Журнал «Современная Наука»

Russian (CIS)English (United Kingdom)
 MOSCOW +7(495)-142-86-81

PNEUMONIA DETECTION IN CHEST X-RAY IMAGES USING A CONVOLUTIONAL NEURAL NETWORK

Kasyuk S.   (South Ural State Medical University" of the Ministry of Health of the Russian Federation (Chelyabinsk))

Didenko G.   (South Ural State Medical University" of the Ministry of Health of the Russian Federation (Chelyabinsk))

Stepanova O.   (South Ural State Medical University" of the Ministry of Health of the Russian Federation (Chelyabinsk))

The article considers a modern technology of X-ray diagnostics based on the use of a convolutional neural network. A publicly available pneumonia X-ray dataset, provided by Kermany et al., for image-based deep learning is described. A configuration of convolutional neural network built on the GoogLeNet architecture is outlined. The Python program implementing neural network's learning process, calculation of evaluation metrics and pneumonia detection is described. The process of training the convolutional neural network is outlined. The comparison of the obtained evaluation metrics of the binary classifier and results of published international researches is given.

Keywords:X-ray diagnostics, data classification, deep learning, convolutional neural network, Python programming
 

Read the full article …

Citation link:
Kasyuk S. , Didenko G. , Stepanova O. PNEUMONIA DETECTION IN CHEST X-RAY IMAGES USING A CONVOLUTIONAL NEURAL NETWORK // Современная наука: актуальные проблемы теории и практики. Серия: Естественные и Технические Науки. -2023. -№09/2. -С. 89-97 DOI 10.37882/2223-2966.2023.9-2.12
LEGAL INFORMATION:
Reproduction of materials is permitted only for non-commercial purposes with reference to the original publication. Protected by the laws of the Russian Federation. Any violations of the law are prosecuted.
© ООО "Научные технологии"

Terms Publications

Issues of the journals (Archive)

ECONOMICS AND LAW
HUMANITIES
NATURAL AND TECHNICAL SCIENCES
COGNITION

Серия - Natural and Technical Sciences