Обнаружение коронавирусной инфекции COVID-19 на основе анализа рентгеновских снимков грудной клетки методами глубокого обучения

Автор: Щетинин Евгений Юрьевич

Журнал: Компьютерная оптика @computer-optics

Рубрика: Обработка изображений, распознавание образов

Статья в выпуске: 6 т.46, 2022 года.

Бесплатный доступ

Раннее выявление пациентов с коронавирусной инфекцией COVID-19 имеет важное значение для обеспечения их адекватного лечения и снижения нагрузки на систему здравоохранения. Эффективным методом обнаружения COVID-19 является компьютерный анализ рентгеновских снимков грудной клетки методами глубокого обучения. В работе предложена методология, состоящая из этапов стандартизации размеров рентгеновских снимков к (224, 224), их классификации с использованием глубоких сверточных нейронных сетей Xception, InceptionResNetV2, MobileNetV2, DenseNet121, ResNet50 и VGG16, предварительно обученных на наборе данных ImageNet, а затем настроенных на наборе рентгеновских снимков грудной клетки. Результаты компьютерных экспериментов показали, что модель VGG16 с тонкой настройкой параметров продемонстрировала максимальную эффективность в классификации COVID-19 с показателями точности (accuracy) 99,09 %, полнота (recall) 99,483 %, прецизионность (precision) 99,08 %.

Еще

Covid-19, рентгеновские снимки грудной клетки, глубокое обучение, сверточные нейронные сети

Короткий адрес: https://sciup.org/140296268

IDR: 140296268   |   DOI: 10.18287/2412-6179-CO-1077

Список литературы Обнаружение коронавирусной инфекции COVID-19 на основе анализа рентгеновских снимков грудной клетки методами глубокого обучения

  • World Health Organization. November 25, 2021. Source: (https://www.who.int/emergencies/diseases/novel-coronavirus-2019).
  • Sohrabi С, et al. World Health Organization declares global emergency: A review of the 2019 novel coronavirus (COVID-19). Int J Surg 2020; 76: 71-76. DOI: 10.1016/j.ijsu.2020.02.034.
  • Zhang R, Tie X, Qi Z, Bevins NB, Zhang C, Griner D, Song TK, Nadig JD, Schiebler ML, Garrett JW, Li K, Reeder SB, Chen G-H. Diagnosis of coronavirus disease 2019 pneumonia by using chest radiography: Value of artificial intelligence. Radiology 2021; 298(2): E88-E97. DOI: 10.1148/radiol.2020202944.
  • Kim M, Yan C, Yang D, Wang Q, Ma J, Wu G. Deep learning in biomedical image analysis. In Book: Biomedical information technology. 2nd ed. Chap 8. London: Academic Press; 2020: 239-263. DOI: 10.1016/B978-0-12-816034-3.00008-0.
  • Mei X, Lee HC, Diao K. Artificial intelligence-enabled rapid diagnosis of patients with COVID-19. Nat Med 2020; 26: 1224-1228. DOI: 10.1038/s41591-020-0931-3.
  • Kong W, Agarwal PP. Chest imaging appearance of COVID-19 infection. Radiol Cardiothorac Imaging 2020; 2(1): e200028. DOI: 10.1148/ryct.2020200028.
  • Simonyan K, Zisserman AJ. Very deep convolutional networks for large-scale image recognition. 2014. arXiv Preprint. Source: (https://arxiv.org/abs/1409.1556). DOI: 10.48550/arXiv.1409.1556.
  • He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. 2016. arXiv Preprint. Source: (https://arxiv.org/abs/1512.03385). DOI: 10.48550/arXiv.1512.03385.
  • Szegedy C, Vanhoucke V, Ioffe S, et al. Rethinking the inception architecture for computer vision. 2015. arXiv Preprint. Source: (https://arxiv.org/abs/1512.00567). DOI: 10.48550/arXiv.1512.00567.
  • Sandler M, Howard A, Zhu M, Zhmoginov A, Chen L-C. MobileNetV2: Inverted residuals and linear bottle. The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2018: 4510-4520. DOI: 10.48550/arXiv.1801.04381.
  • Chowdhury M, Rahman T, Khandakar A, Mazhar R, Kadir MA, Mahbub ZB, Islam KR, Khan MS. Can AI help in screening viral and COVID-19 pneumonia? IEEE Access 2020; 8: 132665-132676.
  • Ismael AM, Sengur A. Deep learning approaches for COVID-19 detection based on chest X-ray images. Expert Syst Appl 2021; 164: 114054. DOI: 10.1016/j.eswa.2020.114054.
  • Ozturk T, Talo M, Yildirim EA, Baloglu UB, Yildirim O, Acharya UR. Automated detection of COVID-19 cases using deep neural networks with X-ray images. Comput Biol Med 2020; 121: 103792. DOI: 10.1016/j.compbiomed.2020.103792.
  • Nafees MT, Rizwan M, Khan MI, Farhan M. A novel con-volutional neural network for COVID-19 detection and classification using chest X-Ray images. 2021. medRxiv Preprint. Source: https://www.medrxiv.org/content/10.1101/2021.08.11.212 61946v1. DOI: 10.1101/2021.08.11.21261946.
  • Nasiri H, Hasani S. Automated detection of COVID-19 cases from chest X-ray images using deep neural network and XGBoost. arXiv Preprint. 2021. Source: https://arxiv.org/abs/2109.02428. DOI: 10.48550/arXiv.2109.02428.
  • Katsamenis I, Protopapadakis E, Voulodimos A. Transfer learning for COVID-19 pneumonia detection and classification in chest X-ray images. medRxiv Preprint. 2020. Source: https://www.medrxiv.org/content/10.1101/2020.1 2.14.20248158v1. DOI: 10.1101/2020.12.14.20248158.
  • Shazia A, Xuan TZ, Chuah JH, Usman J, Qian P, Lai KW. A comparative study of multiple neural network for detection of COVID-19 on chest X-ray. EURASIP J Adv Signal Process 2021; 2021: 50. DOI: 10.1186/s13634-021-00755-1.
  • Narin A, Kaya C, Pamuk Z. Automatic detection of coro-navirus disease (COVID-19) using X-ray images and deep convolutional neural networks. Pattern Anal Appl 2021; 24: 1207-1220. DOI: 10.1007/s10044-021-00984-y.
  • Nasiri H, Alavi SA. A novel framework based on deep learning and ANOVA feature selection method for diagnosis of COVID-19 cases from chest X-ray Images. medRxiv Preprint. October 14, 2021. Source: https://www.medrxiv.org/content/10.1101/2021.10.10.212 64809v1. DOI: 10.1101/2021.10.10.21264809.
  • Shenoy V, Malik SB. CovXR: Automated detection of COVID-19 pneumonia in Chest X-Ray s through machine learning. arXiv Preprint. 2021. Source: https://arxiv.org/abs/2110.06398. DOI: 10.48550/arXiv.2110.06398.
  • Ilyas M, Rehman H, Nait-ali A. Detection of Covid-19 from chest X-ray images using artificial intelligence: an early review. arXiv Preprint. 2020. Source: https://arxiv.org/abs/2004.05436v1. DOI: 10.48550/arXiv.2004.05436.
  • Deng J, Dong W, Socher R, Li L, Li K, Li F-F. ImageNet: A large-scale hierarchical image database. 2009 IEEE Conference on Computer Vision and Pattern Recognition 2009: 248-255.
  • Chollet F. Deep learning with Python. Maning; 2017. ISBN: 978-1-61729-443-3.
  • Best N, Ott J, Linstead EJ. Exploring the efficiency of transfer learning in mining image-based software artifacts. J Big Data 2020; 7(1): 2-10. DOI: 10.1186/s40537-020-00335-4.
  • Shchetinin EYu, Sevastyanov LA, Kulyabov DS, Demidova AV, Ayrjan EA. Deep neural networks for emotion recognition. Lecture Notes in Computer Science 2020; 12563 LNCS: 365-379. DOI: 10.1007/978-3-030-66471-8_28.
  • Shchetinin EYu, Sevastianov LA, Demidova AV, Glushkova AG. Cardiac arrhythmia disorders detection with deep learning models. In Book: Vishnevskiy VM, Samouylov KE, Kozyrev DV, eds. Distributed computer and communication networks. Springer Nature Switzerland AG; 2022: 371-384. DOI: 10.1007/978-3-030-97110-6_29.
  • Geron A. Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow: Concepts, tools, and techniques to build intelligent systems, 2nd ed. O'Reilly Media; 2019. ISBN: 978-1-4920-3264-9.
  • Patel P. Chest X-ray (COVID-19 & Pneumonia). 2020. Source: (https://www.kaggle.com/prashant268/chest-xray-covid19-pneumonia).
  • Rahman T, et al. Exploring the effect of image enhancement techniques on COVID-19 detection using chest X-ray images. Comput Biol Med 2021; 132: 104319. DOI: 10.1016/j.compbiomed.2021.104319.
  • Sokolova M, Lapalme G. A systematic analysis of performance measures of classification tasks. Inf Process Manag 2009; 45(4): 427-437. DOI: 10.1016/j.ipm.2009.03.002.
  • Thrun S, Pratt L. Learning to learn. New York, NY: Springer; 2012. ISBN: 978-0-7923-8047-4.
  • Lin Y, Dai X, Li L, Wang X, Wang F. The new frontier of AI research: generative adversarial networks. Acta Autom Sin 2018; 44: 775-792. DOI: 10.16383/j.aas.2018.y000002.
Еще
Статья научная