Catálogo de publicaciones - libros

Cellular neural networks (CNNs) have been successfully applied to image segmentation problem. Nevertheless, the main difficulty remains in the process of creating appropriate templates to solve a segmentation problem. In this paper we present machine learning approach to obtain completely stable CNN templates and compare the obtained results to unconstrained machine learning approach. Despite introduced constraints of templates stability the results are comparable to unobstructed ones.

A novel algorithm for the segmentation of 3D ultrasound images of ovary is presented in this paper. The algorithm is based on continuous wavelet transform (CWT) and consists of two consecutive steps. In the first step, the centers of follicles are determined by tracing the local maxima from higher to lower scale in the wavelet transform of input images. The center of follicle appears as local maximum near value 0 when the size of the follicle corresponds to the scale of CWT. In the second step, the shape of the follicle is outlined. This is done by casting the rays in different directions from the center of the follicle in order to find its border. The position of border is connected with the wavelet scale and the position of the first local minimum on each ray. The method was tested on a small set of real 3D ultrasound images. The results were evaluated visually, since we do not have manually annotated images.

Ultrasound imaging has been used for decades for medical and industrial imaging. Ultrasound in the range of 1-10 MHz has also been used for evaluating tissue properties characterization for many years. Recently, use of low frequency (audio range) vibration for medical diagnosis and evaluation of tissue properties has attracted increased attention. It has been shown that such vibration can reveal important information about tissue mechanical properties that are related to tissue pathology. We use the radiation force of ultrasound to vibrate tissue at low (kHz) frequency range, and record the resulting acoustic response to produce images that are related to the stiffness of the tissue. This method is tested on human breast, liver, heart valve, and arteries. Results show that small microcalcifications can be detected in human breast, calcium buildups can be seen in arteries, and mass lesions can be detected in liver tissues. In these tests, the vibration frequency ranged from 5 to 50 kHz. Another application of the radiation force method is studying solid structures through modal analysis.

Alcoholism is a disease that affects some part of brain that control emotion, decisions, and behavior. Sometimes, people experience situation that have to drink alcohol in their social life. Alcoholic needs cognitive behavior therapy to develop restraint on alcohol craving. Alcohol craving could be triggered when exposure to object, environment, or social pressure situation which is related with alcohol. But cognitive behavior therapy have defect in which does not provide social pressure situation properly. Virtual reality (VR) is humancomputer interface that computer expressed an immersive and interactive three-dimensional virtual environments like real space in world. In this study, we developed alcohol craving induction system using virtual reality to provide social situations in which avatar asks to drink together. Nine males and one female (age from 21 to 27 years) who do not have any history of alcohol related disease were recruited for this experiment. In the results, in situation without social pressure, more alcohol craving was induced in situation with alcohol than that of a situation without alcohol. That means our alcohol craving induction system shows same result as conventional study shows

Every tenth patient in US and European hospitals suffers from preventable harm and adverse effects related to his or her care. As adverse events also carry a high financial cost, patient safety remains a major global priority. Often forgotten in discussions on the necessary actions to improve patient safety, clinical engineering is one of the major pillars for safe health care. Realizing the huge potential of contributing to the world-wide efforts to provide safer care, the clinical engineering community has accepted the challenge to take a lead in providing a safer environment for patients.

MIDS, Medical Information Data Systems is proposed as a term for systems consisting of medical devices and IT-systems. MIDS are used for collection of physiological data from patients and transferring this data through a computer network to serves and databases. The project showed that the manufacturers of IT-systems for health care and the users of them do not take their full responsibility for the development and implementation of the information safety and functionality. For example there is no clear routines how to secure the accuracy of the information that is transferred between different IT-systems. It is also a problem that the borderline between medical devices and IT-systems is unclear, which makes it difficult to decide what directives or legislation should be applied. This makes it also unclear who should support the systems and the project proposes guidelines to improve the situation. The project also showed that there is need for continuing education of the staff handling MIDS.

Clinical alarms warn caregivers of immediate or potential adverse patient conditions. Alarms must be accurate, intuitive, and provide alerts which are readily interpreted and acted on by clinicians appropriately alarms and their shortcomings have been the topic of numerous studies and analysis. The (JCAHO) established a National Patient Safety (NPS) goal in 2002 to improve the effectiveness of clinical alarms. Despite the technological and healthcare improvements related to efforts to meet the NPS goal, adverse patient events continue to occur related to alarm system design and performance, care management and the complexity of the patient care environment. In 2004, the American College of Clinical Engineering Healthcare Technology Foundation started an initiative to improve clinical alarms. The HTF task force reviews the literature related to clinical alarm factors and analyzes adverse event databases. Forums, meetings and a survey of 1,327 clinicians, engineers, technical staff and managers provided feedback regarding alarm issues. Of particular value is the response from nursing who represented the majority of the respondents.

Clinical Engineering within Ireland has developed significantly in recent years. This Engineering discipline has proven an essential component of the modern healthcare environment. Nationally, Clinical Engineers participate as key members within multidisciplinary teams of every Clinical specialty. The Clinical Engineering membership has developed to include participants from the areas of Healthcare institutions, community medicine, academia and the medical device industry. A national voluntary registration scheme is now established and will further contribute to the professional development of Clinical Engineering.

In a medical center for blood transfusions, the blood haversacks are prepared and identified by a bar code label which identifies, for type and destination, the blood material according to the required standards. The traditional information systems use rigorous methodologies to verify and to watch the haversacks until they are delivered to the nurses. Nevertheless, at this stage, the tracing of the blood material is no more rigorous with particular regard to the mode and timing to give it to the generic patient. This is because we have not automatic systems to verify modes and timing for administering to the patient. This paper describes an automatic system for tracking the delivery process from the transfusion center to the patient transfusion. The proposed tracking system is based on RFID tags in order to offer a basic subset of functionalities also in absence of network collection.

Emerging countries developing their health care systems with support and donations from the industrialized countries need also support to develop the know-how for management of the equipment they get. The lack of knowledge and competence can be over bridged by well-planned education and training programs based on established programs and routines from the supporting countries where clinical engineering is an established profession. The education and training must have both short-term and long-term goals. It is essential that the country get a good base to develop own educational and managerial systems for health care support. The Albanian project shows an example how this can be realized.