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.

Preparação e caracterização de biomateriais poliméricos para avaliação da viabilidade de uso como phantom biológico

The theoretical and experimental developments in the biomaterials area have been directly applied to different fields of Medicine (odontology, regenerative medicine and radiotherapy). These advances have focused both for diagnosing diseases such as for quantifying degrees of progression. From the perspective of these studies, biomaterials are being designed and manufactured for application in various areas of science, provided advances in diagnostic radiology, radiotherapy dosimetry and calibration of radiotherapy equipment. Develop a phantom from a biomaterial has become a great ally of medicine in the treat patients with oncological diseases, allowing better performance of the equipment in order to reduce damage to healthy tissue due to excessive exposure to radiation. This work used polymers: chitosan and gelatin, for making the polymeric structures and controlled for different types of production and processing, characterizing and evaluating the biopolymer by physical techniques (STL, SEM and DEI) and therefore analyze applicability as phantom mouse lung. It was possible to evaluate the morphology of biomaterials quantitatively by scanning electron microscopy associated with imaging technique. The relevance of this work focuses on developing a phantom from polymeric biomaterials that can act as phantom providing high image contrast when subjected to analysis. Thus, the choice of DEI technique is satisfactory since it is an imaging technique of X-ray high resolution. The images obtained by DEI have shown the details of the internal microstructure of the biomaterial produced which have ≈ 10 μm dimension. The phantoms had made density ranging from 0.08 a 0.13 g/cm3.