery. The goal of this paper is to review the most important image segmentation methods starting from a data base composed by real X-ray images. We will discuss the principle and the mathematical model for each method, highlighting the strengths and weaknesses

The segmentation process represents a first step necessary for any automatic method of extracting information from an image. In the case of X-ray images, through segmentation we can differentiate the bone tissue from the rest of the image. There are nowadays several segmentation techniques, but in general, they all require the human intervention in the segmentation process. Consequently, this article proposes a new segmentation method for the X-ray images using a Convolutional Neural Network (CNN). In present, the convolutional networks are the best techniques for image segmentation. This fact is demonstrated by their wide usage in all the fields, including the medical one. As the X-ray images have large dimensions, for reducing the training time, the method proposed by the present article selects only certain areas (maximum interest areas) from the entire image. The neural network is used as pixel classifier thus causing the label of each pixel (bone or none-bone) from a raw pixel values in a square area. We will also present the method through which the network final configuration was chosen and we will make a comparative analysis with other 3 CNN configurations. The network chosen by us obtained the best results for all the evaluation metrics used, i.e. warping error, rand error and pixel error

De novo motif discovery is a difficult computational task. Historically, dedicated algorithms always reported a high percentage of false positives. Their performance did not improve considerably even after they adapted to handle large amounts of chromatin immunoprecipitation sequencing (ChIP-Seq) data. Several studies have advocated aggregating complementary algorithms, combining their predictions to increase the accuracy of the results. This led to the development of ensemble methods. To form a better view on modern ensembles, we review all compound tools designed for ChIP-Seq. After a brief introduction to basic algorithms and early ensembles, we describe the most recent tools. We highlight their limitations and strengths by presenting their architecture, the input options and their output. To provide guidance for next-generation sequencing practitioners, we observe the differences and similarities between them. Last but not least, we identify and recommend several features to be implemented by any novel ensemble algorithm.

No abstract

No abstract