Abstract
One critical research area in the development of a computer-aided diagnosis system for liver cancer is efficient and automatic segmentation of lesion from CT scans. To overcome this issue, we investigated a 2.5D lightweight liver tumor segmentation by fusing the multi-scale semantic features, named MAA-Net. Our framework enhanced the information interaction between the input 2.5D stacked slice via introducing parallel convolution and increasing the knowledge weight of the lesion channel in different receptive fields. To ease the shortage of missed detection of tumors, MAA-Net fused the hierarchical semantic information extracted from the encoder. Moreover, we evaluated our MAA-Net on LiTS2017 and 3DIRCADb datasets. Extensive experiments shows the proposed method outperforms the others on both accuracy and total number of calculation. Specifically, our approach can improve liver tumor segmentation tasks by 2.4%, while reducing amount of parameters by 57.5%. Both quantitative and qualitative results illustrated the MAA-Net can effectively address with the limitation of small tumors, and some tumors are on the edge.
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
Long J., Shelhamer E., Darrell T.: Fully Convolutional Networks for Semantic Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence 39(4), 640–651 (2015).
Ronneberger O., Fischer P., Brox T.: U-Net: Convolutional Networks for Biomedical Image Segmentation. Springer, Cham, (2015).
Qiao W C., Hunag M.: Feature selection and residual fusion segmentation network for liver tumor. Journal of Image and Graphics, 27(03), 838–849 (2022). (in Chinese)
Jiang H., Shi T., Bai Z.,: AHC-Net: An Application of Attention Mechanism and Hybrid Connection for Liver Tumor Segmentation in CT Volumes. IEEE Access, 7, pp. 24898–24909 (2019). https://doi.org/10.1109/ACCESS.2019.2899608
Li X., Chen H., Qi X.: H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation From CT Volumes. IEEE Transactions on Medical Imaging, (2018). https://doi.org/https://doi.org/10.1109/tmi.2018.2845918
Wang Z.: Triplanar Convolutional Neural Network for Automatic Liver and Tumor Image Segmentation. International Journal of Performability Engineering 14(12) (2018). https://doi.org/10.23940/ijpe.18.12.p24.31513158
Dey R, Hong Y, Hybrid Cascaded Neural Network for Liver Lesion Segmentation. International Symposium on Biomedical Imaging. IEEE (2020). https://doi.org/https://doi.org/10.1109/ISBI45749.2020.9098656
Szegedy C., Vanhoucke V., Ioffe S.: Rethinking the Inception Architecture for Computer Vision. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2818–2826 (2016).
Guo N., Bai Z Y.: The integration of attention mechanism and dense atrous convolution for lung image segmentation. Journal of Image and Graphics, 26(09): 2146–2155(2021). (in Chinese)
Lv Peiqing, Wang Jinke, Wang Haiying. 2.5D lightweight RIU-Net for automatic liver and tumor segmentation from CT. Biomedical Signal Processing and Control, 75 (2022). https://doi.org/10.1016/j.bspc.2022.103567
He K M., Zhang X Y., Ren S Q and Sun J.: 2016. Deep residual learning for image recognition // Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA: IEEE: 770–778 (2016). [DOI: 10. 1109 / CVPR. 2016. 90]
Jie, Shen, Samuel, et al. Squeeze-and-Excitation Networks. IEEE transactions on pattern analysis and machine intelligence, (2019). https://doi.org/10.1109/tpami.2019.2913372
Woo S , Park J , Lee J Y , et al. CBAM: Convolutional Block Attention Module. Springer, Cham, (2018).
Wang Q, Wu B, Zhu P, et al. ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, (2020). https://doi.org/10.1109/CVPR42600.2020.01155
Li S D, Bai Z Y. Multiorgan lesion detection and segmentation based on deep learning. Journal of Image and Graphics, 26(11):2723–2731 (2021). (in Chinese)
Jl A., Bo D B., Shuai W C.: COVID-19 Lung Infection Segmentation with A Novel Two-Stage Cross-Domain Transfer Learning Framework. Medical Image Analysis, (2021). https://doi.org/10.1016/j.media.2021.102205
Wardhana G., Naghibi H., Sirmacek B.: Toward reliable automatic liver and tumor segmentation using convolutional neural network based on 2.5D models. International Journal of Computer Assisted Radiology and Surgery, 16(12), (2020). https://doi.org/10.1007/s11548-020-02292-y
Hou Q., Zhou D., Feng J.: Coordinate Attention for Efficient Mobile Network Design, (2021). https://doi.org/10.1109/CVPR46437.2021.01350
Bilic P., Christ P F., Vorontsov E.: The Liver Tumor Segmentation Benchmark (LiTS), (2019). https://doi.org/10.48550/arXiv.1901.04056
Soler L., Hostettler A., Agnus V.: 3D image reconstruction for comparison of algorithm database: A patient specific anatomical and medical image database. IRCAD, Strasbourg, France, Tech. Rep, (2010).
Jha D., Smedsrud P H., Riegler M A.: ResUNet++: An Advanced Architecture for Medical Image Segmentation. 21st IEEE International Symposium on Multimedia. IEEE, (2019). https://doi.org/10.1109/ISM46123.2019.00049
Oktay O., Schlemper J., Folgoc L L.: Attention U-Net: Learning Where to Look for the Pancreas. (2018). https://doi.org/10.48550/arXiv.1804.03999
Lei W., Mei H, Sun Z.: Automatic Segmentation of Organs-at-Risk from Head-and-Neck CT using Separable Convolutional Neural Network with Hard-Region-Weighted Loss. (2021). https://doi.org/10.1016/j.neucom.2021.01.135
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
You, Y., Bai, Z., Zhang, Y., Du, J. (2023). 2.5D Lightweight Network Integrating Multi-scale Semantic Features for Liver Tumor Segmentation. In: Su, R., Zhang, Y., Liu, H., F Frangi, A. (eds) Medical Imaging and Computer-Aided Diagnosis. MICAD 2022. Lecture Notes in Electrical Engineering, vol 810. Springer, Singapore. https://doi.org/10.1007/978-981-16-6775-6_14
Download citation
DOI: https://doi.org/10.1007/978-981-16-6775-6_14
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-6774-9
Online ISBN: 978-981-16-6775-6
eBook Packages: MedicineMedicine (R0)