Abstract
Aiming at the problem of poor medical image recognition accuracy caused by the large individual differences in liver pathological images and the large single feature size, a liver image classification method based on dual-channel recalibration and feature fusion is proposed. Firstly, we construct a dual-channel recalibration model based on attention mechanism, suppress useless features and calculate different feature channel weights, and embed them into the Inception_ResNet_V2 network structure. Secondly, we design fully connected layers on the basis of two-dimensional and three-dimensional convolutional neural networks, then add feature fusion layers to obtain deep semantic information in different dimensions. Finally, we use pre-training models to initialize the network structure and input the fused features into the XGBoost classifier for classification prediction. Experiments have been carried out with liver cancer race imaging datasets and a hospital patient dataset. Experimental results show that this method is superior to previous ones.
Keywords
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
Hessinger Née Reimann, C.: Dielectric contrast between normal and tumor ex-vivo human liver tissue. IEEE Access 164113–164119(2019)
Khosravan, N., Celik, H., Turkbey, B.: A collaborative computer aided diagnosis (C-CAD) system with eye-tracking, sparse attentional model, and deep learning. Med. Image Anal. 51, 101–115 (2019)
Liu, L., Long, Y., Fieguth, P.W.: BRINT: binary rotation invariant and noise tolerant texture classification. IEEE Trans Image Process 23(7), 3071–3084 (2014)
Ramamoorthy, S., Kirubakaran, R., Subramanian, R.S.: Texture feature extraction using mgrlbp method for medical image classification. In: Suresh, L.P., Dash, S.S., Panigrahi, B.K. (eds.) Artificial Intelligence and Evolutionary Algorithms in Engineering Systems. AISC, vol. 324, pp. 747–753. Springer, New Delhi (2015). https://doi.org/10.1007/978-81-322-2126-5_80
Bacciu, D., Crecchi, F.: Augmenting recurrent neural networks resilience by dropout. IEEE Trans. Neural Netw. Learn. Syst. 31, 345–351 (2020)
Zhu, F., Zhu, B., Li, P., Wang, Z., Wei, L.: Quantitative analysis and identification of liver B-scan ultrasonic image based on BP neural network. In: 2013 International Conference on Optoelectronics and Microelectronics (ICOM), pp. 62–66 (2013)
Romero, F.P.: End-to-end discriminative deep network for liver lesion classification. In: 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), pp. 1243–1246(2019)
Szegedy, C., Vanhoucke, V., Ioffe, S.: Rethinking the Inception Architecture for Computer Vision. 32, 2818–2826 (2016)
Xie, X., Cai, X., Zhou, J., Cao, N.: A semantic-based method for visualizing large image collections. IEEE Trans. Vis. Comput. Graph. 25, 2362–2377 (2019)
Chen, S., Sun, W., Huang, L.: Compressing fully connected layers using Kronecker tensor decomposition. In: 2019 IEEE 7th International Conference on Computer Science and Network Technology (ICCSNT), pp. 308–312 (2019)
Zheng, J., Wu, Y., Song, W.: Multi-scale feature channel attention generative adversarial network for face sketch synthesis. IEEE Access 8, 146754–146769 (2020)
Zhang, D.: clcNet: improving the efficiency of convolutional neural network using channel local convolutions. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7912–7919 (2018)
Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7132–7141 (2018)
Hara, K., Kataoka, H., Satoh, Y.: Can spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet? In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6546–6555 (2018)
Chiu, M.T.: Agriculture-vision: a large aerial image database for agricultural pattern analysis. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2825–2835(2020)
Amin, S.U., Alsulaiman, M., Muhammad, G.A.M.: Multilevel weighted feature fusion using convolutional neural networks for EEG motor imagery classification. IEEE Access 7, 18940–18950 (2019)
Gong, H., Zhang, H., Zhou, L.: An interpretable artificial intelligence model of chinese medicine treatment based on XGBoost algorithm. In: 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pp. 1550–1554 (2020)
Gu, K., Tao, D., Qiao, J.: Learning a no-reference quality assessment model of enhanced images with big data. IEEE Trans. Neural Netw. Learn. Syst. 29, 1301–1313 (2018)
Udhayakumar, R.K., Karmakar, C., Palaniswami, M.: Cross entropy profiling to test pattern synchrony in short-term signals. In: 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 737–740 (2019)
Xia, Y., Cai, M., Ni, C.: A switch state recognition method based on improved VGG19 network. In: 2019 IEEE 4th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC), pp. 1658–1662 (2019)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Niu, T., Zhang, X., Deng, C., Chen, R. (2021). Dual-Channel Recalibration and Feature Fusion Method for Liver Image Classification. In: Huang, DS., Jo, KH., Li, J., Gribova, V., Hussain, A. (eds) Intelligent Computing Theories and Application. ICIC 2021. Lecture Notes in Computer Science(), vol 12837. Springer, Cham. https://doi.org/10.1007/978-3-030-84529-2_49
Download citation
DOI: https://doi.org/10.1007/978-3-030-84529-2_49
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-84528-5
Online ISBN: 978-3-030-84529-2
eBook Packages: Computer ScienceComputer Science (R0)