北京生物医学工程

基于拓扑算法的肝脏肿瘤消融术前路径规划系统

A preoperative path planning system for liver tumor ablation based on topological algorithms

作者：徐旭朱文文夏栋巫彤宁陈新华李从胜

单位：中国信息通信研究院泰尔终端实验室（北京100191) 浙江大学附属第一医院（杭州 310003） 通信作者：李从胜，高级工程师。E-mail: licongsheng@caict.ac.cn

关键词：肝肿瘤;计算机辅助; 消融针; 路径规划; 临床约束条件

分类号：R318.04

出版年·卷·期（页码）：2022·41·2（111-117）

摘要：

目的探索提高肝癌消融术路径规划的准确性和肝癌消融术疗效的方法。方法研究结合病患个体解剖特征的多约束进针路径规划模型，优化符合病患病灶分布特征的术前方案。本文提出深度学习模型以提高患者腹部组织器官重建精度，并设计拓扑优化算法进行多约束进针路径规划。结果系统通过重建患者腹部多组织数字模型，分析病灶和周围组织位置关系，制定满足临床条件的进针路径。结论本文所提出的肝肿瘤消融术前路径规划，可实现融合病患个体特征的可行手术穿刺方案制定，临床40例肝肿瘤患者术后增强影像显示病灶均完全消融，技术有效率达100%。

Objective Explore ways to improve the accuracy of ablation pathway planning and the efficacy of ablation for hepatocellular carcinoma. Methods A multi-constrained approach path planning model incorporating individual patient anatomical features is investigated to optimize a preoperative plan that matches the patient's lesion distribution characteristics. This paper proposes a deep learning model to improve the accuracy of the patient's abdominal tissue and organ reconstruction, and designs a topology optimization algorithm for multi-constrained approach path planning. Results By reconstructing a multi-tissue digital model of the patient's abdomen, the system analyses the relationship between the location of the lesion and the surrounding tissues and develops a needle path that meets the clinical conditions. Conclusions The preoperative pathway planning for liver tumor ablation proposed in this paper enables the development of a feasible surgical puncture plan that incorporates individual patient characteristics. 40 patients with liver tumors were completely ablated on postoperative enhanced imaging, with a technical efficiency of 100%.

参考文献：

[1]?Siegel RL, Miller KD, Jemal A, et al.?Cancer Statistics, 2019?[J]. CA: A Cancer Journal for Clinicians, 2019,?69(1): 7–34.

[2]?Guo A,?Pomenti S,?Wattacheril J.?Health disparities in screening, diagnosis, and treatment of hepatocellular carcinoma?[J]. Clinical?Liver Disease(Hoboken),?2021, 17 (5): 353–358.

[3]?陈敏山, 陈敏华, 叶胜龙,等.原发性肝癌局部消融治疗的专家共识[J].临床肿瘤学杂志,2011,16(1):?70-73.

[4]?张睿，周著黄，吴薇薇,等.肝肿瘤热消融治疗穿刺路径规划算法研究综述[J]. 北京工业大学学报, 2020, 46(11):1300-1314.

Zhang R, Zhou ZH, Wu WW,?et al. Review of needle?trajectory planning algorithms for?liver tumor?thermal ablation[J]. Journal of Beijing University of Technology, 2020, 46(11):?1300-1314.

[5]?Chu KF, Dupuy?DE.?Thermal ablation of tumours: biological mechanisms and advances in therapy. [J]. Nature Reviews Cancer, 2014, 14: 199-208.

[6]?Li S,?Yao J,?Navab N.?Guest Editorial: special issue on spine imaging, image-based modeling, and image guided intervention[J]. IEEE Transactions on Medical Imaging, 2015, 34 (8): 1625–1626.

[7]?Butz T, Warfield SK, Tuncali K, et al. Pre and intra-operative planning and simulation of percutaneous tumor ablation?[M]//?Medical Image Computing and Computer- Assisted Intervention?– MICCAI 2000. Lecture Notes in Computer Science.?Berlin : Springer, Berlin, Heidelberg,?2000,?1935: 317-326.?

[8]?Schumann C, Rieder C, Haase S, et al. Interactive access path exploration for planning of needle-based interventions [C]//?Proceedings of the CURAC Annual Meeting. La Clusaz: CEUR, 2013: 103-106.

[9]?Li C,?Yao G,?Xu X,?et al. DCSegNet: deep learning framework based on divide-and-conquer method for liver segmentation[J]. IEEE Access, 2020,?8: 146838–14846.

[10]?Zhang Y,?Pan X,?Li C,?et al. 3D liver and tumor segmentation with CNNs based on region and distance metrics[J]. Applied Sciences, 2020, 10 (11): 3794.

[11]?Xia D, Xu X, Zhang?Y. Segmentation and Reconstruction of Abdominal Multi-Tissues Based on Multiple Algorithms and Networks[J]. Journal of Physics: Conference Series, 2021,?1920: 012060.

[12]?Milletari F, Navab N, Ahmadi SA. V-net: fully convolutional neural networks for volumetric medical image segmentation [M]// 2016 Fourth International Conference on 3D Vision (3DV). Stanford, CA, USA: IEEE Press, 2016: 565-571.

[13]?Karimi D, Salcudean SE.?Reducing the Hausdorff distance in medical image segmentation with convolutional neural networks[J].?IEEE Transactions on Medical Imaging, 2020, 39(2): 499–513.

[14]?Xue Y, Tang H, Qiao Z, et al. Shape-aware organ segmentation by predicting signed distance maps[J]. Proceedings of the AAAI Conference on Artificial Intelligence,2020, 34(7):?12565–12572.

[15]?Schumann C, Bieberstein J, Braunewell S, et al. Visualization support for the planning of hepatic needle placement [J]. International Journal of Computer Assisted Radiology and Surgery, 2012, 7: 191-197.

Schumann C, Rieder C, Haase S,?et al.?Interactive access path exploration for planning of needle-based interventions[C]//?Proceedings of the CURAC Annual Meeting. La Clusaz, FR:?CURAC,?2013: 103-106．

服务与反馈：

【文章下载】【加入收藏】

提示：您还未登录，请登录！点此登录