Enhancing Liver Segmentation: A Deep Learning Approach with EAS Feature Extraction and Multi-Scale Fusion

Weimin Wang; Yufeng Li; Xu Yan; Mingxuan Xiao; Min Gao

Abstract

Deep learning technology have been broadly used in segmentation tasks of liver. To address the limitation of suboptimal segmentation for small targets, an end-to-end EAS(ECA-Attention and Separable convolution) U-Net is proposed based on deep learning. The basic module employs depthwise separable convolutional modules instead of convolutional modules to reduce the parameters count and enhance the extraction of deep-layer information. The pyramid module based on Efficient Channel Attention (ECA) is utilized to obtain different receptive fields. And that model can overcome the limitation of the U-Net model with a single receptive field and improve the segmentation capability for targets of different sizes. A deep supervision module with multi-scale output fusion is designed to extract detailed information about liver with high quality. The proposed method is tested on the Liver Tumor Segmentation (LiTS) dataset for liver segmentation, achieving a Dice Similarity Coefficient (DSC) of 92.20% for liver segmentation. Compared to existing models, the proposed method demonstrates higher accuracy in liver segmentation.

Keywords

Liver Segmentation, Deep Learning, CT Images, EAS, Liver Tumor Segmentation Dataset

References

1. J Ferlay, HR Shin, F Bray, D Forman, C Mathers, and DM Parkin. Estimates of worldwide burden of cancer in 2008: Globocan 2008. International Journal of Cancer, 127:2893–2917, 2010.

2. Mu¨ller S A, Maier-Hein L, Mehrabi A, Pianka F, Rietdorf U, Wolf I, Grenacher L, Richter G, Gutt C N, Schmidt J, Meinzer H P, and Schmied B M. Creation and establishment of a respiratory liver motion simulator for liver interventions. Medical Physics, 34:4605–4608, 2007.

3. Dou Qi, Chen Hao, Jin Yueming, Yu Lequan, Qin Jing, and Pheng-Ann Heng. 3d deeply supervised network for automatic liver segmentation from ct volumes. International Conference on Medical Image Computing and Computer-Assisted Intervention, Athens, 17-21 October 2016:149–157, 2016.

4. J Long, E Shelhamer, and T Darrell. Fully convolutional net-works for semantic segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39:640–651, 2015.

5. Ronneberger Olaf, Fischer Philipp, and Thomas Brox. U-net: Convolutional networks for biomedical image segmentation. Medical Image Computing and Computer-Assisted Intervention— MICCAI 2015, Springer, Cham:234–241, 2015.

6. F. Milletari, N. Navab, and S.A. Ahmadi. V-net: Fully convolutional neural networks for volumetric medical image segmentation. In 2016 Fourth International Conference on 3D Vision (3DV), pages 565–571, Stanford, October 2016.

7. K.M. He, X.Y. Zhang, S.Q. Ren, and J. Sun. Deep residual learning for image recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, pages 770–778, Las Vegas, June 2016.

8. X. Li, C. Hao, X. Qi, D. Qi, C.W. Fu, and H. Pheng-Ann. H-denseunet: Hybrid densely connected unet for liver and liver tumor segmentation from ct volumes. IEEE Transactions on Medical Imaging, 37:2663–2674, 2017.

9. X. Han. Automatic liver lesion segmentation using a deep convolutional neural network method. ArXiv preprint, 2017. arXiv:1704.07239.

10. Q. Jin, Z. Meng, C. Sun, L. Wei, and R. Su. Ra-unet: A hybrid deep attentionaware network to extract liver and tumor in ct scans, 2018.

11. Howard Andrew G, Zhu Menglong, Chen Bo, and et al. Mobilenets: Efficient convolutional neural networks for mobile vision applications. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, 21-26 July 2017:1382–1391, 2017.

12. Maas Andrew L, Hannun Awni Y, and Ng Andrew Y. Rectifier nonlinearities improve neural network acoustic models. Proceedings of the 30th International Conference on Machine Learning, 2013.

13. Chen Liang-Chieh, Zhu Yukun, Papandreou George, Schroff Florian, and Adam Hartwig. Encoder-decoder with atrous separable convolution for semantic image segmentation. European Conference on Computer Vision (ECCV), Springer, Cham:833–851, 2018.

14. Wang Qilong, Wu Banggu, Zhu Pengfei, Li Peihua, Zuo Wangmeng, and Qinghua Hu. Eca-net: Efficient channel attention for deep convolutional neural networks. CVPR 2020, 2019.

15. Wei LU, Dan LIU, Min SHAO, and Yangdong WU. Improved mask r-cnn multitarget detection and segmentation for autonomous driving in complex scenes. Journal of Computer Engineering & Applications, 2021, Vol 57, Issue 24:p234, 2023.

16. Bilic Patrick, Christ Patrick, Bran Li Hongwei, Eugene Vorontsov, and et al. The liver tumor segmentation benchmark (lits). Medical Image Analysis (2022), page Pg. 102680, 2019.

17. H YANG, T LI, and X CHEN. Visualization of time series data based on spiral graph. Journal of Computer Applications, 2017.

Cites this article as

W. Wang, Y. Li, X. Yan, M. Xiao, M. Gao, "Enhancing Liver Segmentation: A Deep Learning Approach with EAS Feature Extraction and Multi-Scale Fusion", International Journal of Innovative Research in Computer Science and Technology (IJIRCST), Vol-12, no.1, pp.26-34, 2024. Available from: https://doi.org/10.55524/ijircst.2024.12.1.6

Corresponding Author

Weimin Wang

Hong Kong University of Science and Technology, HONG KONG, China

Download Full Paper

Download PDF

No. of Downloads: 46 | No. of Views: 618

A Review on Compressed Sensing Space-Time Frequency Index Modulation in OFDM System

Sarita Yadav, Ashish Nema, Jitendra Kumar Mishra.

March 2019 - Vol 7, Issue 2
Promoters of Dengue Virus Complete Genome

Md. Zakir Hossain, Milton K. Debnath, Ishita R. Das, Anita L. Jackson, Rozina Akte.

May 2018 - Vol 6, Issue 3

IJIRCST

Enhancing Liver Segmentation: A Deep Learning Approach with EAS Feature Extraction and Multi-Scale Fusion

Citations

Download Full Paper PDF

Total View 618

Total Download 46