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.

Estudo das alterações hematológicas e urinárias em cães em diferentes estágios de disfunção renal e avaliação do biomarcador cistatina C

Chapter 2 - Cystatin C is a cationic protein is not glycosylated, produced a steady state for all nucleated and present in biological fluids cells being freely filtered by the glomeruli and almost completely catabolized in the proximal tubule, it is a promising early renal dysfunction marker. This study aimed to determine and compare the serum concentration of cystatin C biomarker in 86 dogs. The animals were divided into four groups according to serum creatinine levels: G1 - up. 1.4 mg / dL (23 animals), G2 - 1.5-2.0 mg / dL (16 animals), G3 - 2.1 to 5.0 mg / dL (24 animals) and G4 - above 5.1 mg / dL (23 animals). There was the measurement of the parameters used in the clinical routine of small animals such as urea, urinary gamma glutamyl transferase, proteinuria, alkaline phosphatase, sodium, potassium, chloride, calcium, phosphorus, calcium/phosphorus ratio and cystatin C. There was no statistical difference for urea, proteinuria, phosphorus, calcium/phosphorus, potassium and cystatin C, however, the other showed no statistical difference. Based on the results we can infer that cystatin C was not a good early indicator of kidney disease in dogs. Chapter 3 - This study aimed to determine the hematological and urinalysis elements such as density, proteinuria, cylinders and pH in 86 dogs The animals were divided into four stages according to serum creatinine levels: I - up to 1.4 mg/dL (23 animals), II - 1.5-2.0 mg/dL (16 animals), III from 2.1 to 5.0 mg/dL (24 animals) and IV - above 5.1 mg/dL (23 animals). In stage III, IV there was anemia normocytic normochromic type. Stage II had a leukocytosis frame by neutrophilia with a regenerative left shift and stage III and IV detour degenerative left. The density remained within the reference values all stages. Proteinuria showed statistical significance for the classification 2+ (1.0 g/L), between stage I and II, II and IV. Only the cylinder granular statistical difference in the classification 2+ between stage II and III, and 3+ between stage I and III. The prevailing pH was acid. The haematological values compared to serum creatinine stages showed the changes in hemoglobin and packed cell volume erythrocytes become more pronounced as serum creatinine values rise , this is also the behavior of neutrophils rods and proteinuria.