Liver Vessel Segmentation in CT Images Based on Vascular Skeleton Feature Constraints
Tao Siyu1, Ji Xu2,3, Liu Qiegen4, Chen Yang2,3, Tang Hui2,3*
1(School of Software Engineering, Southeast University, Nanjing 211189, China) 2(School of Computer Science and Engineering, Southeast University, Nanjing 211189, China) 3(Key Laboratory of New Generation Artificial Intelligent Technology and its Interdisciplinary Applications (Southeast University), Ministry of Education, Nanjing 211189, China) 4(School of Information Engineering, Nanchang University, Nanchang 330031, China)
Abstract：Computed tomography (CT) is widely used in the preoperative planning stage of liver ablation surgery to assist doctors in making surgical plans. It is important to segment liver vessels from abdominal CT images. Due to the complex structure of liver blood vessels and the low contrast between blood vessels and surrounding tissues, it is difficult to accurately segment liver blood vessels from CT images. Most of the current segmentation methods only focus on the pixel distribution of blood vessels and ignore the structure information of blood vessels, so that the segmentation results often have fractures and holes. To solve the above problems, this paper proposed a liver vessel segmentation method based on vascular skeleton feature constraint and applies vascular skeleton features to the segmentation neural network. The detail process of the method included following steps: 1) A blood vessel enhancement step was added to the data preprocessing, then the blood vessel enhanced image and the original image were used as the input of the neural network, so as to introduce vascular spatial attention into the network input. 2) A skeletonization module based on Euler features was added to the post-processing procedure of the segmentation network and the output vascular skeleton feature was added to the loss function to design a joint loss function (Dice_MS_Loss) including Dice loss and morphological skeleton loss (MS_Loss), which serves as a constraint to promote the network’s topology preserve ability. In this study, 9 cases were selected from the public dataset IRCAD, and 29 cases were selected from the dataset MSD8. A total of 38 cases were used for method evaluation. The results of five-fold cross experiment showed that the proposed method was superior to other SOTA methods in terms of quantitative evaluation indicators, with the Dice coefficient of 0.749, the centerline Dice (clDice) of 0.79 and the sensitivity (Sen) of 0.754. The visual effects of the experiments showed that the proposed method was able to effectively segment liver blood vessel structures with less fractures and deficiencies.
陶思雨, 季续, 刘且根, 陈阳, 唐慧. 基于血管骨架特征约束的CT图像肝脏血管分割方法研究[J]. 中国生物医学工程学报, 2026, 45(1): 25-37.
Tao Siyu, Ji Xu, Liu Qiegen, Chen Yang, Tang Hui. Liver Vessel Segmentation in CT Images Based on Vascular Skeleton Feature Constraints. Chinese Journal of Biomedical Engineering, 2026, 45(1): 25-37.
[1] Chen Wanqing, Zheng Rongshou, Baade PD, et al. Cancer statistics in China [J]. Cancer Journal for Clinicians, 2016, 6(2): 115-132. [2] 胡英,付美涵. 基于三维全卷积神经网络的肝脏血管分割 [J]. 计算机应用与软件, 2022, 39(10): 217-223, 237. [3] 孙锦峰,丁辉,王广志. 基于W-Net的肝静脉和肝门静脉全自动分割 [J]. 中国生物医学工程学报, 2019, 38(5): 513-521. [4] 卞蓉蓉. 肝脏CT图像血管自动分割算法的研究 [D]. 南宁: 广西大学,2022. [5] Adams R, Bischof L. Seeded region growing [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1994, 16(6): 641-647. [6] Dong Jiahui, Ai Danni, Fan Jingfan, et al. Local-global active contour model based on tensor-based representation for 3D ultrasound vessel segmentation [J]. Physics in Medicine & Biology, 2021, 66(11): 115017. [7] 符晓珠,黄绍辉,王博亮,等. 一种自适应阈值的模糊连接算法及其在肝脏血管分割中的应用 [J]. 厦门大学学报(自然科学版), 2015, 54(04): 546-550. [8] Chapman BE, Parker DL. 3D multi-scale vessel enhancement filtering based on curvature measurements: application to time-of-flight MRA [J]. Medical Image Analysis, 2005, 9(3): 191-208. [9] Friman O, Hindennach M, Kühnel C, et al. Multiple hypothesis template tracking of small 3D vessel structures [J]. Medical Image Analysis, 2010, 14(2): 160-171. [10] Sun Ying. Automated identification of vessel contours in coronary arteriograms by an adaptive tracking algorithm [J]. IEEE Transactions on Medical Imaging, 1989, 8(1): 78-88. [11] Vlachos M, Dermatas E. Multi-scale retinal vessel segmentation using line tracking [J]. Computerized Medical Imaging and Graphics, 2010, 34(3): 213-227. [12] Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation [C] //Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015: 18th International Conference. Munich: MICCAI, 2015: 234-241. [13] Zhou Zongwei, Rahman Siddiquee MM, Tajbakhsh N, et al. Unet++: A nested u-net architecture for medical image segmentation [C] //Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support: 4th International Workshop, DLMIA 2018, and 8th International Workshop, ML-CDS 2018, held in conjunction with MICCAI 2018. Granada: MICCAI, 2018: 3-11. [14] He Kaiming, Zhang Xiangyu, Ren Shaoqing, et al. Deep residual learning for image recognition [C] //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: CVPR, 2016: 770-778. [15] Xia Yingda, Xie Lingxi, Liu Fengze, et al. Bridging the gap between 2d and 3d organ segmentation with volumetric fusion net [C] //Medical Image Computing and Computer Assisted Intervention-MICCAI 2018: 21st International Conference. Granada: MICCAI, 2018: 445-453. [16] Li Lei, Lian Sheng, Luo Zhiming, et al. Learning consistency-and discrepancy-context for 2D organ segmentation [C] //Medical Image Computing and Computer Assisted Intervention-MICCAI 2021: 24th International Conference. Strasbourg: MICCAI, 2021: 261-270. [17] Zhao Ziyuan, Ma Zeyu, Liu Yanjie, et al. Multi-slice dense-sparse learning for efficient liver and tumor segmentation [C] //2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). Mexico: EMBC, 2021: 3582-3585. [18] Zhang Yichi, Yuan Lin, Wang Yujia, et al. SAU-Net: efficient 3D spine MRI segmentation using inter-slice attention [C] //Medical Imaging with Deep Learning. New York: PMLR, 2020: 903-913. [19] Kuang Zhuo, Deng Xianbo, Yu Li, et al. Ψ-Net: Focusing on the border areas of intracerebral hemorrhage on CT images [J]. Computer Methods and Programs in Biomedicine, 2020, 194: 105546. [20] Li Xiaomeng, Chen Hao, Qi Xiaojuan, et al. H-DenseUNet: hybrid densely connected UNet for liver and tumor segmentation from CT volumes [J]. IEEE Transactions on Medical Imaging, 2018, 37(12): 2663-2674. [21] Chen Zijie, Li Cheng, He Junjun, et al. A novel hybrid convolutional neural network for accurate organ segmentation in 3D head and neck CT images [C] //Medical Image Computing and Computer Assisted Intervention-MICCAI 2021: 24th International Conference. Strasbourg: MICCAI, 2021: 569-578. [22] Mei Haochen, Lei Wenhui, Gu Ran, et al. Automatic segmentation of gross target volume of nasopharynx cancer using ensemble of multiscale deep neural networks with spatial attention [J]. Neurocomputing, 2021, 438: 211-222. [23] Zhang Yichi, Liao Qingcheng, Ding Le, et al. Bridging 2D and 3D segmentation networks for computation-efficient volumetric medical image segmentation: An empirical study of 2.5D solutions [J]. Computerized Medical Imaging and Graphics, 2022, 99: 102088. [24] Çiçek Ö, Abdulkadir A, Lienkamp SS, et al. 3D U-Net: learning dense volumetric segmentation from sparse annotation [C] //Medical Image Computing and Computer-Assisted Intervention-MICCAI 2016: 19th International Conference. Athens: MICCAI, 2016: 424-432. [25] Milletari F, Navab N, Ahmadi SA. V-net: Fully convolutional neural networks for volumetric medical image segmentation [C] //2016 4th International Conference on 3D Vision (3DV). Palo Alto: IEEE, 2016: 565-571. [26] Isensee F, Jaeger PF, Kohl SAA, et al. nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation [J]. Nature Methods, 2021, 18(2): 203-211. [27] Shit S, Paetzold JC, Sekuboyina A, et al. clDice-a novel topology-preserving loss function for tubular structure segmentation [C] //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville: CVPR, 2021: 16560-16569. [28] Viti M, Talbot H, Abdallah B, et al. Coronary artery centerline tracking with the morphological skeleton loss [C] //2022 IEEE International Conference on Image Processing (ICIP). Bordeaux: ICIP, 2022: 2741-2745. [29] Menten MJ, Paetzold JC, Zimmer VA, et al. A skeletonization algorithm for gradient-based optimization [C] //Proceedings of the IEEE/CVF International Conference on Computer Vision. Paris: ICCV, 2023: 21394-21403. [30] Sato Y, Nakajima S, Shiraga N, et al. Three-dimensional multi-scale line filter for segmentation and visualization of curvilinear structures in medical images [J]. Medical Image Analysis, 1998, 2(2): 143-168. [31] Soler L, Hostettler A and Agnus V, et al. 3D image reconstruction for comparison of algorithm database [DB]. https://www.ircad.fr/research/data-sets/liver-segmentation-3d-ircadb-01, 2010/2024-01-01. [32] Simpson AL, Antonelli M, Bakas S, et al. A large annotated medical image dataset for the development and evaluation of segmentation algorithms [J]. https://arxiv.org/abs/1902.09063, 2019-02-25/2024-01-01. [33] Liu Li, Tian Jiang, Zhong Cheng, et al. Robust hepatic vessels segmentation model based on noisy dataset [C] //Medical Imaging 2020: Computer-Aided Diagnosis. Oxford: MICAD, 2020, 11314: 122-128. [34] Mou Lei, Zhao Yitian, Fu Huazhu, et al. CS2-Net: Deep learning segmentation of curvilinear structures in medical imaging [J]. Medical Image Analysis, 2021, 67: 101874. [35] Qi Yaolei, He Yuting, Qi Xiaoming, et al. Dynamic snake convolution based on topological geometric constraints for tubular structure segmentation [C] //Proceedings of the IEEE/CVF International Conference on Computer Vision. Paris: ICCV, 2023: 6070-6079.
