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.

Avaliação da adaptação marginal de diferentes tipos de restaurações obtidas por CAD/CAM e métodos convencionais

The past few decades have brought many changes to the dental practice and the technology has become ready available. The result of a satisfactory rehabilitation treatment basically depends on the balance between biological and mechanical factors. The marginal adaptation of crowns and prosthetic structures is vital factor for long-term success. The development of CAD / CAM technology in the manufacture of dental prostheses revolutionized dentistry, this technology is capable of generating a virtual model from the direct digital scanning from the mouth, casts or impressions. It allows the planning and design of the structure in a computered software. The virtual projects are obtained with high precision and a significant reduction in clinical and laboratory time. Thus, the present study (Chapters 1, 2 and 3) computed microtomography was used to evaluate, different materials, different CAD/CAM systems, different ways of obtaining virtual model (with direct or indirect scanning), and in addition, also aims to evaluate the influence of cementing agent in the final adaptation of crowns and copings obtained by CAD / CAM. Furthermore, this study (Chapter 4, 5 and 6) also aims to evaluate significant differences in vertical and horizontal misfits in abutment-free frameworks on external hexagon implants (HE) using full castable UCLAs, castable UCLAs with cobalt-chromium pre-machined bases and obtained by CAD / CAM with CoCr or Zirconia by different scanning and milling systems. For this, the scanning electron microscopy and interferometry were used. It was concluded that the CAD / CAM technology is capable to produce restorations, copings and screw-retained implant-supported frameworks in different materials and systems offering satisfactory results of marginal accuracy, with significative reduction in clinical and laboratory time.