Abstract
A pulmonary nodule classification method of Computer Tomography (CT) images based on transfer learning of deep convolutional neural network (CNN) is proposed. Lung CT images with labels are quite limited compared with the large scale image database such as ImageNet. It is easy to produce over-fitting problem when using the limited data to train the deep CNN for classification task. In this paper, in order to overcome this difficulty, the deep CNNs GoogleNet and ResNet are pre-trained on the large scale database ImageNet. The fully connected layers and the classifiers of the pre-trained networks are replaced to complete the classification of CT images of pulmonary nodules. A sub set of the Lung Image Database Consortium image collection (LIDC-IDRI) is used to fine-tune the network and validate the classification accuracy. This is the process of transfer learning. It solves the problem of the deficiency of lung CT images as labeled training data for CNNs. By the knowledge obtained from the pre-trained CNNs which have been trained on ImageNet, the network is easier to converge and the training time is greatly reduced. The classification accuracy of Pulmonary Nodules can be reached up to 71.88% by using the proposed method.
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
American Cancer Society: Cancer Facts and Figures 2016. American Cancer Society, Atlanta (2016)
Diciotti, S., Picozzi, G., Falchini, M., Mascalchi, M., Villari, N.: 3-D segmentation algorithm of small lung nodules in spiral CT Images. IEEE Trans. Inf. Technol. Biomed. 12(1), 7–19 (2008)
Wang, Y., Zhou, T., Lu, H., Wu, C., Yang, P.: Computer aided diagnosis model for lung tumor based on ensemble convolutional neural network. J. Biomed. Eng. 4(34), 543–551 (2017)
Hinton, G.E., Srivastava, N., Krizhevsky, A.: Improving neural networks by preventing co-adaption of feature detectors, pp. 1–18. arXiv:1207.0580 [cs.NE] (2012)
Szegedy, C., Liu, W., Jia, Y.: Going deeper with convolutions. In: Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8. IEEE Computer Society, Washington (2015)
He, K., Zhang, X., Ren, S.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, United States, pp. 770–778 (2016)
Zhuang, F., Luo, P., He, Q., Shi, Z.: Survey on transfer learning research. J. Softw. 26(1), 26–39 (2015)
Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 818–833. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10590-1_53
Zhou, B., Lapedriza, A., Xiao, J.: Learning deep features for scene recognition using places database. In: Proceedings of Advances in Neural Information Processing Systems, pp. 487–495. MIT Press, Cambridge (2014)
ImageNet Homepage. http://www.image-net.org. Accessed 8 July 2018
Canziani, A., Paszke, A., Culurciello, E.: An analysis of deep neural network models for practical applications, pp. 1–7. arXiv:1605.07678 [cs.CV] (2016)
Razavian, S., Azizpor, H., Sullivan, J.: CNN features off-the-shelf: an astounding baseline for recognition, pp. 1–8. arXiv:1403.6382 [cs.CV] (2014)
LIDC-IDRI Collection. https://wiki.cancerimagingarchive.net/display/Public/LIDC-IDRI. Accessed 4 Aug 2018
Acknowledgment
This work is supported by the Basic Scientific Research Operating Expense Project of Provincial Institutions of Higher Education in Heilongjiang (17XN003); the Doctoral Research Startup Project of Harbin University of Commerce (2016BS28); and the Humanities and Social Sciences Research Projects of the Ministry of Education (18YJAZH128).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Wang, R., Sun, H., Zhang, J., Zhao, Z. (2019). A Transfer Learning Method for CT Image Classification of Pulmonary Nodules. In: Jia, M., Guo, Q., Meng, W. (eds) Wireless and Satellite Systems. WiSATS 2019. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 281. Springer, Cham. https://doi.org/10.1007/978-3-030-19156-6_15
Download citation
DOI: https://doi.org/10.1007/978-3-030-19156-6_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-19155-9
Online ISBN: 978-3-030-19156-6
eBook Packages: Computer ScienceComputer Science (R0)