Progress in Application of Deep Learning in Liver and Liver Tumor Segmentation

doi:10.3778/j.issn.1002-8331.2411-0100

Abstract

Abstract: Liver cancer is a malignant tumor with increasing morbidity and mortality. Precise segmentation of the liver and tumor is crucial for diagnosing and treating this disease. Traditional liver and tumor segmentation relies on manual work by doctors, which is time-consuming, experience-dependent, and challenging to ensure accuracy and efficiency in large-scale data processing. Recent advances in deep learning, particularly with its automatic feature extraction capabilities, have significantly improved liver and tumor segmentation. This review introduces widely-used public datasets and evaluation metrics, and summarizes progress in liver and tumor segmentation from supervised and unsupervised learning perspectives. Advantages and limitations of various models are discussed, and performance comparisons across methods are presented. Finally, limitations and challenges in current research are highlighted, along with future research directions, providing a reference for further studies.

Key words: liver and liver tumors, image segmentation, deep learning, supervised learning, unsupervised learning

摘要： 肝癌作为一种恶性肿瘤，其发病率和死亡率正呈逐年上升趋势，临床中精准分割肝脏与肿瘤对肝癌的诊断与治疗至关重要。传统的肝脏及肿瘤分割依赖医生手工操作，过程耗时且高度依赖医生经验，在大规模数据处理中难以确保效率和精度，且易因主观判断差异导致误差。近年来，深度学习因能自动提取图像特征被广泛应用于医学图像处理，在肝脏及肝脏肿瘤分割任务中也取得了显著进展。为更深入开展深度学习在肝脏及肝脏肿瘤分割的应用研究，从常用公开数据集及评价指标入手，分别从有监督与无监督学习的角度，梳理近年来深度学习在肝脏及其肿瘤分割领域的应用进展，总结各模型的优缺点，对比各类方法的性能差异，并以此为基础讨论现有研究尚存的不足及挑战，展望其未来发展方向，以期为进一步研究提供参考。

关键词: 肝脏及肝脏肿瘤, 图像分割, 深度学习, 有监督学习, 无监督学习

CUI Hui, GUO Yinghui, CAI Xiaohong, WANG Xiaoyan. Progress in Application of Deep Learning in Liver and Liver Tumor Segmentation[J]. Computer Engineering and Applications, 2025, 61(17): 47-61.

崔慧, 郭英慧, 蔡肖红, 王晓燕. 深度学习在肝脏及肝脏肿瘤分割中的应用进展[J]. 计算机工程与应用, 2025, 61(17): 47-61.

References

[1] 王培宇, 黄祺, 王少东, 等. 《全球癌症统计数据2022》要点解读[J]. 中国胸心血管外科临床杂志, 2024, 31(7): 933-954.
WANG P Y, HUANG Q, WANG S D, et al. Interpretation of the key points of “global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries”[J]. Chinese Journal of Clinical Thoracic and Cardiovascular Surgery, 2024, 31(7): 933-954.
[2] BRAY F, LAVERSANNE M, SUNG H, et al. Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries[J]. CA: A Cancer Journal for Clinicians, 2024, 74(3): 229-263.
[3] 郭振宁. 超声造影诊断微小原发性肝癌患者临床价值研究[J]. 实用肝脏病杂志, 2018, 21(5): 741-744.
GUO Z N. Contrast-enhanced ultrasound monitoring in early diagnosis of patients with small primary liver cancer[J]. Journal of Practical Hepatology, 2018, 21(5): 741-744.
[4] 朱风叶, 李红, 乔继红, 等. CT与MRI在诊断原发性肝癌介入术后病灶残留及复发中的应用价值[J]. 中国CT和MRI杂志, 2018, 16(3): 76-78.
ZHU F Y, LI H, QIAO J H, et al. The value of CT and MRI in the diagnosis of the residual and recurrent lesion of primary liver cancer after interventional therapy[J]. Chinese Journal of CT and MRI, 2018, 16(3): 76-78.
[5] 冯焕, 姜晖, 王雪梅. 功能磁共振成像在肿瘤学领域的应用[J]. 电工技术学报, 2021, 36(4): 705-716.
FENG H, JIANG H, WANG X M. Application of functional magnetic resonance imaging in the field of oncology[J]. Transactions of China Electrotechnical Society, 2021, 36(4): 705-716.
[6] ALTINI N, PRENCIPE B, CASCARANO G D, et al. Liver, kidney and spleen segmentation from CT scans and MRI with deep learning: a survey[J]. Neurocomputing, 2022, 490: 30-53.
[7] 谭健权, 伊力亚尔·加尔木哈买提. 基于深度学习的医学图像分割综述[J]. 电脑知识与技术, 2024, 20(18): 97-99.
TAN J Q. YILIYAER J. Summary of medical image segmentation based on deep learning[J]. Computer Knowledge and Technology, 2024, 20(18): 97-99.
[8] LUNDERVOLD A S, LUNDERVOLD A. An overview of deep learning in medical imaging focusing on MRI[J]. Zeitschrift Für Medizinische Physik, 2019, 29(2): 102-127.
[9] 王霄, 朱恩照, 艾自胜. 卷积神经网络的原理及其在医学影像诊断中的应用[J]. 中国医学物理学杂志, 2022, 39(12): 1485-1489.
WANG X, ZHU E Z, AI Z S. Principle of convolutional neural network and its applications in medical imaging diagnosis[J]. Chinese Journal of Medical Physics, 2022, 39(12): 1485-1489.
[10] 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.
ZHANG H, LIU J, FENG Y B, et al. Review of U-Net and its application in segmentation of liver and liver tumors[J]. Computer Engineering and Applications, 2022, 58(2): 1-14.
[11] GUL S, KHAN M S, BIBI A, et al. Deep learning techniques for liver and liver tumor segmentation: a review[J]. Computers in Biology and Medicine, 2022, 147: 105620.
[12] 陈英, 郑铖, 易珍, 等. 肝脏及肿瘤图像分割方法综述[J]. 计算机应用研究, 2022, 39(3): 641-650.
CHEN Y, ZHENG C, YI Z, et al. Review of liver and tumor image segmentation methods[J]. Application Research of Computers, 2022, 39(3): 641-650.
[13] 夏栋, 张义, 巫彤宁, 等. 深度学习在肝脏肿瘤CT图像分割中的应用[J]. 北京生物医学工程, 2023, 42(3): 308-314.
XIA D, ZHANG Y, WU T N, et al. Applications of deep learning in liver tumor segmentation from CT scans[J]. Beijing Biomedical Engineering, 2023, 42(3): 308-314.
[14] EGALA R, SAIRAM M V S. A review on medical image analysis using deep learning[C]//Proceedings of the 5th International Conference on Innovative Product Design and Intelligent Manufacturing Systems, 2024: 7.
[15] KAVUR A E, GEZER N S, BAR?? M, et al. CHAOS challenge-combined (CT-MR) healthy abdominal organ segmentation[J]. Medical Image Analysis, 2021, 69: 101950.
[16] BILIC P, CHRIST P, LI H B, et al. The liver tumor segmentation benchmark (lits)[J]. Medical Image Analysis, 2023, 84: 102680.
[17] SOLER L, HOSTETTLER A, AGNUS V, et al. 3D image reconstruction for comparison of algorithm database[EB/OL]. (2010-01-08) [2023-12-23]. https://www.ircad.fr/research/data-sets/liver-segmentation-3d-ircadb-01.
[18] AL-SHAIKHLI S D S, YANG M, ROSENHAHN B. Automatic 3D liver segmentation using sparse representation of global and local image information via level set formulation[J]. arXiv:1508.01521, 2015.
[19]于营, 王春平, 付强, 等. 语义分割评价指标和评价方法综述[J]. 计算机工程与应用, 2023, 59(6): 57-69.
YU Y, WANG C P, FU Q, et al. Survey of evaluation metrics and methods for semantic segmentation[J]. Computer Engineering and Applications, 2023, 59(6): 57-69.
[20] 蒋西然, 蒋韬, 孙嘉瑶, 等. 深度学习人工智能技术在医学影像辅助分析中的应用[J]. 中国医疗设备, 2021, 36(6): 164-171.
JIANG X R, JIANG T, SUN J Y, et al. Deep learning in computer aided analyses of medical images[J]. China Medical Devices, 2021, 36(6): 164-171.
[21] ALJABRI M, ALGHAMDI M. A review on the use of deep learning for medical images segmentation[J]. Neurocomputing, 2022, 506: 311-335.
[22] LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.
[23] LONG J, SHELHAMER E, DARRELL T. Fully convolutional networks for semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2015: 3431-3440.
[24] RONNEBERGER O, FISCHER P, BROX T. U-Net: convolutional networks for biomedical image segmentation[C]//Proceedings of the Medical Image Computing and Computer-Assisted Intervention. Cham: Springer International Publishing, 2015: 234-241.
[25] 李彦冬, 郝宗波, 雷航. 卷积神经网络研究综述[J]. 计算机应用, 2016, 36(9): 2508-2512.
LI Y D, HAO Z B, LEI H. Survey of convolutional neural network[J]. Journal of Computer Applications, 2016, 36(9): 2508-2512.
[26] AGHAMOHAMMADI A, RANJBARZADEH R, NAIEMI F, et al. TPCNN: two-path convolutional neural network for tumor and liver segmentation in CT images using a novel encoding approach[J]. Expert Systems with Applications, 2021, 183: 115406.
[27] KHAN R, SU L, ZAMAN A, et al. Customized m-RCNN and hybrid deep classifier for liver cancer segmentation and classification[J]. Heliyon, 2024, 10(10): e30528.
[28] SELVARAJ A, NITHIYARAJ E. CEDRNN: a convolutional encoder-decoder residual neural network for liver tumour segmentation[J]. Neural Processing Letters, 2023, 55(2): 1605-1624.
[29] MENG L, TIAN Y, BU S. Liver tumor segmentation based on 3D convolutional neural network with dual scale[J]. Journal of Applied Clinical Medical Physics, 2020, 21(1): 144-157.
[30] BUDAK ü, GUO Y H, TANYILDIZI E, et al. Cascaded deep convolutional encoder-decoder neural networks for efficient liver tumor segmentation[J]. Medical Hypotheses, 2020, 134: 109431.
[31] ANIL B C, DAYANANDA P. Automatic liver tumor segmentation based on multi-level deep convolutional networks and fractal residual network[J]. IETE Journal of Research, 2023, 69(4): 1925-1933.
[32] AHMAD M, QADRI S F, QADRI S, et al. A lightweight convolutional neural network model for liver segmentation in medical diagnosis[J]. Computational Intelligence and Neuroscience, 2022, 2022: 7954333.
[33] 李梦怡, 朱定局. 基于全卷积网络的图像语义分割方法综述[J]. 计算机系统应用, 2021, 30(9): 41-52.
LI M Y, ZHU D J. Review on image semantic segmentation based on fully convolutional network[J]. Computer Systems & Applications, 2021, 30(9): 41-52.
[34] ROTH H R, ODA H, ZHOU X, et al. An application of cascaded 3D fully convolutional networks for medical image segmentation[J]. Computerized Medical Imaging and Grapics, 2018, 66: 90-99.
[35] ALIRR O I. Deep learning and level set approach for liver and tumor segmentation from CT scans[J]. Journal of Applied Clinical Medical Physics, 2020, 21(10): 200-209.
[36] CHRIST P F, ETTLINGER F, GRüN F, et al. Automatic liver and tumor segmentation of CT and MRI volumes using cascaded fully convolutional neural networks[J]. arXiv:1702. 05970, 2017.
[37] CHLEBUS G, SCHENK A, MOLTZ J H, et al. Automatic liver tumor segmentation in CT with fully convolutional neural networks and object-based postprocessing[J]. Sci Rep, 2018, 8(1): 15497.
[38] RAFIEI S, NASR-ESFAHANI E, NAJARIAN K, et al. Liver segmentation in CT images using three dimensional to two dimensional fully convolutional network[C]//Proceedings of the 25th IEEE International Conference on Image Processing. Piscataway: IEEE, 2018: 2067-2071.
[39] JIANG H Y, SHI T Y, BAI Z Q, et al. AHCNet: an application of attention mechanism and hybrid connection for liver tumor segmentation in CT volumes[J]. IEEE Access, 2019, 7: 24898-24909.
[40] HAN Y X, LI X L, WANG B, et al. Boundary loss-based 2.5D fully convolutional neural networks approach for segmentation: a case study of the liver and tumor on computed tomography[J]. Algorithms, 2021, 14(5): 144.
[41] DONG X, ZHOU Y Z, WANG L T, et al. Liver cancer dete-ction using hybridized fully convolutional neural network based on deep learning framework[J]. IEEE Access, 2020, 8: 129889-129898.
[42] HARIPRIYA T, DHARMARAJAN K, CHOWDHURY S. An innovative research of liver malignancy imaging using HFCNN based on deep neural network model[J]. Samvakti Journal of Research in Information Technology, 2024, 5(1): 1-16.
[43] 崔珂, 田启川, 廉露. 基于U-Net变体的医学图像分割算法综述[J]. 计算机工程与应用, 2024, 60(11): 32-49.
CUI K, TIAN Q C, LIAN L. Review of medical image segmentation algorithms based on U-Net variants[J]. Computer Engineering and Applications, 2024, 60(11): 32-49.
[44] CZIPCZER V, MANNO-KOVACS A. Adaptable volumetric liver segmentation model for CT images using region-based features and convolutional neural network[J]. Neurocomputing, 2022, 505: 388-401.
[45] LI S, TSO G K F, HE K J. Bottleneck feature supervised U-Net for pixel-wise liver and tumor segmentation[J]. Expert Systems with Applications, 2020, 145: 113131.
[46] DENG Y J, HOU Y L, YAN J T, et al. ELU-Net: an efficient and lightweight U-Net for medical image segmentation[J]. IEEE Access, 2022, 10: 35932-35941.
[47] ALAFER F, SIDDIQI H M, KHAN S M, et al. A comprehensive exploration of L-UNet approach: revolutionizing medical image segmentation[J]. IEEE Access, 2024, 12: 140769-140791.
[48] LEE Z Q, QI S M, FAN C C, et al. RA V-Net: deep learning network for automated liver segmentation[J]. Physics in Medicine & Biology, 2022, 67(12): 125022.
[49] NAAQVI Z, HAIDER M A, FAHEEM M R, et al. Modified U-Net model for segmentation and classification of liver cancer using CT images[J]. Journal of Computing & Biomedical Informatics, 2024: 1-12.
[50] 杨振, 邸拴虎, 赵于前, 等. 基于级联 Dense-UNet 和图割的肝脏肿瘤自动分割[J]. 电子与信息学报, 2022, 44(5): 1683-1693.
YANG Z, DI S H, ZHAO Y Q, et al. Automatic liver tumor segmentation based on cascaded Dense-UNet and graph cuts [J]. Journal of Electronics & Information Technology, 2022, 44(5): 1683-1693.
[51] SABIR M W, KHAN Z, SAAD N M, et al. Segmentation of liver tumor in CT scan using ResU-Net[J]. Applied Sciences, 2022, 12(17): 8650.
[52] LI J, LIU K Y, HU Y T, et al. Eres-UNet++: liver CT image segmentation based on high-efficiency channel attention and Res-UNet++[J]. Computers in Biology and Medicine, 2023, 158: 106501.
[53] DING J S, NI W, WAN J H, et al. MulA-nnUNet: a multi-attention enhanced nnUNet framework for 3D abdominal multi-organs segmentation[J]. IEEE Access, 2024, 12: 106658-106671.
[54] 杨本臣, 贾宇航, 金海波. 融合多分支特征的肝脏和肝脏肿瘤的体积分割[J]. 计算机工程, 2023, 49(10): 194-201.
YANG B C, JIA Y H, JIN H B. Volume segmentation of liver and liver tumor with fusion of multi-branch features[J]. Computer Engineering, 2023, 49(10): 194-201.
[55] OU J J, JIANG L F, BAI T, et al. ResTransUnet: an effective network combined with Transformer and U-Net for liver segmentation in CT scans[J]. Computers in Biology and Medicine, 2024, 177: 108625.
[56] LI L, MA H. RDCTrans U-Net: a hybrid variable architecture for liver CT image segmentation[J]. Sensors (Basel), 2022, 22(7): 2452.
[57] 陈丽芳, 罗世勇. 融合卷积和Transformer的多尺度肝肿瘤分割方法[J]. 计算机工程与应用, 2024, 60(4): 270-279.
CHEN L F, LUO S Y. Multi-scale liver tumor segmentation algorithm by fusing convolution and transformer[J]. Computer Engineering and Applications, 2024, 60(4): 270-279.
[58] 马露凡, 罗凤, 严江鹏, 等. 深度医学图像配准研究进展: 迈向无监督学习[J]. 中国图象图形学报, 2021, 26(9): 2037-2057.
MA L F, LUO F, YAN J P, et al. Deep-learning based medical image registration pathway: towards unsupervised learning[J]. Journal of Image and Graphics, 2021, 26(9): 2037-2057.
[59] RAZA K, SINGH N K. A tour of unsupervised deep learning for medical image analysis[J]. Current Medical Imaging, 2021, 17(9): 1059-1077.
[60] XUN S Y, LI D W, ZHU H, et al. Generative adversarial networks in medical image segmentation: a review[J]. Computers in Biology and Medicine, 2022, 140: 105063.
[61] SONG C, HE B, CHEN H, et al. Non-contrast CT liver seg-mentation using CycleGAN data augmentation from contrast enhanced CT[C]//Proceedings of the 3rd International Workshop on Interpretable and Annotation-Efficient Learning for Medical Image Computing, 2020: 122-129.
[62] LI H, IWAMOTO Y, HAN X, et al. An accurate unsupervised liver lesion detection method using pseu-do-lesions[C]//Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer Nature Switzerland, 2022: 214-223.
[63] WANG L, GUO D, WANG G, et al. Annotation-efficient learning for medical image segmentation based on noisy pseudo labels and adversarial learning[J]. IEEE Transactions on Medical Imaging, 2021, 40(10): 2795-2807.
[64] RAFIQ M, ALI H, MUJTABA G, et al. Cross modality medical image synthesis for improving liver segmentation[J]. arXiv:2503.00945, 2025.
[65] LIU Y, MENG L, ZHONG J. MAGAN: mask attention generative adversarial network for liver tumor CT image synthesis[J]. Journal of Healthcare Engineering, 2021, 2021: 6675259.
[66] LIU Y, YANG F, YANG Y. A partial convolution generative adversarial network for lesion synthesis and enhanced liver tumor segmentation[J]. Journal of Applied Clinical Medical Physics, 2023, 24(4): e13927.
[67] ZHENG Z C, WANG M, FAN C, et al. Light&fast generative adversarial network for high-fidelity CT image synthesis of liver tumor[J]. Computer Methods and Programs in Biomedicine, 2024, 254: 108252.
[68] ZHANG Y, WU J, JIANG B X, et al. Deep learning and unsupervised fuzzy C-means based level-set segmentation for liver tumor[C]//Proceedings of the IEEE 17th International Symposium on Biomedical Imaging. Piscataway: IEEE, 2020: 1193-1196.
[69] AL-SAEED Y, SOLIMAN H, ELMOGY M. Liver segmentation using fast-generalized fuzzy C-means (FG-FCM) from CT scans[C]//Proceedings of the International Conference on Data Analytics for Business and Industry: Way Towards a Sustainable Economy. Piscataway: IEEE, 2020: 1-6.
[70] RANJBARZADEH R, SAADI S B. Automated liver and tumor segmentation based on concave and convex points using fuzzy C-means and mean shift clustering[J]. Measurement, 2020, 150: 107086.
[71] RELA M, NAGARAJA S, RAMANA P. Liver tumor segmentation using superpixel based fast fuzzy C means clustering[J]. International Journal of Advanced Computer Science and Applications, 2020, 11(11): 230120927.
[72] LI S, LI X. Fully incomplete information for multiview clustering in postoperative liver tumor diagnoses[J]. Sensors (Basel), 2025, 25(4): 1215.
[73] KRISHAN A, MITTAL D. Effective segmentation and classification of tumor on liver MRI and CT images using multi-kernel K-means clustering[J]. Biomedizinische Technik, 2020, 65(3): 301-313.
[74] 林家兴, 吕东澔. 基于区域生长与K-means聚类结合的肝脏肿瘤分割[J]. 电脑知识与技术, 2021, 17(26): 134-137.
LIN J X, LYU D H. Segmentation of liver tumors based on regional growth combined with K-means clustering[J]. Computer Knowledge and Technology, 2021, 17(26): 134-137.
[75] ANANTH C, AMUTHA S, NIHA K. Enhancing segmentation approaches from super pixel division algorithm to hidden Markov random fields with expectation maximization (HMRF-EM)[J]. International Journal of Early Childhood Special Education, 2022, 14(5): 2400-2410.
[76] PATTWAKKAR V N, KAMATH S, KANABAGATTE NANJUNDAPPA M, et al. Automatic liver tumor segmentation on multiphase computed tomography volume using SegNet deep neural network and K-means clustering[J]. International Journal of Imaging Systems and Technology, 2023, 33(2): 729-745.
[77] GUAN H, GUAN H, LIU M. Domain adaptation for medical image analysis: a survey[J]. IEEE Transactions on Biomedical Engineering , 2022, 69(3): 1173-1185.
[78] JIANG K D, QUAN L, GONG T. Disentangled represen-tation and cross-modality image translation based unsupervised domain adaptation method for abdominal organ segmentation[J]. International Journal of Computer Assisted Radiology and Surgery, 2022, 17(6): 1101-1113.
[79] XIE Q S, LI Y X, HE N J, et al. Unsupervised domain adaptation for medical image segmentation by disentanglement learning and self-training[J]. IEEE Transactions on Medical Imaging, 2024, 43(1): 4-14.
[80] HONG J, ZHANG Y D, CHEN W T. Source-free unsupervised domain adaptation for cross-modality abdominal multi-organ segmentation[J]. Knowledge-Based Systems, 2022, 250: 109155.
[81] OZKAN S, SELVER M A, BAYDAR B, et al. Cross-modal learning via adversarial loss and covariate shift for enhanced liver segmentation[J]. IEEE Transactions on Emerging Topics in Computational Intelligence, 2024, 8(4): 2723-2735.
[82] 王淼, 黄智忠, 何晖光, 等. 分割一切模型SAM的潜力与展望: 综述[J]. 中国图象图形学报, 2024, 29(6): 1479-1509.
WANG M, HUANG Z Z, HE H G, et al. Potential and prospects of segment anything model: a survey[J]. Journal of Image and Graphics, 2024, 29(6): 1479-1509.
[83] RATHI N, CHAKRABORTY I, KOSTA A, et al. Exploring neuromorphic computing based on spiking neural networks: algorithms to hardware[J]. ACM Computing Surveys, 2023, 55(12): 1-49.
[84] WEI L, LIU H W, XU J, et al. Quantum machine learning in medical image analysis: a survey[J]. Neurocomputing, 2023, 525: 42-53.