Classification and staging of chronic liver disease from multimodal data

Chronic liver disease (CLD) is most of the time an asymptomatic, progressive, and ultimately potentially fatal disease. In this study, an automatic hierarchical procedure to stage CLD using ultrasound images, laboratory tests, and clinical records are described. The first stage of the proposed method, called clinical based classifier (CBC), discriminates healthy from pathologic conditions. When nonhealthy conditions are detected, the method refines the results in three exclusive pathologies in a hierarchical basis: 1) chronic hepatitis; 2) compensated cirrhosis; and 3) decompensated cirrhosis. The features used as well as the classifiers (Bayes, Parzen, support vector machine, and k-nearest neighbor) are optimally selected for each stage. A large multimodal feature database was specifically built for this study containing 30 chronic hepatitis cases, 34 compensated cirrhosis cases, and 36 decompensated cirrhosis cases, all validated after histopathologic analysis by liver biopsy. The CBC classification scheme outperformed the nonhierachical one against all scheme, achieving an overall accuracy of 98.67% for the normal detector, 87.45% for the chronic hepatitis detector, and 95.71% for the cirrhosis detector.

Valores de referência de robustez óssea avaliados próximo ao nascimento por ultrassonografia quantitativa em recém-nascidos de termo e pré-termo

Objectivo: Estabelecer valores de referência da robustez óssea nos primeiros dias de vida, em recém-nascidos de termo e pré-termo adequados para a idade de gestação nascidos em Portugal. Métodos: Foi medida a velocidade do som (VdS) (m/s) por ultrassonografia quantitativa, numa amostra sistemática de recém-nascidos adequados para a idade de gestação, de termo e pré-termo, respectivamente nos primeiros dois e cinco dias após o nascimento. Foi avaliada a homogeneidade de valores entre géneros e entre grupos de idade de gestação. Resultados: A amostra constou de 158 recém-nascidos, 34 de termo e 124 pré-termo (idade de gestação entre 26 a 41 semanas), com peso de nascimento de 595 g a 4195 g, 84 do sexo masculino (53,2%) e 20 gémeos (10,8%). A média da VdS aumenta significativamente com a idade de gestação. São providenciados valores de referência da VdS para os percentis 10, 25, 50, 75 e 90, para grupos de idade de gestação, sem distinção para o género. Conclusão: São disponibilizados valores de referência de VdS nos primeiros dias de vida, de recém-nascidos adequados para a idade de gestação, de termo e pré-termo, nascidos em Portugal. Estes valores reflectem a robustez óssea intrauterina e servem de referência basal para estudos evolutivos realizados em Portugal.

Robótica móvel: sistema de condução autónoma

Dissertação para obtenção do grau de Mestre em Engenharia Electrotécnica Ramo Automação e Electrónica Industrial

Desenvolvimento e mensuração do diâmetro transversal do cerebelo fetal por ressonância magnética

A ressonância magnética fetal é um método eficaz na avaliação pré-natal da morfologia normal do cérebro e no diagnóstico de patologias do sistema nervoso central, sendo um importante complemento clínico à ecografia. O cerebelo é uma das estruturas menos afetadas em casos de restrição de crescimento fetal, tornando-se um bom indicador na avaliação do desenvolvimento fetal e da idade gestacional. Deste modo, a avaliação biométrica fetal é fundamental no diagnóstico pré-natal do desenvolvimento cerebral. Objetivo – Avaliação do diâmetro transversal do cerebelo (estrutura anatómica de referência do sistema nervoso central) do feto e posterior comparação com um estudo internacional reconhecido nesta matéria. Material e métodos – A amostra foi constituída por 84 gestantes que realizaram ressonância magnética fetal numa clínica de imagiologia médica da região Centro. A medição considerada para a avaliação do desenvolvimento fetal foi o diâmetro transversal do cerebelo. Resultados – Os resultados obtidos para o diâmetro transversal do cerebelo por ressonância magnética fetal vieram a demonstrar a ausência de diferenças médias estatisticamente significativas (p>0,05) em função do número de semanas de gestação, face aos valores teóricos aferidos no estudo de Garel. Conclusão – Com base nos resultados obtidos, para o diâmetro transversal do cerebelo podemos concluir que o parâmetro analisado é coerente com a publicação de Catherine Garel – Le développement du cerveau foetal atlas IRM et biometrie.

Does diaphragmatic breathing technique really improve its range of motion? An objective assessment

Purpose - To verify the results of a diaphragmatic breathing technique (DBT) on diaphragmatic range of motion in healthy subjects. Methods - A total of 51 healthy subjects (10 male; 41 female), mean age 20 years old and a body mass index (BMI) ranging from 15.6 to 34.9 kg/m2, were enrolled in this study. Diaphragmatic range of motion was assessed by M-mode ultrasound imaging. Measurements were made before and after the DBT implementation in a standard protocol, based on 3 seconds of inspiration starting from a maximum expiration. Differences between assessments were analyzed by descriptive statistics and t-test (p < 0.05). Results - Mean value range of motion before DBT was 55.3 ± 13.4 mm and after DBT was 63.8 ± 13.2 mm showing a significant improvement of 8.5 ± 14.7 mm (p < 0.001). A strong correlation between the slope and the range of motion was found (r = 0.71, p < 0.001). Conclusions - Based on ultrasound measurements, it has been proved that DBT really contributes to a higher diaphragmatic range of motion. Future studies are needed in order to understand the influence of protocol parameters (e.g. inspiration time). Clinical implications - In the contest of evidence-based practice in physiotherapy, it has been showed by objective measurements that DBT improves the diaphragm range of motion, translating into a more efficient ventilatory function and thus can be used in clinical setting. To our knowledge this is the first study to assess the effects of DBT on range of motion of diaphragm muscle with ultrasound imaging.

Análise por ultra-sons no controlo de condição

Trabalho Final de Mestrado para obtenção do grau de Mestre em Engenharia Mecânica

X Radiation dose implications in screening patients with ferromagnetic IOFBs prior to MRI: a literary review

Patients scheduled for a magnetic resonance imaging (MRI) scan sometimes require screening for ferromagnetic Intra Orbital Foreign Bodies (IOFBs). To assess this, they are required to fill out a screening protocol questionnaire before their scan. If it is established that a patient is at high risk, radiographic imaging is necessary. This review examines literature to evaluate which imaging modality should be used to screen for IOFBs, considering that the eye is highly sensitive to ionising radiation and any dose should be minimised. Method: Several websites and books were searched for information, these were as follows: PubMed, Science Direct, Web of Knowledge and Google Scholar. The terms searched related to IOFB, Ionising radiation, Magnetic Resonance Imaging Safety, Image Quality, Effective Dose, Orbits and X-ray. Thirty five articles were found, several were rejected due to age or irrelevance; twenty eight were eventually accepted. Results: There are several imaging techniques that can be used. Some articles investigated the use of ultrasound for investigation of ferromagnetic IOFBs of the eye and others discussed using Computed Tomography (CT) and X-ray. Some gaps in the literature were identified, mainly that there are no articles which discuss the lowest effective dose while having adequate image quality for orbital imaging. Conclusion: X-ray is the best method to identify IOFBs. The only problem is that there is no research which highlights exposure factors that maintain sufficient image quality for viewing IOFBs and keep the effective dose to the eye As Low As Reasonably Achievable (ALARA).

Estimation of 3D shapes using active surface models

This paper addresses the estimation of surfaces from a set of 3D points using the unified framework described in [1]. This framework proposes the use of competitive learning for curve estimation, i.e., a set of points is defined on a deformable curve and they all compete to represent the available data. This paper extends the use of the unified framework to surface estimation. It o shown that competitive learning performes better than snakes, improving the model performance in the presence of concavities and allowing to desciminate close surfaces. The proposed model is evaluated in this paper using syntheticdata and medical images (MRI and ultrasound images).

Coluna de som utilizando array de transdutores de ultrasons

Trabalho Final de Mestrado para obtenção do grau de Mestre em Engenharia de Electrónica e Telecomunicações