Analysis of ultrasound images of chronic diffuse liver diseases using texture parameters of gray gradations

The paper proposes a technology for analyzing ultrasound images based on textural characteristics the development of medical decision-making system determining presence pathological changes in diffuse liver diseases. list algorithmic solutions known and proposed by authors formation selection informative features was applied, version Random Forest classification algorithm developed, which achieved (compared with analogues) highest quality indicators normal pathology. Ensuring "explainability" computer diagnostic solution radiologists is accompanying conclusion an image indicator, binarized transformation primary image, where binary colors are associated corresponding norm-pathology class. kind "amplifier" effect pathology, allows to consciously agree artificial intelligence or question its diagnosis recommend additional research. handed over co-authors work, specialists Institute Nuclear Medicine Radiodiagnosis National Academy Medical Sciences Ukraine, trial operation.