Deep learning for accurate lung artery segmentation with shape-position priors_Chinese Journal of Clinical Thoracic and Cardiovascular Surgery

Authors：

GUO Chao ¹ , GAO Xuehan ¹ , HU Qidi ^2,3 , LI Jian ² , ZHU Haixing ² , ZHAO Ke ¹ , LIU Weipeng ² ,  LI Shanqing ¹

1. Department of Thoracic Surgery, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100730, P. R. China;
2. Hebei University of Technology, School of Artificial Intelligence and Data Science, Tianjin, 300401, P. R. China;
3. Hubei Industrial Internet Industry Technology Research Institute, Huangshi, 431602, Hubei, P. R. China;

Corresponding author：

LI Shanqing, Email: lishanqing@pumch.cn

Keywords：

Pulmonary artery segmentation; deep learning; three-dimensional U-Net; prior knowledge; surgical navigation

DOI：

10.7507/1007-4848.202411009

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Objective To propose a lung artery segmentation method that integrates shape and position prior knowledge, aiming to solve the issues of inaccurate segmentation caused by the high similarity and small size differences between the lung arteries and surrounding tissues in CT images. Methods Based on the three-dimensional U-Net network architecture and relying on the PARSE 2022 database image data, shape and position prior knowledge was introduced to design feature extraction and fusion strategies to enhance the ability of lung artery segmentation. The data of the patients were divided into three groups: a training set, a validation set, and a test set. The performance metrics for evaluating the model included Dice Similarity Coefficient (DSC), sensitivity, accuracy, and Hausdorff distance (HD95). Results The study included lung artery imaging data from 203 patients, including 100 patients in the training set, 30 patients in the validation set, and 73 patients in the test set. Through the backbone network, a rough segmentation of the lung arteries was performed to obtain a complete vascular structure; the branch network integrating shape and position information was used to extract features of small pulmonary arteries, reducing interference from the pulmonary artery trunk and left and right pulmonary arteries. Experimental results showed that the segmentation model based on shape and position prior knowledge had a higher DSC (82.81%±3.20% vs. 80.47%±3.17% vs. 80.36%±3.43%), sensitivity (85.30%±8.04% vs. 80.95%±6.89% vs. 82.82%±7.29%), and accuracy (81.63%±7.53% vs. 81.19%±8.35% vs. 79.36%±8.98%) compared to traditional three-dimensional U-Net and V-Net methods. HD95 could reach (9.52±4.29) mm, which was 6.05 mm shorter than traditional methods, showing excellent performance in segmentation boundaries. Conclusion The lung artery segmentation method based on shape and position prior knowledge can achieve precise segmentation of lung artery vessels and has potential application value in tasks such as bronchoscopy or percutaneous puncture surgery navigation.

Citation： GUO Chao, GAO Xuehan, HU Qidi, LI Jian, ZHU Haixing, ZHAO Ke, LIU Weipeng, LI Shanqing. Deep learning for accurate lung artery segmentation with shape-position priors. Chinese Journal of Clinical Thoracic and Cardiovascular Surgery, 2025, 32(3): 332-338. doi: 10.7507/1007-4848.202411009 Copy

1.	Han B, Zheng R, Zeng H, et al. Cancer incidence and mortality in China, 2022. J Natl Cancer Cent, 2024, 4(1): 47-53.
2.	Siegel RL, Miller KD, Wagle NS, et al. Cancer statistics, 2023. CA Cancer J Clin, 2023, 73(1): 17-48.
3.	罗汶鑫, 杨澜, 王成弟, 等. 肺癌筛查与早期诊断的研究现状与挑战. 中国科学: 生命科学, 2022, 52(11): 1603-1611.Luo WX, Yang L, Wang CD, et al. Current status and challenges of research on lung cancer screening and early diagnosis. Sci Sin Vitae, 2022, 52(11): 1603-1611.
4.	Herth FJ, Eberhardt R, Sterman D, et al. Bronchoscopic transparenchymal nodule access (BTPNA): First in human trial of a novel procedure for sampling solitary pulmonary nodules. Thorax, 2015, 70(4): 326-332.
5.	张皓, 韩铭钧. 肺部疾病中肺血管及肺血流变化的CT研究. 国外医学(临床放射学分册), 2006, 29(4): 250-253.Zhang H, Han MJ. CT study of lung vasculature and blood flow changes in lung diseases. Foreign Med Sci (Clin Radiol F), 2006, 29(4): 250-253.
6.	段辉宏, 龚敬, 王丽嘉, 等. 肺部CT图像气管树分割技术研究进展. 中国生物医学工程学报, 2018, 37(6): 739-748.Duan HH, Gong J, Wang LJ, et al. A review of segmentation of pulmonary airway in lung CT scans. Chin J Biomed Eng, 2018, 37(6): 739-748.
7.	Zheng H, Qin Y, Gu Y, et al. Alleviating class-wise gradient imbalance for pulmonary airway segmentation. IEEE Trans Med Imaging, 2021, 40(9): 2452-2462.
8.	Lassen B, van Rikxoort EM, Schmidt M, et al. Automatic segmentation of the pulmonary lobes from chest CT scans based on fissures, vessels, and bronchi. IEEE Trans Med Imaging, 2013, 32(2): 210-222.
9.	Chen B, Kitasaka T, Honma H, et al. Automatic segmentation of pulmonary blood vessels and nodules based on local intensity structure analysis and surface propagation in 3D chest CT images. Int J Comput Assist Radiol Surg, 2012, 7(3): 465-482.
10.	Helmberger M, Pienn M, Urschler M, et al. Quantification of tortuosity and fractal dimension of the lung vessels in pulmonary hypertension patients. PLoS One, 2014, 9(1): e87515.
11.	Xu S, Zhang Z, Zhou Q, et al. A pulmonary vascular extraction algorithm from chest CT/CTA images. J Healthc Eng, 2021, 2021: 5763177.
12.	Gu X, Wang J, Zhao J, et al. Segmentation and suppression of pulmonary vessels in low-dose chest CT scans. Med Phys, 2019, 46(8): 3603-3614.
13.	Ronneberger O, Fischer P, Brox T. U-Net: Convolutional networks for biomedical image segmentation. arXiv:1505.04597.
14.	Chen LC, Zhu Y, Papandreou G, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Ferrari V, Hebert M, Sminchisescu C, et al. (eds) Computer Vision–ECCV 2018. ECCV 2018. Lecture Notes in Computer Science, vol 11211. Springer, Cham.
15.	Çiçek Ö, Abdulkadir A, Lienkamp SS, et al. 3D U-Net: Learning dense volumetric segmentation from sparse annotation. In: Ourselin S, Joskowicz L, Sabuncu M, et al. (eds) Medical Image Computing and Computer-assisted Intervention–MICCAI 2016. MICCAI 2016. Lecture Notes in Computer Science, vol 9901. Springer, Cham.
16.	Lee HY, Chung YJ, Wang HJ, et al. Automated 3D segmentation of the aorta and pulmonary artery for predicting outcomes after thoracoscopic lobectomy in lung cancer patients. Front Oncol, 2022, 12: 1027036.
17.	Luo G, Wang K, Liu J, et al. Efficient automatic segmentation for multi-level pulmonary arteries: The PARSE challenge. arXiv: 2304.03708.
18.	Wang HJ, Chen LW, Lee HY, et al. Automated 3D segmentation of the aorta and pulmonary artery on non-contrast-enhanced chest computed tomography images in lung cancer patients. Diagnostics (Basel), 2022, 12(4): 967.
19.	Wu Y, Qi S, Wang M, et al. Transformer-based 3D U-Net for pulmonary vessel segmentation and artery-vein separation from CT images. Med Biol Eng Comput, 2023, 61(10): 2649-2663.
20.	Kundu S, Karale V, Ghorai G, et al. Nested U-Net for segmentation of red lesions in retinal fundus images and sub-image classification for removal of false positives. J Digit Imaging, 2022, 35(5): 1111-1119.
21.	Milletari F, Navab N, Ahmadi SA. V-Net: Fully convolutional neural networks for volumetric medical image segmentation. arXiv:1606.04797.
22.	Aydin OU, Taha AA, Hilbert A, et al. On the usage of average Hausdorff distance for segmentation performance assessment: Hidden error when used for ranking. Eur Radiol Exp, 2021, 5(1): 4.
23.	Shen D, Wu G, Suk HI. Deep learning in medical image analysis. Annu Rev Biomed Eng, 2017, 19: 221-248.
24.	Lai H, Fu S, Zhang J, et al. Prior knowledge-aware fusion network for prediction of macrovascular invasion in hepatocellular carcinoma. IEEE Trans Med Imaging, 2022, 41(10): 2644-2657.
25.	Wu Y, Wu G, Lin J, et al. Role exchange-based self-training semi-supervision framework for complex medical image segmentation. IEEE Trans Neural Netw Learn Syst, 2024, 1-15.

1. Han B, Zheng R, Zeng H, et al. Cancer incidence and mortality in China, 2022. J Natl Cancer Cent, 2024, 4(1): 47-53.
2. Siegel RL, Miller KD, Wagle NS, et al. Cancer statistics, 2023. CA Cancer J Clin, 2023, 73(1): 17-48.
3. 罗汶鑫, 杨澜, 王成弟, 等. 肺癌筛查与早期诊断的研究现状与挑战. 中国科学: 生命科学, 2022, 52(11): 1603-1611.Luo WX, Yang L, Wang CD, et al. Current status and challenges of research on lung cancer screening and early diagnosis. Sci Sin Vitae, 2022, 52(11): 1603-1611.
4. Herth FJ, Eberhardt R, Sterman D, et al. Bronchoscopic transparenchymal nodule access (BTPNA): First in human trial of a novel procedure for sampling solitary pulmonary nodules. Thorax, 2015, 70(4): 326-332.
5. 张皓, 韩铭钧. 肺部疾病中肺血管及肺血流变化的CT研究. 国外医学(临床放射学分册), 2006, 29(4): 250-253.Zhang H, Han MJ. CT study of lung vasculature and blood flow changes in lung diseases. Foreign Med Sci (Clin Radiol F), 2006, 29(4): 250-253.
6. 段辉宏, 龚敬, 王丽嘉, 等. 肺部CT图像气管树分割技术研究进展. 中国生物医学工程学报, 2018, 37(6): 739-748.Duan HH, Gong J, Wang LJ, et al. A review of segmentation of pulmonary airway in lung CT scans. Chin J Biomed Eng, 2018, 37(6): 739-748.
7. Zheng H, Qin Y, Gu Y, et al. Alleviating class-wise gradient imbalance for pulmonary airway segmentation. IEEE Trans Med Imaging, 2021, 40(9): 2452-2462.
8. Lassen B, van Rikxoort EM, Schmidt M, et al. Automatic segmentation of the pulmonary lobes from chest CT scans based on fissures, vessels, and bronchi. IEEE Trans Med Imaging, 2013, 32(2): 210-222.
9. Chen B, Kitasaka T, Honma H, et al. Automatic segmentation of pulmonary blood vessels and nodules based on local intensity structure analysis and surface propagation in 3D chest CT images. Int J Comput Assist Radiol Surg, 2012, 7(3): 465-482.
10. Helmberger M, Pienn M, Urschler M, et al. Quantification of tortuosity and fractal dimension of the lung vessels in pulmonary hypertension patients. PLoS One, 2014, 9(1): e87515.
11. Xu S, Zhang Z, Zhou Q, et al. A pulmonary vascular extraction algorithm from chest CT/CTA images. J Healthc Eng, 2021, 2021: 5763177.
12. Gu X, Wang J, Zhao J, et al. Segmentation and suppression of pulmonary vessels in low-dose chest CT scans. Med Phys, 2019, 46(8): 3603-3614.
13. Ronneberger O, Fischer P, Brox T. U-Net: Convolutional networks for biomedical image segmentation. arXiv:1505.04597.
14. Chen LC, Zhu Y, Papandreou G, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Ferrari V, Hebert M, Sminchisescu C, et al. (eds) Computer Vision–ECCV 2018. ECCV 2018. Lecture Notes in Computer Science, vol 11211. Springer, Cham.
15. Çiçek Ö, Abdulkadir A, Lienkamp SS, et al. 3D U-Net: Learning dense volumetric segmentation from sparse annotation. In: Ourselin S, Joskowicz L, Sabuncu M, et al. (eds) Medical Image Computing and Computer-assisted Intervention–MICCAI 2016. MICCAI 2016. Lecture Notes in Computer Science, vol 9901. Springer, Cham.
16. Lee HY, Chung YJ, Wang HJ, et al. Automated 3D segmentation of the aorta and pulmonary artery for predicting outcomes after thoracoscopic lobectomy in lung cancer patients. Front Oncol, 2022, 12: 1027036.
17. Luo G, Wang K, Liu J, et al. Efficient automatic segmentation for multi-level pulmonary arteries: The PARSE challenge. arXiv: 2304.03708.
18. Wang HJ, Chen LW, Lee HY, et al. Automated 3D segmentation of the aorta and pulmonary artery on non-contrast-enhanced chest computed tomography images in lung cancer patients. Diagnostics (Basel), 2022, 12(4): 967.
19. Wu Y, Qi S, Wang M, et al. Transformer-based 3D U-Net for pulmonary vessel segmentation and artery-vein separation from CT images. Med Biol Eng Comput, 2023, 61(10): 2649-2663.
20. Kundu S, Karale V, Ghorai G, et al. Nested U-Net for segmentation of red lesions in retinal fundus images and sub-image classification for removal of false positives. J Digit Imaging, 2022, 35(5): 1111-1119.
21. Milletari F, Navab N, Ahmadi SA. V-Net: Fully convolutional neural networks for volumetric medical image segmentation. arXiv:1606.04797.
22. Aydin OU, Taha AA, Hilbert A, et al. On the usage of average Hausdorff distance for segmentation performance assessment: Hidden error when used for ranking. Eur Radiol Exp, 2021, 5(1): 4.
23. Shen D, Wu G, Suk HI. Deep learning in medical image analysis. Annu Rev Biomed Eng, 2017, 19: 221-248.
24. Lai H, Fu S, Zhang J, et al. Prior knowledge-aware fusion network for prediction of macrovascular invasion in hepatocellular carcinoma. IEEE Trans Med Imaging, 2022, 41(10): 2644-2657.
25. Wu Y, Wu G, Lin J, et al. Role exchange-based self-training semi-supervision framework for complex medical image segmentation. IEEE Trans Neural Netw Learn Syst, 2024, 1-15.

Chinese Journal of Clinical Thoracic and Cardiovascular Surgery

Deep learning for accurate lung artery segmentation with shape-position priors

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content