INTELLIGENT SYSTEMS FOR BREAST CANCER PATHOLOGY DETECTION BASED ON DEEP NEURAL NETWORKS

The paper is devoted to the development and implementation of intelligent systems based on deep neural networks for detecting the level of mammary gland pathologies. The relevance and importance of the topic is due to the high morbidity and mortality among women, in particular, in the Republic of Kazakhstan, from breast cancer, which occupies one of the leading places in the structure of oncological diseases. Early detection of pathologies is a key factor in successful treatment; however, traditional diagnostic methods often require significant resources and are dependent on human factors. The use of artificial intelligence can improve diagnostic accuracy, reduce the workload on radiologists, and minimize the likelihood of missing early signs of the disease. The article discusses the architecture of deep neural networks adapted for analyzing mammographic images and provides a comparison of the efficiency of the proposed methods with traditional approaches. The study results demonstrate high sensitivity and specificity of automated systems in detecting both benign and malignant tumors, making them promising for clinical use.