Deep Learning Models Selection and Adaptation for a Typical Problem of X-Ray Image Processing

The paper explores a problem of artificial neural networks comparative analysis and adaptation while solving a typical task of image analysis and pattern recognition. This article examines four neural networks using different optimizers to solve a problem of pneumonia detection on X-ray images. The...

Full description

Saved in:

Bibliographic Details
Published in:	2021 Innovations in Intelligent Systems and Applications Conference (ASYU) pp. 1 - 5
Main Authors:	Sheshulin, Kirill, Chuvakov, Aleksandr, Ivaschenko, Anton
Format:	Conference Proceeding
Language:	English
Published:	IEEE 06-10-2021
Subjects:	Adaptation models artificial neural networks image processing intelligent systems Pattern recognition Pulmonary diseases Technological innovation Training Transfer learning Visualization
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	The paper explores a problem of artificial neural networks comparative analysis and adaptation while solving a typical task of image analysis and pattern recognition. This article examines four neural networks using different optimizers to solve a problem of pneumonia detection on X-ray images. The study implements convolutional neural networks, as well as the method of their transfer learning. The architecture of neural networks and the results of their work with various metrics that assess the success of this model are presented. The problem of interpretability of the decision made by a neural network can be solved using a special visualization method presented in the study. Advantages of the proposed research are related with a possibility to use the convolutional neural networks in practical applications.
DOI:	10.1109/ASYU52992.2021.9599075