Classificação de nódulos pulmonares em imagens tomográficas utilizando redes neurais artificiais em cascata

Lung cancer is the most common of malignant tumors, with 1.59 million new cases worldwide in 2012. Early detection is the main factor to determine the survival of patients affected by this disease. Furthermore, the correct classification is important to define the most appropriate therapeutic approach as well as suggest the prognosis and the clinical disease evolution. Among the exams used to detect lung cancer, computed tomography have been the most indicated. However, CT images are naturally complex and even experts medical are subject to fault detection or classification. In order to assist the detection of malignant tumors, computer-aided diagnosis systems have been developed to aid reduce the amount of false positives biopsies. In this work it was developed an automatic classification system of pulmonary nodules on CT images by using Artificial Neural Networks. Morphological, texture and intensity attributes were extracted from lung nodules cut tomographic images using elliptical regions of interest that they were subsequently segmented by Otsu method. These features were selected through statistical tests that compare populations (T test of Student and U test of Mann-Whitney); from which it originated a ranking. The features after selected, were inserted in Artificial Neural Networks (backpropagation) to compose two types of classification; one to classify nodules in malignant and benign (network 1); and another to classify two types of malignancies (network 2); featuring a cascade classifier. The best networks were associated and its performance was measured by the area under the ROC curve, where the network 1 and network 2 achieved performance equal to 0.901 and 0.892 respectively.

Utilização da transformada de wavelet para detecção de variações anormais de tensão em sistemas elétricos com geração distribuída

The increasing demand in electricity and decrease forecast, increasingly, of fossil fuel reserves, as well as increasing environmental concern in the use of these have generated a concern about the quality of electricity generation, making it well welcome new investments in generation through alternative, clean and renewable sources. Distributed generation is one of the main solutions for the independent and selfsufficient generating systems, such as the sugarcane industry. This sector has grown considerably, contributing expressively in the production of electricity to the distribution networks. Faced with this situation, one of the main objectives of this study is to propose the implementation of an algorithm to detect islanding disturbances in the electrical system, characterized by situations of under- or overvoltage. The algorithm should also commonly quantize the time that the system was operating in these conditions, to check the possible consequences that will be caused in the electric power system. In order to achieve this it used the technique of wavelet multiresolution analysis (AMR) for detecting the generated disorders. The data obtained can be processed so as to be used for a possible predictive maintenance in the protection equipment of electrical network, since they are prone to damage on prolonged operation under abnormal conditions of frequency and voltage.

Relação entre a cárie precoce da infância com o índice de Apgar e outros fatores de risco

The aim of this cross-sectional study was to investigate the association of early childhood caries (ECC) with the Apgar score (AS) and other variables related to the child (conditions at birth and medical history) and related to the child and parents and / or guardians and family (demographic, socioeconomic and behavioral). One hundred and twenty healthy children aged between 3-5 years-old treated by Pediatric Dentistry Area of Dentistry College of the Federal University of Uberlandia during 2015 were selected. To obtain qualitative and quantitative variables a questionnaire was applied as an interview to the parents and/or guardians. The 5-minute AS (interest exposure) was obtained through the record in the Child Health Handbook. To assess the prevalence of caries (clinical dependent variable), a single calibrated researcher conducted the clinical examination, according to the criteria of the World Health Organization. Caries experience was measured using the indexes dmft and dmfs. The children were classified into three groups, according to age and dmfs index: no caries (NC), with ECC and with severe early childhood caries (S-ECC). Data were tabulated and submitted to statistical analysis using the SPSS software (IBM, Inc, Chicago, Illinois, USA) 17th version. Three logistics models were carried out having the following classifications: NC and ECC, NC and S-ECC, ECC and S-ECC (p<0.05). The overall ECC prevalence, considering children with ECC and S-ECC, was 55,8% (n= 67). The AS was not a statistically significant variable. The child’s age, weaning age and recent hospitalization were variables associated with the ECC prevalence. The age of brush start and the educational level of the mother were variables associated with the S-ECC prevalence. Considering the ECC and the S-ECC groups, the child's age and the beginning of the use of fluoride toothpaste, recent hospitalization, the educational level of the mother and the father's income were associated with the S-ECC prevalence. Considering the methodology employed and the analysis of results, it was concluded that there was no association between the ECC with the AS in healthy children. However, an association was found of ECC and S-ECC with some variables related to birth and to medical history of the child (recent hospitalization), demographic (child’s age), socioeconomic (educational level of the mother and father's income) and behavioral (age of brush start, weaning age and use of fluoride toothpaste) related to children and to the parents and/or guardians.

Modelagem molecular voltada para a construção de um nanobiossensor para detecção do herbicida Imazaquin

In this study, our goal was develop and describe a molecular model of the enzyme-inhibiting interaction which can be used for an optimized projection of a Microscope Force Atomic nanobiosensor to detect pesticides molecules, used in agriculture, to evaluate its accordance with limit levels stipulated in valid legislation for its use. The studied herbicide (imazaquin) is a typical member of imidazolinone family and is an inhibitor of the enzymatic activity of Acetohydroxiacid Synthase (AHAS) enzyme that is responsible for the first step of pathway for the synthesis of side-chains in amino acids. The analysis of this enzyme property in the presence of its cofactors was made to obtain structural information and charge distribution of the molecular surface to evaluate its capacity of became immobilized on the Microscopy Atomic Force tip. The computational simulation of the system, using Molecular Dynamics, was possible with the force-field parameters for the cofactor and the herbicides obtained by the online tool SwissParam and it was implemented in force-field CHARMM27, used by software GROMACS; then appropriated simulations were made to validate the new parameters. The molecular orientation of the AHAS was defined based on electrostatic map and the availability of the herbicide in the active site. Steered Molecular Dynamics (SMD) Simulations, followed by quantum mechanics calculations for more representative frames, according to the sequential QM/MM methodology, in a specific direction of extraction of the herbicide from the active site. Therefore, external harmonic forces were applied with similar force constants of AFM cantilever for to simulate herbicide detection experiments by the proposed nanobiosensor. Force value of 1391 pN and binding energy of -14048.52 kJ mol-1 were calculated.

Avaliação do AAM - Active Appearance Model para detecção de regiões de interesse em radiografias carpais na estimativa da idade óssea através do método TW

In several areas of health professionals (pediatricians, nutritionists, orthopedists, endocrinologists, dentists, etc.) are used in the assessment of bone age to diagnose growth disorders in children. Through interviews with specialists in diagnostic imaging and research done in the literature, we identified the TW method - Tanner and Whitehouse as the most efficient. Even achieving better results than other methods, it is still not the most used, due to the complexity of their use. This work presents the possibility of automation of this method and therefore that its use more widespread. Also in this work, they are met two important steps in the evaluation of bone age, identification and classification of regions of interest. Even in the radiography in which the positioning of the hands were not suitable for TW method, the identification algorithm of the fingers showed good results. As the use AAM - Active Appearance Models showed good results in the identification of regions of interest even in radiographs with high contrast and brightness variation. It has been shown through appearance, good results in the classification of the epiphysis in their stages of development, being chosen the average epiphysis finger III (middle) to show the performance. The final results show an average percentage of 90% hit and misclassified, it was found that the error went away just one stage of the correct stage.