Xosé López

Computer-Aided Lung Nodule Detection in Chest Radiography

Computer-aided diagnoses programs are developed for alerting the radiologist by indicating potential sites of lesions. One of the important tasks in the development of a computational system for detecting lung nodules is to diminish the number of false positives keeping on high sensitivities. In this work we describe a system for automatic lung nodule detection. The detection is carried out in several stages. First, a knowledge-based segmentation process delimits the lung boundaries. Then, a progressive thresholding of an image in which the conspicuity of nodules has been enhanced by means of filter matching and a set of growth and circularity tests fix the areas suspicious of being nodules into region previously labelled as lungs. Finally, these suspicious regions are confirmed as nodules in a new feature (curvature) space, which gives us an important help in the task of distinguishing true and false nodules from previously extracted suspicious regions. Preliminary results are very promising, achieving high sensitivities with a little ratio of false positives.

Application of a Multilayer Discrete-Time CNN to Deformable Models

In this work Cellular Neural Networks are applied to image analysis techniques as a deformable models. To this end the problem is considered based on a discrete-time CNN with cyclic templates and time-variant external inputs. The appropriateness for a VLSI implementation and massively parallel computing of CNNs will permit a considerable improvement in processing speed with respect to the clasical active contours approaches.

CT Image Segmentation by Self-Organizing Learning

In this paper we approach the segmentation of tibia CT images using a self-organizing feature map. This type of Artificial Neural Network carries out a competitive learning process which permits the discrimination of different structures found in the images with sensitivity to changes in the distribution and value of the gray levels of the pixels. The results obtained show that this technique is adequate for the segmentation of images with complex structures and a low signal/noise ratio.

A Review of Mobile Journalism in Spain

Studies on communication in mobility have been taking importance as the access to contents has been consolidated among users in all the strata and social and cultural levels. In the last ten years, acceleration in the technological innovations in mobile telephony was produced. This has had its corollary in the corresponding interest in investigating its relationship with the diffusion of news contents and, in general terms, with social communication. This communication explains the impact of mobile telephony on journalism. We reveal the aspect of this device as a news medium and present the context of the vertiginous social expansion that digital mobile technologies have nowadays. Our objective is to disclose this new communicational phenomenon, where the media are usually making their incursions very slowly.

A Markov Random Field Model for Bony Tissue Classification

3D biomedical images are a valuable source of information for clinical diagnosis. In areas such as bone remodeling, fracture prediction and prosthesis design, the external geometry of the bones needs to be precisely defined and injuries identified. A system that automatically interprets and presents a 3D reconstruction of the bone can be very useful, although this task cannot be carried out without specific knowledge of the domain. This knowledge may be represented by a set of constraints over properties and relationships between regions. In this work we present a Markov random field model for identification of injuries in the proximal tibia.