Software implementation for diagnostic decision-making based on multiparametric ultrasonography parameters of breast masses

Abstract

Purpose. To build a system for making diagnostic decisions based on multiparametric ultrasound examination of the mammary gland.Material and Methods. A total of 277 women with various complaints of breast diseases were examined using a wide range of ultrasound technologies, including elastography and contrast enhancement. To verify the lesions, the patients underwent histological or cytological examination. The results of ultrasound examination, histological and cytological conclusions were entered into the database. The system was trained with 219 patient samples selected from the database. The patient’s samples were grouped according to the visual ultrasound characteristics. The data groups’ analysis allowed the compilation of a table with relative frequencies (probability) of symptoms for this diagnosis. Based on the convolution and the Bayesian method, the system for support of the medical decision by age, clinical picture, and ultrasound diagnostics results were built. Sensitivity and specificity were determined for software implementation in the initial database.Conclusion. The proposed decision support system allows us to determine the probability of malignancy and standardize decision-making in the differential diagnosis of breast masses.