Medical Image Segmentation Using SegResNet Integrated with Non-local Neural Networks

Jun Liao; Jing Zhang; Tingjie He; Yujie Zhang

doi:10.6919/ICJE.202601_12(1).0007

Authors

Jun Liao
Jing Zhang
Tingjie He
Yujie Zhang

DOI:

https://doi.org/10.6919/ICJE.202601_12(1).0007

Keywords:

Pancreas Segmentation; SegResNet; Medical Image Segmentation; CT Imaging.

Abstract

Pancreas segmentation is a challenging task in medical image analysis due to factors like ambiguous pancreatic boundaries and inter-individual variability. Current methods need improvement in balancing accuracy and efficiency. This study designs a lightweight pancreas segmentation model based on SegResNet, enhanced with Non-local Neural Networks. Trained on the Task07_Pancreas dataset, the model achieves a Dice coefficient of 91.51% and a Recall rate of 91.97% on the test set, with only 6.3M parameters. It outperforms advanced models such as UMambaEnc and UNETR, effectively balancing segmentation precision and computational efficiency.

Downloads

Download data is not yet available.

References

[1] R.L. Siegel, K.D. Miller and A. Jemal: Cancer Statistics, 2019, Ca: A Cancer Journal For Clinicians, Vol. 69 (2019) No.1, p.7-34.

[2] K. Karasawa, M. Oda, T. Kitasaka, et al.: Multi-Atlas Pancreas Segmentation: Atlas Selection Based On Vessel Structure, Medical Image Analysis, Vol. 39 (2017), p.18-28.

[3] T.D. Tam and N.T. Binh: Efficient Pancreas Segmentation in Computed Tomography Based on Region-Growing, Proc. International Conference on Nature of Computation and Communication (Springer, 2015), p.332-340.

[4] A. Farag, L. Lu, B. Turkbey, et al.: A Bottom-Up Approach for Automatic Pancreas Segmentation in Abdominal CT Scans, Proc. Abdominal Imaging. Computational and Clinical Applications: 6th International Workshop (Springer, 2014), p.103-113.

[5] O. Ronneberger, P. Fischer and T. Brox: U-Net: Convolutional Networks for Biomedical Image Segmentation, Proc. International Conference on Medical Image Computing and Computer-Assisted Intervention (Springer, 2015), p.234-241.

[6] O. Oktay, J. Schlemper, L.L. Folgoc, et al.: Attention U-Net: Learning Where to Look for the Pancreas, ArXiv Preprint ArXiv:1804.03999, (2018).

[7] E.Z. Xie, W.H. Wang, Z.D. Yu, et al.: SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers, Advances in Neural Information Processing Systems, Vol. 34 (2021), p.12077-12090.

[8] P.R. Liang, G.J. Xin and C.S. Ding: Pancreatic Image Segmentation Method Based on Improved SegFormer, Computer and Modernization, (2025) No.6, p.71-78.

[9] M. Antonelli, A. Reinke, S. Bakas, et al.: The Medical Segmentation Decathlon, ArXiv Preprint ArXiv:2106.05735, (2021).

[10] Z.T. Xiang, J.C. Liu, L. Wei, et al.: Pancreatic Image Segmentation Based on Global Feature U-Net, Journal of Chongqing University of Posts and Telecommunications (Natural Science Edition), Vol. 34 (2022) No.2, p.216-222.

[11] J.B. Ji, S. Chen and Y.Y. Yang: Pancreatic CT Segmentation Using Dual Dimensionality Reduction Channel Attention Gated U-Net, Chinese Journal of Biomedical Engineering, Vol. 42 (2023) No.3, p.281-288.

[12] B.Y. Zhou, G.J. Xin, H. Liang, et al.: Pancreatic Segmentation Based on Two-Stage Multi-Attention Mechanism Network, Computer and Modernization, (2025) No.10, p.67-72.

[13] H. Ma, Y. Liu and J.R. Zhang: Pancreatic Segmentation Based on Model Compression and Reconstruction U-Net, Computer Engineering and Design, Vol. 43 (2022) No.7, p.1998-2006.

[14] Information on: https://ai.googleblog.com/2020/12/transformers-for-image-recognitionat.html

[15] A. Hatamizadeh, Y. Tang, V. Nath, et al.: UNETR: Transformers for 3D Medical Image Segmentation, Proc. IEEE/CVF Winter Conference on Applications of Computer Vision (2022), p.1748–1758.

[16] A. Myronenko: 3D MRI Brain Tumor Segmentation Using Autoencoder Regularization, Proc. International MICCAI Brainlesion Workshop (Springer, Cham 2018), p.311-320.

[17] X. Wang, R. Girshick, A. Gupta, et al.: Non-Local Neural Networks, Proc. the IEEE Conference on Computer Vision and Pattern Recognition (2018), p.7794-7803.

[18] A. Hatamizadeh, V. Nath, Y. Tang, et al.: Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Images, Proc. International MICCAI Brainlesion Workshop (Cham: Springer International Publishing, 2021), p.272-284.

[19] J. Ma, F. Li and B. Wang: U-Mamba: Enhancing Long-Range Dependency for Biomedical Image Segmentation, ArXiv Preprint ArXiv:2401.04722, (2024).