Automated detection of COVID-19 coronavirus infection based on analysis of chest X-ray images by deep learning methods

Early detection of COVID-19 infected patients is essential to ensure adequate treatment and reduce the load on the healthcare systems. One of effective methods for detecting COVID-19 is deep learning models of chest X-ray images. They can detect the changes caused by COVID-19 even in asymptomatic patients, so they have great potential as auxiliary systems for diagnostics or screening tools. This paper proposed a methodology consisting of the stage of pre-processing of X-ray images, augmentation and classification using deep convolutional neural networksXception, InceptionResNetV2, MobileNetV2, DenseNet121, ResNet50 and VGG16, previously trained on theImageNet dataset. Next, they fine-tuned and trained on prepared data set of chest X-rays images. The results of computer experiments showed that theVGG16 model with fine tuning of the parameters demonstrated the best performance in the classification of COVID-19 with accuracy 99,09%, recall=98,318%, precision=99,08% and f1_score=98,78. This signifies the performance of proposed fine-tuned deep learning models for COVID-19 detection on chest X-ray images.

Одним из эффективных методов обнаружения коронавирусной инфекции COVID-19 является рентгенография легких. В работе предложена методика компьютерного анализа рентгеновских снимков с использованием глубоких сверточных нейронных сетей Xception, MobileNetV2, DenseNet121, ResNet50, InceptionResNetV2 и VGG16, предварительно обученных на наборе данных ImageNet. Компьютерные эксперименты показали, что модель VGG16 обладает наилучшей производительностью при классификации COVID-19 с показателями точности (accuracy) 99,09%, чувствительности (recall) 98,318%.

Shchetinin E.Y.1 , Sevastyanov L.A. 2
Редакция журнала "Вестник ТГУ. УВТиИ"
Number of issue
  • 1 Financial University under the Government of Russian Federation
  • 2 Peoples Friendship University of Russia
Chest X-rays; deep learning; convolutional neural networks; covid-19; рентгеновские снимки; глубокое обучение; сверточные нейронные сети
Date of creation
Date of change
Short link

Other records

Nikolaev V., Peliy A., Borodina E., Ameth Diop, Shatohin A.
Каспий и глобальные вызовы. Федеральное государственное бюджетное образовательное учреждение высшего профессионального образования "Астраханский государственный университет". 2022. P. 475-479