Abstract
The leading reason of death linked to cancer worldwide is lung cancer. To plan effective treatment, create monetary and care plans, early diagnosing of lung nodules in computed tomography (CT) chest scans must be performed. In this context, the purpose of this paper is to take into account the problem of classification between malignant and benign pulmonary nodules in CT scans, which aims to automatically map 3D nodules to category labels. Thus, we propose an ensemble learning approach based on three Convolutional Neural Networks including a basic 3D CNN, a 3D model inspired by AlexNet, and another 3D mod-el inspired by ResNet. The result from these CNNs is combined to estimate one result, using a fully-connected layer with a softmax activation. These CNNs are trained and evaluated on the LIDC-IDRI public dataset. The best result is obtained by the ensemble model, providing a larger AUC (84.66%); “area under the receiver operating characteristic curve” and 94.44% for TPR (sensitivity), with a data augmentation technique.
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
Similar content being viewed by others
References
Luís, G., Jorge, N., António, C., Aurélio, C.: Evaluation of the degree of malignancy of lung nodules in computed tomography images (2017)
National Lung Screening Trial Research Team et al.: Reduced lung-cancer mortality with low-dose computed tomographic screening. Natl. Engl. J. Med. 2011(365), 395–409 (2011)
Senthilkumar, K., Ganesh, N., Umamaheswari, R.: Three-dimensional lung nodule segmentation and shape variance analysis to detect lung cancer with reduced false positives. In: Proceedings of the Institution of Mechanical Engineers, vol. 230, no. 1, pp. 58–70, Journal of Engineering in Medicine (2016)
Ying, L., Yoganand, B., Thomas, A., Sanja, A., Qian, L., Ronald, C.W., Gary, S., Pierre, P.M., Matthew, B.S., Robert, J.G.: Radiological image traits predictive of cancer status in pulmonary nodules. In: Clinical Cancer Research, clincanres–3102 (2016).
Wei, S., Mu, Z., Feng, Y., Caiyun, Y., Jie, T.: Multi-scale convolutional neural networks for lung nodule classification. In: International Conference on Information Processing in Medical Imaging, pp. 588–599. Springer (2015)
Aiden, N., Zhen, H., Dennis, W.: Pulmonary nodule classification with deep residual networks. In: International Journal of Computer Assisted Radiology and Surgery, p. 10 (2017)
Kui, L., Guixia, K.: Multiview convolutional neural networks for lung nodule classification. Int. J. Imaging Syst. Technol. 27(1), 12–22 (2017)
Sarfaraz, H., Kunlin, C., Qi, S., Ulas, B.: Risk stratification of lung nodules using 3D CNN-based multi-task learning. In: International Conference on Information Processing in Medical Imaging, pp. 249–260. Springer (2017)
Hongtao, X., Dongbao, Y., Nannan, S., Zhineng, C., Yongdong, Z.: Automated pulm nary nodule detection in CT images using deep convolutional neural networks (2018).
Wentao, Z., Chaochun, L., Wei, F., Xiaohui, X.: DeepLung: deep 3D Dual Path Nets for Automated Pulmonary Nodule Detection and Classification. In: arXiv preprint arXiv:1709.05538 (2017)
Alex, K., Ilya, S., Geoffrey, E.H.: ImageNet classification with deep convolutional neural networks
Kaiming, H., Xiangyu, Z., Shaoqing, R., Jian, S.: Deep Residual Learning for Image Recognition
Anthony, P.R., Alberto, M.B.: The lung image database consortium (lidc) nodule size report, October. https://www.via.cornell.edu/lidc/
Chollet, F., et al.: Keras (2015.) https://github.com/keras-team/keras
Abadi, M., et al.: Large-scale machine learning on heterogeneous systems, 2015. Software available from https://www.tensorow.org/
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Elhoussaine, E., Salwa, B. (2021). Pulmonary Nodule Classification Based on Three Convolutional Neural Networks Models. In: Saeed, F., Mohammed, F., Al-Nahari, A. (eds) Innovative Systems for Intelligent Health Informatics. IRICT 2020. Lecture Notes on Data Engineering and Communications Technologies, vol 72. Springer, Cham. https://doi.org/10.1007/978-3-030-70713-2_13
Download citation
DOI: https://doi.org/10.1007/978-3-030-70713-2_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-70712-5
Online ISBN: 978-3-030-70713-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)