Using data mining techniques to support breast cancer diagnosis

More than ever, there is an increase of the number of decision support methods and computer aided diagnostic systems applied to various areas of medicine. In breast cancer research, many works have been done in order to reduce false-positives when used as a double reading method. In this study, we aimed to present a set of data mining techniques that were applied to approach a decision support system in the area of breast cancer diagnosis. This method is geared to assist clinical practice in identifying mammographic findings such as microcalcifications, masses and even normal tissues, in order to avoid misdiagnosis. In this work a reliable database was used, with 410 images from about 115 patients, containing previous reviews performed by radiologists as microcalcifications, masses and also normal tissue findings. Throughout this work, two feature extraction techniques were used: the gray level co-occurrence matrix and the gray level run length matrix. For classification purposes, we considered various scenarios according to different distinct patterns of injuries and several classifiers in order to distinguish the best performance in each case described. The many classifiers used were Naïve Bayes, Support Vector Machines, k-nearest Neighbors and Decision Trees (J48 and Random Forests). The results in distinguishing mammographic findings revealed great percentages of PPV and very good accuracy values. Furthermore, it also presented other related results of classification of breast density and BI-RADS® scale. The best predictive method found for all tested groups was the Random Forest classifier, and the best performance has been achieved through the distinction of microcalcifications. The conclusions based on the several tested scenarios represent a new perspective in breast cancer diagnosis using data mining techniques.

Human pulmonary dirofilariasis: a review

The authors presented a detailed summary of the geographical distribution, clinical and pathological aspects of human pulmonary dirofilariasis. Although benign, this zoonosis, of which Dirofilaria immitis is the major etiological agent, represents a medical problem since it produces symptoms which may be confused with neoplasia and thus may subject patients to unnecessary thoracic surgery. Of 229 cases cited in the literature, only 17 were reported in Brazil, despite the existence of highly favorable conditions for the transmission of this infection in man. Thus it may well be that this parasitic infection remains underdiagnosed. Finally, the importance of a differential diagnosis between dirofilariasis and pulmonary neoplasia is emphasized in cases where there is a solitary subpleural nodule ("coin lesion") present. In addition, the development and improvement of modern immunological diagnostic techniques are essential to distinguish this benign disease from other pathological conditions and thus avoid unneccessary surgery. These techniques may reveal the true prevalence of this parasitic infection in our environment.

Artificial Intelligence in geospatial analysis: applications of self-organizing maps in the context of geographic information science.

A thesis submitted in partial fulfilment of the requirements for the degree of Doctor of Philosophy in Information Systems.

Detection of mycoplasmas in urethral swabs from HIV-1 infected patients and control individuals using culture techniques and polymerase chain reaction

The objective of the present study was to determine the prevalence of certain mycoplasma species, i.e., Mycoplasma hominis, Ureaplasma urealyticum and Mycoplasma penetrans, in urethral swabs from HIV-1 infected patients compared to swabs from a control group. Mycoplasmas were detected by routine culture techniques and by the Polymerase Chain Reaction (PCR) technique, using 16SrRNA generic primers of conserved region and Mycoplasma penetrans specific primers. The positivity rates obtained with the two methods were comparable. Nevertheless, PCR was more sensitive, while the culture techniques allowed the quantification of the isolates. The results showed no significant difference (p < 0.05) in positivity rates between the methods used for mycoplasma detection.

PALEOPARASITOLOGY: PERSPECTIVES WITH NEW TECHNIQUES

Paleoparasitology is the study of parasites found in archaeological material. The development of this field of research began with histological identification of helminth eggs in mummy tissues, analysis of coprolites, and recently through molecular biology. An approach to the history of paleoparasitology is reviewed in this paper, with special reference to the studies of ancient DNA identified in archaeological material.

Invited review: Models for the optimization of regional wastewater treatment systems

European Journal of Operational Research, nº 73 (1994)

Archaeological roman glasses: comparative characterisation by non-destructive analytical techniques

Dissertation presented in fulfilment of the requirements for the Master’s degree in Conservation and Restoration

Gold nanoparticle-DNA conjugates for oligonucleotide vectorization towards gene silencing

Dissertação para obtenção do Grau de Mestre em Genética Molecular e Biomedicina

Archaeometallurgical study of artefacts from Castro de Vila Nova de São Pedro (Azambuja, Portugal)

Dissertação para obtenção do Grau de Mestre em Conservação e Restauro

Inovação de técnicas administrativas para o melhoramento de desempenho das atividades organizacionais

Dissertação apresentada ao Instituto Politécnico do Porto - Instituto Superior de Contabilidade e Administração do Porto, para obtenção do Grau de Mestre em Assessoria e Administração de Organizações, sob orientação de Anabela Mesquita, PhD

Trace elements quantification in Portuguese red wines

Dissertation for the Degree of Master in Technology and Food Safety – Food Quality

Calculating rabies virus neutralizing antibodies titres by flow cytometry

The determination of the rabies neutralizing antibody (VNA) response after immunization against rabies is an acceptable index of the efficacy of a vaccine and a successful treatment. Several tests have been developed in attempt to improve the assessment of VNA, from mice inoculation to cell-culture fluorescence inhibition tests. All of them, however, present special difficulties in terms of reading or accuracy. The present study describes a neutralization test performed in cell-culture appraised by flow cytometry (FC). Serial dilutions of the serum samples were mixed in vitro with rabies virus before the addition of BHK-21 cells. After 24h-incubation, cells were released by trypsin treatment, fixed and permeabilized with a p-formaldehyde solution and stained with a rabies virus nucleocapsid protein-specific antibody conjugate. The percentage of virus infection inhibition caused by specific antibodies present in the serum were evaluated in a Beckton & Dickinson FACSCalibur® flow cytometer. A correlation curve between the IU/ml content and the percentage of infective inhibition was built with a reference serum and the VNA titers of serum samples were obtained by extrapolation. Titers obtained by FC and standard test showed an effective pairing results (p < 0.01), with a correlation coefficient (r) = 0.7. These results permit to envisage the FC as a suitable technique to evaluate VNA in sera from immunized animals and likely in human serum samples. Nevertheless, new studies comparing FC to gold-standard techniques are required for determining the FC values of Sensibility and Specificity .