IMPROVING THE VISUAL DIAGNOSIS OF DISEASES USING HYBRID NEURAL NETWORKS

Section: Articles Published Date: 2022-11-28 Pages: 20-25 Views: 0 Downloads: 0

Authors

  • S.N. Iskandarova Tashkent University of Information Technologies named after Muhammad al-Khorazmi Tashkent, Uzbekistan
  • J.K. Saydazimov Tashkent State Institute of Stomatology Tashkent, Uzbekistan
PDF

Abstract

Computer recognition algorithms based on microscopic images of blood particles can be used as a decision support mechanism to help specialists speed up the diagnostic process. The purpose of this work is to evaluate the quantitative analysis of hybrid neural networks (CNN + RNN). It can visually check the solution area of the input image used by CNN + LSTM. Based on the microscope image, the recognition results of blood composition particles according to their shape have been achieved up to 90%.

Keywords

coronavirus, convolutional neural network (CNN, recurrent neural network (RNN