Inteligência computacional aplicada em microcalcificações mamárias

Abstract

Breast cancer is the second most common cancer worldwide. According to the National Cancer Institute (INCA) in 2014 were diagnosed 52,680 new cases in Brazil, a number that corresponds to a 22% increase over the year 2013. Being responsible for approximately 39% of women's deaths cancer patients. Despite the high incidence rate, mortality from this cancer has declined since the late eighties, thanks to advances in research on methods for early diagnosis. However, correctly diagnosing cancer is a complex and difficult process as a result of the different variables involved. For an accurate diagnosis, a lot of experience and especially it is required, that the classification of clinical staging of tumor (cancer stage) is correct. The conditions used traditional classification systems are complex and often offer limitations. As is the case of mammography technique, widely used, it is not as effective for women with dense breasts, surgically altered, or under 40 years. Thus, it becomes necessary to develop integrated systems that combined with the professionals in the field experience, allows performing accurate diagnosis in detecting breast cancer. The objective of this study is to apply the technique SVM (Support Vector Machine), so as to assist in the diagnostic interpretation of microcalcifications detected on screening mammography. The data set used consisted of 961 samples of mammograms, obtained from the Radiology Institute of the University of Erlangen Nuremberg. In this set we have information on the age of the patient, BI-RADS (Breast Imaging Reporting and Data System), shape, mass, density and severity (benign | malignant) of microcalcifications. The SVM was developed implemented using the R software (R Development Core Team; http: // www.R-project.org/). The data were divided into two groups: the training set consisting of 80% of the samples of mammographic, used to estimate the model parameters and the independent test set, with 20% of the remaining samples, used to measure the performance of SVM . To evaluate the performance of proposed computational model we used the value of the Total Precision or Accuracy (ACC), sensitivity (S) and specificity (E). The results presented by SVM in identifying malignant lesions in patients with calcifications remained between 72.7% and 100%, which shows that they achieved a satisfactory level in relation to other literatures applied