Model for making diagnostic decisions in multiparametric ultrasound of breast lesions

Abstract

In order to standardize the description of the breast imaging, the BI-RADS (Breast Imaging Reporting And Data System) imaging system developed by the American College of Radiologists ACR is widely used in world practice. At the same time, numerous visual characteristics of breast lesions with different diagnostic methods complicate the adoption of diagnostic decisions while using the BI-RADS system. The greatest difficulties arise when assessing a variety of multiparametric ultrasound signs of diseases. In this regard, in order to increase the efficiency of these technologies and make fast diagnostic decisions, it becomes relevant to develop a system model based on algorithms using the BI-RADS lexicon. Materials and methods: from 2017 to 2019 on the basis of the Research Oncology Center named after N.N. Petrov 277 women with various complaints of breast disease were examined using multiparametric ultrasound with elastography and contrast enhancement (2.5 ml Sonovue) on a Hitachi Hi Vision Ascendus ultrasound scanner. The software implementation of the diagnostic decision-making model was carried out using the C # programming language using the Microsoft Visual integrated development environment. Results: The effectiveness of the developed diagnostic model using the optimal algorithm for the use of various ultrasound technologies in determining the malignancy of the formation showed Sensitivity (Se) = 90.8%, Specificity (Sp) = 95.5%, Positive Predictive Value (PPV) = 88.5%, Negative Predictive Value (NPV) = 96.4%, Accuracy (Ac) = 94.2%. The effectiveness of the developed model in grouping diseases showed Se = 84.2%, Sp = 81.1%, PPV = 62.7%, NPV = 93.1%, Ac = 81.9%. Conclusions: The proposed system model of the optimal algorithm for making a diagnostic decision based on statistically significant multiparametric ultrasound signs increases the diagnostic efficiency.