Abstract
The risk of lung disease is immense for many people, especially in developing countries, where billions of people face energy poverty and are dependent on polluting forms of energy. The World Health Organization estimates that more than four million premature deaths occur each year from diseases related to household air pollution, including pneumonia. Radiologists diagnose and detect medical conditions with imaging techniques such as CT, MRI, and X-rays. However, they face many challenges interpreting chest radiographs in high workload conditions, even for highly experienced physicians. A tool for automatically locating and classifying anomalies would be of great value, and a deep learning approach provides several ways to achieve this goal. In this study, we train Faster R-CNN neural network for lung disease classification using the feature extraction networks such as ResNet, CheXnet, and Inception ResNet V2. The experiments are conducted on a dataset of 112,000 images with corresponding labels annotated by experienced radiologists. The experimental results show that the models can identify the exact lesion area for a given chest X-ray and the classification accuracy is up to 95.5%. The Grad-CAM is performed to highlight the lesion area thus reducing stress for physicians while providing patients with a more accurate diagnosis.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Girshick, R.: Fast r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440–1448 (2015)
Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580–587 (2014)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700–4708 (2017)
Jain, R., Nagrath, P., Kataria, G., Kaushik, V.S., Hemanth, D.J.: Pneumonia detection in chest x-ray images using convolutional neural networks and transfer learning. Measurement 165, 108046 (2020)
Pizer, S.M., et al.: Adaptive histogram equalization and its variations. Comput. Vision Graph. Image Process. 39(3), 355–368 (1987)
Rajpurkar, P., et al.: Chexnet: radiologist-level pneumonia detection on chest x-rays with deep learning. arXiv preprint arXiv:1711.05225 (2017)
Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst. 28 (2015)
Sarker, L., Islam, M.M., Hannan, T., Ahmed, Z.: Covid-densenet: a deep learning architecture to detect covid-19 from chest radiology images. Preprint 2020050151 (2020)
Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, inception-resnet and the impact of residual connections on learning. In: Thirty-First AAAI Conference on Artificial Intelligence (2017)
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818–2826 (2016)
Weiss, K., Khoshgoftaar, T.M., Wang, D.: A survey of transfer learning. J. Big Data 3(1), 1–40 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Phan, TC., Phan, AC., Tran, QT., Trieu, TN. (2022). Lung Lesions Segmentation and Classification with Deep Neural Networks. In: Dang, T.K., Küng, J., Chung, T.M. (eds) Future Data and Security Engineering. Big Data, Security and Privacy, Smart City and Industry 4.0 Applications. FDSE 2022. Communications in Computer and Information Science, vol 1688. Springer, Singapore. https://doi.org/10.1007/978-981-19-8069-5_45
Download citation
DOI: https://doi.org/10.1007/978-981-19-8069-5_45
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-8068-8
Online ISBN: 978-981-19-8069-5
eBook Packages: Computer ScienceComputer Science (R0)