Abstract
The coronavirus disease 2019 (COVID-19) caused by a novel coronavirus, turned into a pandemic and raised a serious concern to the global healthcare system. The reverse transcription polymerase chain reaction (RT-PCR) is the most widely used diagnostic tool to detect COVID-19. However, this test is time consuming and subject to availability of the test kits during a crisis. An automated method of screening chest x-ray images using convolutional neural network (CNN) Transfer Learning approach has been proposed as a relatively fast and cost-effective, decision support tool to detect pulmonary pathology due to COVID-19. In this study we have used Kaggle dataset with chest x-ray images of normal and pneumonia cases. We have added COVID-19 x-ray images from 5 different open-source datasets. The images were pre-processed based on the position of radiography images and greyscale was applied and subsequently the images were used for training. After consolidation, COVID-19 images comprised only 5% of the dataset. To address the class imbalance, we have used dynamic image augmentation technique to reduce the bias. We have then explored custom CNN and VGG-16, InceptionNet-V3, MobileNet-V2, ResNet-50, and DarkNet-53 transfer learning approaches to classify COVID-19, other pneumonia and normal x-ray images and compared their performances. So far, we have achieved the best score of F1 score 0.95, sensitivity 95% and specificity 95% for COVID-19 class with Darknet-53 feature extractor. Darknet-53 classifier is part of the state-of-the-art object detection algorithm named Yolo-v3. We have also done a McNemar-Bowker post-hoc test to compare Darknet-53 performance with the next best ResNet-50. This test suggests that Darknet-53 is significantly better skilled than ResNet-50 in differentiating COVID-19 from other pneumonia in chest x-ray images.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Corman, V.M., et al.: others, Detection of 2019 novel coronavirus (2019-nCoV) by real-time RT-PCR. Eurosurveillance 25, 2000045 (2020)
Maguolo, G., Nanni, L.: A critic evaluation of methods for COVID-19 automatic detection from X-Ray images (2020). arXiv [eess.IV]
Narin, A., Kaya, C., Pamuk, Z.: Automatic detection of Coronavirus disease (COVID-19) using X-ray images and deep convolutional neural networks (2020). arXiv [eess.IV]
Ozturk, T., Talo, M., Yildirim, E.A., Baloglu, U.B., Yildirim, O., Rajendra Acharya, U.: Automated detection of COVID-19 cases using deep neural networks with X-ray images. Comput. Biol. Med. 121, 103792 (2020)
Cohen, J.P., Morrison, P., Dao, L., Roth, K., Duong, T.Q., Ghassemi, M.: COVID-19 Image Data Collection: Prospective Predictions Are the Future (2020). arXiv [q-bio.QM]
Wang, L., Lin, Z.Q., Wong, A.: COVID-Net: a tailored deep convolutional neural network design for detection of COVID-19 cases from chest X-ray images. Sci. Rep. 10(1), 19549 (2020)
Ng, M.-Y., et al.: Imaging profile of the COVID-19 infection: Radiologic findings and literature review. Radiol. Cardiothorac. Imaging. 2(1), 200034 (2020)
Abiyev, R.H., Maaitah, M.K.S.: Deep convolutional neural networks for chest diseases detection. J. Healthc. Eng. 2018, 1–11 (2018)
Shin, H.-C., et al.: Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE Trans. Med. Imaging 35(5), 1285–1298 (2016)
Redmon, J., Farhadi, A.: YOLOv3: An Incremental Improvement (2018). arXiv [cs.CV]
Convert Darknet-53 ImageNet weights and architecture from NVIDIA CUDA framework to Tensor Flow 2.0: Github repository - https://github.com/qqwweee/keras-yolo3
COVID-19 Image Data collection from Cohen et al.: [10] - https://github.com/ieee8023/covid-chestxray-dataset
COVID-19 datasets with Bounding box and Segmentation information: https://github.com/GeneralBlockchain
Kaggle RSNA Pneumonia detection challenge dataset: https://www.kaggle.com/c/rsna-pneumonia-detection-challenge
Data Source reference for Kaggle RSNA Pneumonia detection: https://nihcc.app.box.com/v/ChestXray-NIHCC
Figure 1 COVID-19 Chest X-ray Dataset Initiative - https://github.com/agchung/Figure1-COVID-chestxray-dataset
Actualmed COVID-19 Chest X-ray Dataset Initiative - https://github.com/agchung/Actualmed-COVID-chestxray-dataset
Italian Society of Medical and Interventional Radiology (SIRM). https://www.kaggle.com/tawsifurrahman/covid19-radiography-database
DarkNet-53 ImageNet weights in CUDA format. https://pjreddie.com/darknet/imagenet/#darknet53
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition (2014). arXiv [cs.CV]
Darapaneni, N., et al.: COVID 19 severity of pneumonia analysis using chest X rays. In: 2020 IEEE 15th International Conference on Industrial and Information Systems (ICIIS), pp. 381–386 (2020)
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition (2015). arXiv [cs.CV]
Dubey, R., Sen, K.K., Panda, S., Goyal, M., Menon, S.M., Arora, R.: Potential of Conventional Chest Radiography as a diagnostic and follow up imaging tool in COVID pandemic era Ejmcm.com. https://www.ejmcm.com/article_7273_4828eb9ff564ab3bc54bcfee5973b8b6.pdf. Accessed 10 Apr 2021
Ronneberger, O., Fischer, P., Brox, T.: U-Net: Convolutional Networks for Biomedical Image Segmentation (2015). arXiv [cs.CV]
Darapaneni, N., et al.: Inception C-net(IC-net): altered inception module for detection of covid-19 and pneumonia using chest X-rays. In: 2020 IEEE 15th International Conference on Industrial and Information Systems (ICIIS), pp. 393–398 (2020)
Albawi, S., Mohammed, T.A., Al-Zawi, S.: Understanding of a convolutional neural network. Int. Conf. Eng. Technol. (ICET) 2017, 1–6 (2017). https://doi.org/10.1109/ICEngTechnol.2017.8308186
Neuman, M.I., et al.: Variability in the interpretation of chest radiographs for the diagnosis of pneumonia in children. J. Hosp. Med. 7(4), 294–298 (2012)
Wikipedia reference for Evaluating McNemar test statistic. https://en.wikipedia.org/wiki/McNemar%27s_test
Reference book for Bowkers test – Basic Biostatistics for medical and Bio-Medical practioners (second edition) (2019). https://www.sciencedirect.com/book/9780128170847/basic-biostatistics-for-medical-and-biomedical-practitioners
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.-C.: MobileNetV2: Inverted residuals and linear bottlenecks (2018). arXiv [cs.CV]
Yolo-v3 author PJ Reddie’s website used for downloading DarkNet-53 weights. https://pjreddie.com/darknet/imagenet/#darknet53
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 IFIP International Federation for Information Processing
About this paper
Cite this paper
Darapaneni, N. et al. (2021). Deep Convolutional Neural Network (CNN) Design for Pathology Detection of COVID-19 in Chest X-Ray Images. In: Holzinger, A., Kieseberg, P., Tjoa, A.M., Weippl, E. (eds) Machine Learning and Knowledge Extraction. CD-MAKE 2021. Lecture Notes in Computer Science(), vol 12844. Springer, Cham. https://doi.org/10.1007/978-3-030-84060-0_14
Download citation
DOI: https://doi.org/10.1007/978-3-030-84060-0_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-84059-4
Online ISBN: 978-3-030-84060-0
eBook Packages: Computer ScienceComputer Science (R0)
