Liver Pathological States Identification in Diffuse Diseases with Self-Organization Models Based on Ultrasound Images Texture Features (original) (raw)

2020 IEEE 15th International Conference on Computer Sciences and Information Technologies (CSIT), 2020

Abstract

The article deals with the construction of the norm-pathology states classifiers according to statistical features of the ultrasound images texture in diffuse liver diseases. A number of new features are proposed to distinguish the texture of classes. Classifiers are constructed in the form of analytical expressions using the GMDH Shell DS software and in the form of a forest, the trees of which are obtained in accordance with the GMDH principles. The work was performed on data, had provided by the Nuclear Medicine and Radiation Diagnostics Institute of the National Academy of Medical Sciences of Ukraine.

Irina Dykan hasn't uploaded this paper.

Let Irina know you want this paper to be uploaded.

Ask for this paper to be uploaded.