Liver Tumor Segmentation via State Space Modeling and Multi-Scale Detail Enhancement
DOI:
https://doi.org/10.54097/qd9dgg96Keywords:
Liver Tumor Segmentation, State-space Model, Multi-scale Feature EnhancementAbstract
Accurate liver tumor segmentation from CT images is challenging because tumors present blurred boundaries, irregular shapes, and substantial scale variation. To address these issues, we propose a liver tumor segmentation network that combines state-space modeling with multi-scale detail enhancement (SSMDENet). SSMDENet follows an encoder-decoder architecture and introduces a Global-Local Modeling (GLM) block as the basic feature extractor. Within GLM, the Spatial Dependency Modeling (SMD) module captures long-range spatial dependencies to encode global anatomical context, while the Multi-scale Feature Enhancement (MFE) module uses parallel depthwise convolutions and channel recalibration to strengthen local boundary and texture information. In this way, the proposed network jointly models global semantics and local details. Experiments on the LiTS2017 and 3DIRCADB-01 datasets demonstrate the effectiveness of the method. SSMDENet achieves Dice scores of 85.79% and 84.12% on LiTS2017 and 3DIRCADB-01, respectively, outperforming several representative segmentation methods. Ablation studies further confirm the complementary benefits of the SMD and MFE modules. These results indicate that SSMDENet is an effective and robust solution for liver tumor segmentation.
Downloads
References
[1] WEI D, JIANG Y, ZHOU X, et al. A review of advancements and challenges in liver segmentation[J]. Journal of Imaging, 2024, 10(8): 202. DOI: https://doi.org/10.3390/jimaging10080202
[2] WU C, CHEN Q, WANG H, et al. A review of deep learning approaches for multimodal image segmentation of liver cancer[J]. Journal of Applied Clinical Medical Physics, 2024, 25(12): e14540. DOI: https://doi.org/10.1002/acm2.14540
[3] MANJUNATH R, GOWDA Y. Automated segmentation of liver tumors from computed tomographic scans[J]. Journal of Liver Transplantation, 2024, 15: 100232. DOI: https://doi.org/10.1016/j.liver.2024.100232
[4] O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional Networks for Biomedical Image Segmentation,” in Proc. MICCAI, 2015, pp. 234-241. DOI: https://doi.org/10.1007/978-3-319-24574-4_28
[5] Z. Zhou, M. M. R. Siddiquee, N. Tajbakhsh, and J. Liang, “UNet++: A Nested U-Net Architecture for Medical Image Segmentation,” in Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, 2018, pp. 3-11. DOI: https://doi.org/10.1007/978-3-030-00889-5_1
[6] O. Oktay et al., “Attention U-Net: Learning Where to Look for the Pancreas,” arXiv:1804.03999, 2018.
[7] Z. Gu et al., “CE-Net: Context Encoder Network for 2D Medical Image Segmentation,” IEEE Transactions on Medical Imaging, vol. 38, no. 10, pp. 2281-2292, 2019. DOI: https://doi.org/10.1109/TMI.2019.2903562
[8] A. Gu and T. Dao, “Mamba: Linear-Time Sequence Modeling with Selective State Spaces,” arXiv:2312.00752, 2023.
[9] Y. Liu et al., “VMamba: Visual State Space Model,” arXiv:2401.10166, 2024.
[10] J. Ruan et al., “VM-UNet: Vision Mamba UNet for Medical Image Segmentation,” arXiv:2402.02491, 2024. DOI: https://doi.org/10.1145/3767748
[11] Z. Xing, T. Ye, Y. Yang, G. Liu, and L. Zhu, “SegMamba: Long-range Sequential Modeling Mamba for 3D Medical Image Segmentation,” in Proc. MICCAI, 2024. DOI: https://doi.org/10.1007/978-3-031-72111-3_54
[12] X. Li, H. Chen, X. Qi, Q. Dou, C.-W. Fu, and P.-A. Heng, “H-DenseUNet: Hybrid Densely Connected U-Net for Liver and Tumor Segmentation From CT Volumes,” IEEE Transactions on Medical Imaging, vol. 37, no. 12, pp. 2663-2674, 2018. DOI: https://doi.org/10.1109/TMI.2018.2845918
[13] J. Chen et al., “TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation,” arXiv:2102.04306, 2021.
[14] H. Wang, P. Cao, J. Wang, and O. R. Zaiane, “UCTransNet: Rethinking the Skip Connections in U-Net from a Channel-wise Perspective with Transformer,” in Proc. AAAI, 2022. DOI: https://doi.org/10.1609/aaai.v36i3.20144
[15] H. Cao et al., “Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation,” in Proc. ECCV Workshops, 2022. DOI: https://doi.org/10.1007/978-3-031-25066-8_9
[16] KONG L, DONG J, TANG J, et al. Efficient visual state space model for image deblurring[C]//Proceedings of the computer vision and pattern recognition conference. 2025: 12710-12719.
[17] KONG L, DONG J, TANG J, et al. Efficient visual state space model for image deblurring[C]//Proceedings of the computer vision and pattern recognition conference. 2025: 12710-12719. DOI: https://doi.org/10.1109/CVPR52734.2025.01186
[18] BILIC P, CHRIST P, LI H B, et al. The liver tumor segmentation benchmark (lits)[J]. Medical image analysis, 2023, 84: 102680.
[19] SOLER L, HOSTETTLER A, AGNUS V, et al. 3d image reconstruction for comparison of algorithm database[J].
[20] P. Lv, J. Wang, and H. Wang, “2.5D Lightweight RIU-Net for Automatic Liver and Tumor Segmentation from CT,” Biomedical Signal Processing and Control, vol. 75, p. 103567, 2022. DOI: https://doi.org/10.1016/j.bspc.2022.103567
[21] L. Hong, R. Wang, T. Lei, X. Du, and Y. Wan, “QAU-Net: Quartet Attention U-Net for Liver and Liver-Tumor Segmentation,” in Proc. IEEE International Conference on Multimedia and Expo (ICME), 2021, pp. 1-6. DOI: https://doi.org/10.1109/ICME51207.2021.9428427
[22] R. Singh et al., “FasNet: A Hybrid Deep Learning Model with Attention Mechanisms and Uncertainty Estimation for Liver Tumor Segmentation on LiTS17,” Scientific Reports, vol. 15, p. 17697, 2025. DOI: https://doi.org/10.1038/s41598-025-98427-9
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Academic Journal of Applied Sciences
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
