Support to the Diagnosis of the Pap Test, Using Computer Algorithms of Digital Image Processing

40 years ago, uterine cervix cancer represented one of the greatest threats of cancer death among women. With continued advances in medicine and technology, deaths from this disease have declined significantly. The investigations concerning this issue have been determined key symptoms to detect the disease in time to give timely treatment. Conventional cytology is one of the most commonly used techniques being widely accepted because it's inexpensive, and provide many control mechanisms. In order to alleviate the workload to specialists, some researchers have proposed the development of computer vision tools to detect and classify the changes in the cells of the cervix region. This research aims to provide researchers with an automatic classification tool applicable to the conditions in medical and research centers in the country. This tool classifies the cells of the cervix, based solely on the features extracted from the nucleus region and reduces the rate of false negative Pap test. From the study, a tool using the technique k-nearest neighbors with distance Manhattan, which showed high performance while maintaining AUC values greater than 91% and reaching 97.1% with a sensitivity of 96% and 88% of obtained specificity.