Alfonso Castro

Development of a system for access to and exploitation of medical images

This article describes a system for the acquisition, storage and secure remote access to information generated by a hospitals devices for image diagnosis. The system allows the experts of a medical centre to recover and manage information. Our solution also makes it possible to obtain more elaborate results, thanks to the implemented functionalities of image analysis (edge detectors, clustering algorithms, etc.) and the storage of historical diagnosis results that give a certain experience to the application.

Intelligent agents technology applied to tasks control in ICU telesupervision

This work presents a telemedicine system for Intensive Care Units (ICUs). The system provides the real time acquisition and analysis of physiological data of patients, the graphical visualization of these data and their transmission to a central system charged with the collection and control of all the information concerning the patient, including knowledge based systems (KBS) for medical reasoning. For the distribution and control of various processing tasks, requested by the medical KBS or directly by physicians, we have developed a module based on intelligent agents technology that controls and distributes the tasks according to their priority and to the availability of resources between the interconnected computers.

Development of an analysis system of the X-rays of bones [for prosthesis placement]

This article presents the current development state of a system for the analysis of radiological images. Its purpose is to provide the clinicians with information that helps him to take decisions on the placing of prostheses: type of prosthesis, implantation point, etc. At present we are developing the segmentation module that is based on tests with different algorithms and used for the analysis of medical images, focusing on different elements: edge detectors and adaptive clustering algorithms.

Study on various defuzzification methods for fuzzy clustering algorithms to improve ROIs detection in lung CTs

The detection of pulmonary nodules is one of the most studied areas and challenging task in the field of medical image analysis, due the current relevance of the lung carcinoma. The difficulty and complexity of this task has led to the development of CAD systems for the automated detection of lung nodules in CT scans, which provides valuable assistance for radiologists and could improve the detection rate. A common phase of these systems is the detection of regions of interest (ROIs) that could be marked as nodules, in order to reduce the searching space problem. In this paper, we evaluate and compare the combination of various approaches of supervised vector machines (SVMs) with different kinds of fuzzy clustering algorithms, so as to improve the detection and segmentation of ROIs that could represent lung nodules in high resolution CT scans. These images are provided by the LIDC database (Lung Internet Database Consortium).

An improved algorithm for the automatic isolation of lungs in CT studies

The complexity of detecting pulmonary nodules has led to the development of Computer Aided Systems (CAD) that automate and reduce the cost of this task. The first phase of such systems usually consists in preprocessing the Computer Tomography (CT) scans, with the aim of segmenting the lungs and eliminating the elements that might interfere with the process. This paper presents an automatic method for the segmentation of lungs into three-dimensional pulmonary high resolution CT images. The proposed method has three main steps, that combine both 3D and 2D techniques. Firstly the trachea and the main airways are removed from the volume; then the lung region is segmented by grey-level thresholding, separating the right and left lungs if a junction is visible in the image, and the lung contour is smoothed; finally, a ”region growing” is applied using two seeds from each identified lung, avoiding as such the incorporation of other elements that do not belong to the lungs.

An analysis of different clustering algorithms for ROI detection in high resolutions CT lung images

The detection of pulmonary nodules in radiological or CT images has been widely investigated in the field of medical image analysis due to the high degree of difficulty it presents. The traditional approach is to develop a multistage CAD system that will reveal the presence or absence of nodules to the radiologist. One of the stages within this system is the detection of ROIs (regions of interest) that may possibly be nodules, in order to reduce the scope of the problem. In this article we evaluate clustering algorithms that use different classification strategies for this purpose. In order to evaluate these algorithms we used high resolution CT images from the LIDC (Lung Internet Database Consortium) database.

The performance of various edge detector algorithms in the analysis of total hip replacement x-rays

Most traumatology services use radiological images to control the state and possible displacements of total hip replacement implants. Prostheses are typically and traditionally detected by means of edge detectors, a widely used technique in medical image analysis. This article analyses how different edge detectors identify the prosthesis in X-Rays by measuring the performance of each detection algorithm; it also determines the clinical usefulness of the algorithms with the help of clinical experts.

3D visualization module in a telemedicine project

Advances in telemedicine technology have led to intelligent monitoring systems that are capable of helping medical experts in their decision-making process. These systems imply the introduction of a bed-side computer that supervises the patient and collects, stores and visualizes all the information provided by the medical devices in an accessible way. This paper describes the telemedicine system that is currently being developed by our research team for the intelligent telemonitoring of patients at an intensive care unit (ICU). Concretely, the paper focuses on our 3D visualization module, which shows a virtual model of the patient and allows the clinical staff to visualize the patients evolution in a rapid and clear manner.

Fuzzy Clustering Applied to ROI Detection in Helical Thoracic CT Scans with a New Proposal and Variants

The detection of pulmonary nodules is one of the most studied problems in the field of medical image analysis due to the great difficulty in the early detection of such nodules and their social impact. The traditional approach involves the development of a multistage CAD system capable of informing the radiologist of the presence or absence of nodules. One stage in such systems is the detection of ROI (regions of interest) that may be nodules in order to reduce the space of the problem. This paper evaluates fuzzy clustering algorithms that employ different classification strategies to achieve this goal. After characterising these algorithms, the authors propose a new algorithm and different variations to improve the results obtained initially. Finally it is shown as the most recent developments in fuzzy clustering are able to detect regions that may be nodules in CT studies. The algorithms were evaluated using helical thoracic CT scans obtained from the database of the LIDC (Lung Image Database Consortium).

A novel visualizer of medical images by integrating an extensible plugin framework

The use of medical imaging for the diagnosis and, to a lesser extent, the prognosis and treatment of disease, is a common practice in modern medicine. Consequently, the need has arisen to develop applications that combine the ability to visualize digital medical images with the features required by clinical personnel in order to manage them. A number of medical image viewers are currently available, but nearly all of them are oriented towards visualizing and managing a single study of a patient, which limits the analysis of the expert. This paper introduces a novel application that contains the basic functionality required for common medical image analysis and which may be extended by a plug-in system with new features that could be demanded in the future. The application also makes it possible to visualize and analyze several studies at the same time, completely independently, increasing the accuracy of the analysis and facilitating the work of experts.