U-Net网络在肝脏肿瘤CT图像分割应用综述
Comprehensive Review on the Application of U-Net Architecture for Hepatic Neoplasm Segmentation in Computed Tomography Imaging
DOI: 10.12677/acm.2025.1551519, PDF,    科研立项经费支持
作者: 陆 韬, 张允劼, 吴雨晗, 王雪景, 蔡忠昊, 樊 邵, 徐晓燕*：皖南医学院医学影像学院医学影像学实验实训中心，安徽 芜湖
关键词: 深度学习；U-Net；医学图像处理；肝脏肿瘤分割；Deep Learning； U-Net； Medical Imaging Processing； Hepatic Neoplasm Segmentation
摘要: 肝脏肿瘤(Hepatic Neoplasm)作为全球公共卫生领域的重大威胁，其发病率与致死率持续攀升的态势亟需精准诊疗技术的突破。在多种计算机断层扫描(computed tomography, CT)图像进行肝脏及肝脏肿瘤分割的深度学习(Deep Learning, DL)方案对比中，U-Net及其变种表现较优秀。为此，本文对近年来U-Net在肝脏及肝脏肿瘤CT图像分割中的应用以及具体优化方法进行了归纳，对比分析不同模型间的优劣并提出可能的发展方向，以期为进一步研究提供参考。
Abstract: Hepatic neoplasm pose a significant global public health threat, with their persistently rising incidence and mortality rates necessitating breakthroughs in precise diagnostic and therapeutic technologies. Among deep learning (DL) solutions for liver and hepatic neoplasm segmentation in computed tomography (CT) images, U-Net and its variants demonstrate relatively superior performance. To this end, this paper provides a summary of the applications of U-Net in the segmentation of liver and hepatic neoplasm CT images in recent years, as well as specific optimization methods. It compares and analyzes the strengths and weaknesses of different models and proposes potential directions for future development, with the aim of providing a reference for further research.
文章引用：陆韬, 张允劼, 吴雨晗, 王雪景, 蔡忠昊, 樊邵, 徐晓燕. U-Net网络在肝脏肿瘤CT图像分割应用综述[J]. 临床医学进展, 2025, 15(5): 1495-1505. https://doi.org/10.12677/acm.2025.1551519

参考文献

[1] Ciresan, D., Giusti, A., Gambardella, L., et al. (2012) Deep Neural Networks Segment Neuronal Membranes in Electron Microscopy Images. Advances in Neural Information Processing Systems, Lake Tahoe, 3-6 December 2012, 2843-2851.
[2] Sutskever, I., Martens, J. and Hinton, G.E. (2016) Generating Text with Recurrent Neural Networks. Proceedings of International Conference on Machine Learning, Bellevue, 19-24 June 2016, 1017-1024.
[3] Ronneberger, O., Fischer, P. and Brox, T. (2015) U-Net: Convolutional Networks for Biomedical Image Segmentation. In: Navab, N., Hornegger, J., Wells, W. and Frangi, A., Eds., Medical Image Computing and Computer-Assisted Intervention—MICCAI 2015, Springer, 234-241. [Google Scholar] [CrossRef] 
[4] 张欢, 刘静, 冯毅博, 等. U-Net及其在肝脏和肝脏肿瘤分割中的应用综述[J]. 计算机工程与应用, 2022, 58(2): 1-14.
[5] Wehrend, J., Silosky, M., Xing, F. and Chin, B.B. (2021) Automated Liver Lesion Detection in 68Ga DOTATATE PET/CT Using a Deep Fully Convolutional Neural Network. EJNMMI Research, 11, Article No. 98. [Google Scholar] [CrossRef] [PubMed]
[6] Wang, J., Lv, P., Wang, H. and Shi, C. (2021) Sar-U-Net: Squeeze-And-Excitation Block and Atrous Spatial Pyramid Pooling Based Residual U-Net for Automatic Liver Segmentation in Computed Tomography. Computer Methods and Programs in Biomedicine, 208, Article ID: 106268. [Google Scholar] [CrossRef] [PubMed]
[7] Liu, J., Yan, Z., Zhou, C., Shao, L., Han, Y. and Song, Y. (2023) mfeeU-Net: A Multi-Scale Feature Extraction and Enhancement U-Net for Automatic Liver Segmentation from CT Images. Mathematical Biosciences and Engineering, 20, 7784-7801. [Google Scholar] [CrossRef] [PubMed]
[8] Wu, J., Zhou, S., Zuo, S., Chen, Y., Sun, W., Luo, J., et al. (2021) U-Net Combined with Multi-Scale Attention Mechanism for Liver Segmentation in CT Images. BMC Medical Informatics and Decision Making, 21, Article No. 283. [Google Scholar] [CrossRef] [PubMed]
[9] Chen, Y., Zheng, C., Zhou, T., Feng, L., Liu, L., Zeng, Q., et al. (2023) A Deep Residual Attention-Based U-Net with a Biplane Joint Method for Liver Segmentation from CT Scans. Computers in Biology and Medicine, 152, Article ID: 106421. [Google Scholar] [CrossRef] [PubMed]
[10] Ayalew, Y.A., Fante, K.A. and Mohammed, M.A. (2021) Modified U-Net for Liver Cancer Segmentation from Computed Tomography Images with a New Class Balancing Method. BMC Biomedical Engineering, 3, Article No. 4. [Google Scholar] [CrossRef] [PubMed]
[11] Özcan, F., Uçan, O., Karaçam, S. and Tunçman, D. (2023) Fully Automatic Liver and Tumor Segmentation from CT Image Using an Aim-UNet. Bioengineering, 10, Article 215. [Google Scholar] [CrossRef] [PubMed]
[12] Jiang, L., Ou, J., Liu, R., Zou, Y., Xie, T., Xiao, H., et al. (2023) RMAU-Net: Residual Multi-Scale Attention U-Net for Liver and Tumor Segmentation in CT Images. Computers in Biology and Medicine, 158, Article ID: 106838. [Google Scholar] [CrossRef] [PubMed]
[13] Wang, F., Cheng, X., Luo, N. and Su, D. (2024) Attention-Guided Context Asymmetric Fusion Networks for the Liver Tumor Segmentation of Computed Tomography Images. Quantitative Imaging in Medicine and Surgery, 14, 4825-4839. [Google Scholar] [CrossRef] [PubMed]
[14] Wang, Z., Zou, Y. and Liu, P.X. (2021) Hybrid Dilation and Attention Residual U-Net for Medical Image Segmentation. Computers in Biology and Medicine, 134, Article ID: 104449. [Google Scholar] [CrossRef] [PubMed]
[15] Liu, H., Fu, Y., Zhang, S., Liu, J., Wang, Y., Wang, G., et al. (2023) GCHA-Net: Global Context and Hybrid Attention Network for Automatic Liver Segmentation. Computers in Biology and Medicine, 152, Article ID: 106352. [Google Scholar] [CrossRef] [PubMed]
[16] Hettihewa, K., Kobchaisawat, T., Tanpowpong, N. and Chalidabhongse, T.H. (2023) Manet: A Multi-Attention Network for Automatic Liver Tumor Segmentation in Computed Tomography (CT) Imaging. Scientific Reports, 13, Article No. 20098. [Google Scholar] [CrossRef] [PubMed]
[17] Saumiya, S. and Franklin, S.W. (2023) Residual Deformable Split Channel and Spatial U-Net for Automated Liver and Liver Tumour Segmentation. Journal of Digital Imaging, 36, 2164-2178. [Google Scholar] [CrossRef] [PubMed]
[18] Ester, O., Hörst, F., Seibold, C., Keyl, J., Ting, S., Vasileiadis, N., et al. (2023) Valuing Vicinity: Memory Attention Framework for Context-Based Semantic Segmentation in Histopathology. Computerized Medical Imaging and Graphics, 107, Article ID: 102238. [Google Scholar] [CrossRef] [PubMed]
[19] Gupta, A.C., Cazoulat, G., Al Taie, M., Yedururi, S., Rigaud, B., Castelo, A., et al. (2024) Fully Automated Deep Learning Based Auto-Contouring of Liver Segments and Spleen on Contrast-Enhanced CT Images. Scientific Reports, 14, Article No. 4678. [Google Scholar] [CrossRef] [PubMed]
[20] Lv, P., Wang, J., Zhang, X., Ji, C., Zhou, L. and Wang, H. (2021) An Improved Residual U-Net with Morphological-Based Loss Function for Automatic Liver Segmentation in Computed Tomography. Mathematical Biosciences and Engineering, 19, 1426-1447. [Google Scholar] [CrossRef] [PubMed]
[21] Chen, Y., Hu, F., Wang, Y. and Zheng, C. (2022) Hybrid‐Attention Densely Connected U‐net with GAP for Extracting Livers from CT Volumes. Medical Physics, 49, 1015-1033. [Google Scholar] [CrossRef] [PubMed]
[22] Li, L. and Ma, H. (2022) Rdctrans U-Net: A Hybrid Variable Architecture for Liver CT Image Segmentation. Sensors, 22, Article 2452. [Google Scholar] [CrossRef] [PubMed]
[23] Guo, X., Wang, Z., Wu, P., Li, Y., Alsaadi, F.E. and Zeng, N. (2024) ELTS-Net: An Enhanced Liver Tumor Segmentation Network with Augmented Receptive Field and Global Contextual Information. Computers in Biology and Medicine, 169, Article ID: 107879. [Google Scholar] [CrossRef] [PubMed]
[24] 王国刚, 李泽欣, 董志豪. 基于注意力机制和多空间金字塔池化的实时目标检测算法[J]. 计算机测量与控制, 2024, 32(2): 56-64.
[25] Song, Z., Wu, H., Chen, W. and Slowik, A. (2024) Improving Automatic Segmentation of Liver Tumor Images Using a Deep Learning Model. Heliyon, 10, e28538. [Google Scholar] [CrossRef] [PubMed]
[26] Gao, Q. and Almekkawy, M. (2021) ASU-Net++: A Nested U-Net with Adaptive Feature Extractions for Liver Tumor Segmentation. Computers in Biology and Medicine, 136, Article ID: 104688. [Google Scholar] [CrossRef] [PubMed]
[27] Lee, Z., Qi, S., Fan, C., Xie, Z. and Meng, J. (2022) RA V-Net: Deep Learning Network for Automated Liver Segmentation. Physics in Medicine & Biology, 67, Article ID: 125022. [Google Scholar] [CrossRef] [PubMed]
[28] Sun, L., Jiang, L., Wang, M., Wang, Z. and Xin, Y. (2024) A Multi-Scale Liver Tumor Segmentation Method Based on Residual and Hybrid Attention Enhanced Network with Contextual Integration. Sensors, 24, Article 5845. [Google Scholar] [CrossRef] [PubMed]
[29] Sheela, K.S., Justus, V., Asaad, R.R. and Kumar, R.L. (2025) Enhancing Liver Tumor Segmentation with UNet-Resnet: Leveraging Resnet’s Power. Technology and Health Care, 33, 1-15. [Google Scholar] [CrossRef] [PubMed]
[30] Li, Q., Song, H., Wei, Z., Yang, F., Fan, J., Ai, D., et al. (2023) Densely Connected U-Net with Criss-Cross Attention for Automatic Liver Tumor Segmentation in CT Images. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 20, 3399-3410. [Google Scholar] [CrossRef] [PubMed]
[31] Li, R., Xu, L., Xie, K., Song, J., Ma, X., Chang, L., et al. (2023) DHT-Net: Dynamic Hierarchical Transformer Network for Liver and Tumor Segmentation. IEEE Journal of Biomedical and Health Informatics, 27, 3443-3454. [Google Scholar] [CrossRef] [PubMed]
[32] 魏公正. 基于改进V-Net的3D医学图像分割方法研究[D]: [硕士学位论文]. 北京: 北京化工大学, 2023.
[33] Sahli, H., Ben Slama, A. and Labidi, S. (2022) U-Net: A Valuable Encoder-Decoder Architecture for Liver Tumors Segmentation in CT Images. Journal of X-Ray Science and Technology, 30, 45-56. [Google Scholar] [CrossRef] [PubMed]
[34] Park, S., Kim, J.H., Kim, J., Joseph, W., Lee, D. and Park, S.J. (2022) Development of a Deep Learning-Based Auto-Segmentation Algorithm for Hepatocellular Carcinoma (HCC) and Application to Predict Microvascular Invasion of HCC Using CT Texture Analysis: Preliminary Results. Acta Radiologica, 64, 907-917. [Google Scholar] [CrossRef] [PubMed]
[35] Vo, V.T., Yang, H.J., Lee, G.S., Kang, S.R. and Kim, S.H. (2021) Effects of Multiple Filters on Liver Tumor Segmentation from CT Images. Frontiers in Oncology, 11, Article 697178.
[36] Shao, H., Huang, X., Folkert, M.R., Wang, J. and Zhang, Y. (2021) Automatic Liver Tumor Localization Using Deep Learning‐Based Liver Boundary Motion Estimation and Biomechanical Modeling (DL‐BIO). Medical Physics, 48, 7790-7805. [Google Scholar] [CrossRef] [PubMed]
[37] Lee, I., Tsai, Y., Lin, Y., Chen, T., Yen, C., Chiu, N., et al. (2024) A Hierarchical Fusion Strategy of Deep Learning Networks for Detection and Segmentation of Hepatocellular Carcinoma from Computed Tomography Images. Cancer Imaging, 24, Article No. 43. [Google Scholar] [CrossRef] [PubMed]
[38] Christ, P.F., Elshaer, M.E.A., Ettlinger, F., Tatavarty, S., Bickel, M., Bilic, P., et al. (2016) Automatic Liver and Lesion Segmentation in CT Using Cascaded Fully Convolutional Neural Networks and 3D Conditional Random Fields. In: Ourselin, S., Joskowicz, L., Sabuncu, M., Unal, G. and Wells, W., Eds., Medical Image Computing and Computer-Assisted Intervention—MICCAI 2016, Springer, 415-423. [Google Scholar] [CrossRef] 
[39] He, K., Liu, X., Shahzad, R., Reimer, R., Thiele, F., Niehoff, J., et al. (2021) Advanced Deep Learning Approach to Automatically Segment Malignant Tumors and Ablation Zone in the Liver with Contrast-Enhanced CT. Frontiers in Oncology, 11, Article 669437. [Google Scholar] [CrossRef] [PubMed]
[40] 刘云鹏, 刘光品, 王仁芳, 等. 深度学习结合影像组学的肝脏肿瘤CT分割[J]. 中国图象图形学报, 2020, 25(10): 2128-2141.
[41] Xu, C., Hu, D., Zhang, Y. and Pang, Y. (2021) Study on the Segmentation Method of Multi-Phase CT Liver Tumor Based on Dual Channel U-Nets. Journal of Physics: Conference Series, 1828, Article ID: 012043. [Google Scholar] [CrossRef] 
[42] Wu, Y., Shen, H., Tan, Y. and Shi, Y. (2022) Automatic Liver Tumor Segmentation Used the Cascade Multi-Scale Attention Architecture Method Based on 3D U-Net. International Journal of Computer Assisted Radiology and Surgery, 17, 1915-1922. [Google Scholar] [CrossRef] [PubMed]
[43] Chen, Y., Zheng, C., Hu, F., Zhou, T., Feng, L., Xu, G., et al. (2022) Efficient Two-Step Liver and Tumour Segmentation on Abdominal CT via Deep Learning and a Conditional Random Field. Computers in Biology and Medicine, 150, Article ID: 106076. [Google Scholar] [CrossRef] [PubMed]
[44] Vorontsov, E., Tang, A., Pal, C. and Kadoury, S. (2018) Liver Lesion Segmentation Informed by Joint Liver Segmentation. 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), Washington, 4-7 April 2018, 1332-1335. [Google Scholar] [CrossRef] 
[45] Li, X., Chen, H., Qi, X., Dou, Q., Fu, C. and Heng, P. (2018) H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation from CT Volumes. IEEE Transactions on Medical Imaging, 37, 2663-2674. [Google Scholar] [CrossRef] [PubMed]
[46] Ou, J., Jiang, L., Bai, T., Zhan, P., Liu, R. and Xiao, H. (2024) ResTransUnet: An Effective Network Combined with Transformer and U-Net for Liver Segmentation in CT Scans. Computers in Biology and Medicine, 177, Article ID: 108625. [Google Scholar] [CrossRef] [PubMed]
[47] Khattab, M.A., Liao, I.Y., Ooi, E.H. and Chong, S.Y. (2022) Compound W-Net with Fully Accumulative Residual Connections for Liver Segmentation Using CT Images. Computational and Mathematical Methods in Medicine, 2022, Article ID: 8501828.

为你推荐