RESUMO
RESUMEN Fundamento: existen muchas herramientas computacionales para administrar imágenes y conjuntos de datos; reducir la dimensión de estos favorece el manejo de la información. Objetivo: reducir la dimensión de un conjunto de datos para un mejor manejo de la información. Métodos: se utilizó el conjunto de datos de Breast Cancer Wisconsin (información de biopsias - células nucleares) y la plataforma Python Jupyter. Se implementaron técnicas de análisis de la componente principal (PCA) y Kernel PCA (kPCA) para reducir la dimensión a 2, 4, 6. Se hizo una validación cruzada para seleccionar los mejores hiperparámetros de los algoritmos de máquina de vectores de soporte y regresión logística. La clasificación se realizó con el training test original, training test (PCA y kPCA) y training test (datos transformados de PCA y kPCA). Se analizó la exactitud, precisión, exhaustividad, recuperación y el área bajo la curva. Resultados: la PCA con seis componentes explicó la tasa de variación casi en 90 %. Los mejores hiperparámetros hallados para máquina de soporte de vectores: kernel lineal y C = 100, para regresión logística fueron C = 100, Newton-cg solución (solver) e I2. Los mejores resultados de las métricas fueron para PCA 2 y 4(0,99; 0,99; 1; 0,99; 0,99). Para el training set con datos originales fueron 0,96; 0,95; 0,99; 0,97; 0,95. Para regresión logística los mejores resultados fueron para kPCA con seis componentes. Los resultados estadísticos fueron iguales a 1. Para el training set con datos originales, esos valores fueron 0,96; 0,95; 0,99; 0,97; 0.95. Conclusiones: los resultados de las métricas mejoraron utilizando PCA y kPCA.
ABSTRACT Background: there are many computational tools for managing images and data sets; reducing the size of these favors the management of information. Objective: reduce the data set size for better information management. Methods: the Breast Cancer Wisconsin data set (biopsy information - nuclear cells) and the Python Jupyter platform were used. Principal Component Analysis (PCA) and Kernel PCA (kPCA) techniques were implemented to reduce the dimension to 2, 4, 6. Cross-validation was made to select the best hyperparameters of the regression and support vector machine algorithms Logistics. The classification was carried out with the original training test, training test (PCA and kPCA) and training test (data transformed from PCA and kPCA). Accuracy, precision, completeness, recovery, and area under the curve were analyzed. Results: the PCA with six components explained the variation rate by almost 90%. The best hyperparameters found for the vector support machine: linear kernel and C = 100, for logistic regression were C = 100, Newton-cg solution (solver) and I2. The best results of the metrics were for PCA 2 and 4 (0.99, 0.99, 1, 0.99, 0.99). For the training set with original data they were 0.96; 0.95; 0.99; 0.97; 0.95. For logistic regression the best results were for kPCA with 6 components. The statistical results were equal to 1. For the training set with original data, these values were 0.96; 0.95; 0.99; 0.97; 0.95. Conclusions: the results of the metrics improved using PCA and kPCA.
RESUMO
In this study we present the radiation dose distribution for a theoretical model with Montecarlo simulation, and based on an experimental model developed for the study of the prevention of restenosis post-angioplasty employing intravascular brachytherapy. In the experimental in vivo model, the atherosclerotic plaques were induced in femoral arteries of male New Zealand rabbits through surgical intervention and later administration of cholesterol enriched diet. For the intravascular irradiation we employed a 32P source contained within the balloon used for the angioplasty. The radiation dose distributions were calculated using the Monte Carlo code MCNP4B according to a segment of a simulated artery. We studied the radiation dose distribution in the axial and radial directions for different thickness of the atherosclerotic plaques. The results will be correlated with the biologic effects observed by means of histological analysis of the irradiated arteries