Clasificación de Imágenes Médicas para la Detección del Cáncer de mama mediante Redes Neuronales

At present, it is not easy to interpret mammography images and provide a medical diagnosis by a health professional. Despite the professional's experience, anomalies or tumors are not detected 100% quickly. Since it is not easy to interpret. main objective was to perform an image classifier and apply a convolutional neuron. After a rigorous training of the neuron to provide an efficient diagnosis, it is shown that by increasing training the result is more efficient and the error factor is decreased. Only in the second test was 64.3% effective. In the research, no incompatible images with the neural network were presented, so no attributes were lost if parameter adjustments were made. So it is demonstrable that the system has great practical scope because the resources used are easy to reach.