Abstract
Computer-aided diagnosis (CAD) systems are useful in assisting radiologists with clinical diagnoses by classifying focal liver lesions based on computed tomography (CT) images. Extracting discriminative features from CT images is a crucial step in CAD systems. Although deep neural networks have demonstrated immense success in the computer vision community, there still remain two challenges in this field of medical image analysis. First, there are only limited dataset. Second, the local and global information of lesions both are necessary for this task. In this study, inspired by the importance of global and local information, we propose a novel model for distinguishing diverse types of focal liver lesions, called residual CNN with global and local pathways (ResNet-GL) model. The model uses both patches of lesion region (local information) and a whole-lesion region (global information) as inputs. Since the proposed ResNet-GL is a pixel-wise classification method (it assigns a label to each pixel of the lesion), we used the normalized label map produced by the ResNet-GL as an input of support vector machines (SVM) for classification of lesions. The effectiveness of our model is confirmed by the accuracy of our testing dataset, which is over 87%. Our results show that the proposed ResNet-GL model can not only achieves superior performance than state-of-the-art approaches, which are based on mid-level learning-based features, but also can achieve results better than other CNN-based approaches.
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
Ryerson, A.B., et al: Annual report to the nation on the status of cancer 1975–2012 featuring the increasing incidence of liver cancer. Cancer 122(9), 1312–1337 (2016)
Doron, Y., et al.: Texture feature based liver lesion classification. In: Medical Imaging 2014: Computer-Aided Diagnosis. 9035. International Society for Optics and Photonics (2014)
Yang, W.: Content-based retrieval of focal liver lesions using bag-of-visual-words representations of single-and multiphase contrast-enhanced CT images. J. Digit. Imaging 25(6), 708–719 (2012)
Diamant, I.: Improved patch-based automated liver lesion classification by separate analysis of the interior and boundary regions. IEEE J. Biomed. Health Inform. 20(6), 1585–1594 (2016)
Diamant, I., et al.: Multi-phase liver lesions classification using relevant visual words based on mutual information.In: IEEE 12th International Symposium on IEEE, pp. 407–410 (2015)
Xu, Y., et al.: Bag of temporal co-occurrence words for retrieval of focal liver lesions using 3D multiphase contrast-enhanced CT images. In: Proceedings of 23rd International Conference on Pattern Recognition (ICPR2016), pp. 2283–2288 (2016)
Xu, Y., et al.: Texture-specific bag of visual words model and spatial cone matching-based method for the retrieval of focal liver lesions using multiphase contrast-enhanced CT images. Int. J. Comput. Assist. Radiol. Surg. 13(1), 151–164 (2018)
Wang, J., et al.: Sparse codebook model of local structures for retrieval of focal liver lesions using multiphase medical images. Int. J. Biomed. Imaging 2017, 13 (2017)
Setio, A.: Pulmonary nodule detection in CT images: false positive reduction using multi-view convolutional networks. IEEE Trans. Med. Imaging 35(5), 1160–1169 (2016)
Yasaka, K.: Deep learning with convolutional neural network for differentiation of liver masses at dynamic contrast-enhanced CT: a preliminary study. Radiology 286(3), 887–896 (2017)
Frid-Adar, M., Diamant, I., Klang, E., Amitai, M., Goldberger, J., Greenspan, H.: Modeling the intra-class variability for liver lesion detection using a multi-class patch-based CNN. In: Wu, G., et al. (eds.) Patch-MI 2017. LNCS, vol. 10530, pp. 129–137. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-67434-6_15
Dong, C., et al.: Simultaneous segmentation of multiple organs using random walks. J. Inf. Process. 24(2), 320–329 (2016)
He, K., et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition (2016)
Dong, C.: Non-rigid image registration with anatomical structure constraint for assessing locoregional therapy of hepatocellular carcinoma. Comput. Med. Imaging Graph. 45, 75–83 (2015)
Acknowledgements
This work was supported in part by the National Key R&D Program of China under the Grant No. 2017YFB0309800, in part by the Key Science and Technology Innovation Support Program of Hangzhou under the Grant No. 20172011A038, and in part by the Grant-in Aid for Scientific Research from the Japanese Ministry for Education, Science, Culture and Sports (MEXT) under the Grant No. 18H03267 and No. 17H00754.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Liang, D. et al. (2018). Residual Convolutional Neural Networks with Global and Local Pathways for Classification of Focal Liver Lesions. In: Geng, X., Kang, BH. (eds) PRICAI 2018: Trends in Artificial Intelligence. PRICAI 2018. Lecture Notes in Computer Science(), vol 11012. Springer, Cham. https://doi.org/10.1007/978-3-319-97304-3_47
Download citation
DOI: https://doi.org/10.1007/978-3-319-97304-3_47
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-97303-6
Online ISBN: 978-3-319-97304-3
eBook Packages: Computer ScienceComputer Science (R0)