Desarrollo de una aplicación software para la caracterización BIRADS ecográfica automatizada de lesiones en phantom de mama.

Abstract

Breast cancer is the second leading cause of death in the world. There are several methods to diagnose this disease, however, mammography has become the main exam to determine the presence of benign or malignant lesions in the breast. For their part, radiologist doctors use the BI-RADS protocol (Breast Imaging Report and Database System) to categorize the lesions according to the degree of suspicion and to inform the patient in simple terms of their respective diagnosis. Breast ultrasound is used as a complementary examination to mammography and is used in the first instance for the identification of suspicions that can be confirmed by better resolution images, thrown by the mammographer, a robust, high-cost equipment that uses ionizing radiation, for this reason, in this work, a software application for the automated calculation of BI-RADS1 ultrasound descriptors (echogenic pattern, orientation, edges, morphology) was analyzed, implementing computational algorithms in digital format of biomedical images captured by the use of an INTERSON USB ultrasound probe on an acoustic phantom of mom, with nodular lesions and processed on the Matlab platform, whose long-term objective is to support the qualitative analysis of the radiologist, to reduce the times of diagnosis and false positives.