Діагностика медичних зображень пухлин головного мозку з використанням гібридних згорткових нейронечітких мереж

The problem of classification of brain tumors on medical images is considered. For its solution hybrid CNN-ANFIS is developed in which convolutional neural network VGG-16 and ResNetV2_50 are used as feature extractors while ANFIS is used as the classifier. Training algorithms of ANFIS were implement...

Full description

Saved in:
Bibliographic Details
Date:2020
Author Affiliations:
  • Yuriy P. Zaychenko — Учебно-научный комплекс "Институт прикладного системного анализа" Национального технического университета Украины "Киевский политехнический институт имени Игоря Сикорского", Киев
  • Kostiantyn A. Zdor — Национальный технический университет Украины "Киевский политехнический институт имени Игоря Сикорского", Киев
  • Galib Hamidov — Компания “Азершиг”, Баку
Keywords:keywords
Main Authors: Zaychenko, Yuriy P., Zdor, Kostiantyn A., Hamidov, Galib
Format: Article
Language:Russian
Published: The National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute" 2020
Subjects:
Online Access:https://journal.iasa.kpi.ua/article/view/209135
Tags: Add Tag
No Tags, Be the first to tag this record!
Journal Title:System research and information technologies
Download file: Pdf

Institution

System research and information technologies
Description
Summary:The problem of classification of brain tumors on medical images is considered. For its solution hybrid CNN-ANFIS is developed in which convolutional neural network VGG-16 and ResNetV2_50 are used as feature extractors while ANFIS is used as the classifier. Training algorithms of ANFIS were implemented. The experimental investigations of the suggested hybrid network on the standard dataset Brain MRI images for brain tumor detection were carried out and comparison with known results was performed.
DOI:10.20535/SRIT.2308-8893.2020.1.06