Round table: Pattern recognition methods in pulmonology and phthisiology using the differential diagnosis of bronchopulmonary diseases as an example.
Julia Brodskaya, Saratov State University
Abstract
The article describes approaches to solving problems that are found in the modern application of the mathematical theory of pattern recognition - medical diagnostics. The author propose the implementation of a pattern recognition method for diagnosing diseases of a selected class of the thoracic region - human broncho-pulmonary diseases.The study describes a convolutional neural network trained by a teacher, which can help doctors of various fields (general practitioners, TB doctors, radiation and functional diagnostics) with the problem of early diagnosis of pneumonia, both bacterial and viral (to differentiate between viral and bacterial pathologies)
Speaker
Julia Brodskaya
Saratov State University
Russia
Discussion
Ask question