AUTHOR=Chen Xiuyuan , Xu Hao , Qi Qingyi , Sun Chao , Jin Jian , Zhao Heng , Wang Xun , Weng Wenhan , Wang Shaodong , Sui Xizhao , Wang Zhenfan , Dai Chenyang , Peng Muyun , Wang Dawei , Hao Zenghao , Huang Yafen , Wang Xiang , Duan Liang , Zhu Yuming , Hong Nan , Yang Fan 

TITLE=AI-based chest CT semantic segmentation algorithm enables semi-automated lung cancer surgery planning by recognizing anatomical variants of pulmonary vessels

JOURNAL=Frontiers in Oncology

VOLUME=Volume 12 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2022.1021084

DOI=10.3389/fonc.2022.1021084

ISSN=2234-943X

ABSTRACT=Background: The recognition of anatomical variants is essential in preoperative planning for lung cancer surgery. Although 3-dimensional (3D) reconstruction provided an intuitive demonstration of anatomical structure, the recognition process remains fully manual. To render a semi-automated approach for surgery planning, we developed an AI-based chest CT semantic segmentation algorithm that recognizes pulmonary vessels on lobular or segmental levels. Hereby, we present a retrospective validation of the algorithm comparing to surgeons’ performance. Methods: The semantic segmentation algorithm to be validated was trained on non-contrast CT scans from a single center. A retrospective pilot study was performed. An independent validation dataset was constituted by an arbitrary selection from patients who underwent lobectomy or segmentectomy in 3 institutions during Apr. 2020 to Jun. 2021. The golden standard of anatomical variants of each enrolled case was obtained via expert surgeons’ judgments based on chest CT, 3-D reconstruction, and surgical observation. The performance of the algorithm is compared against the performance of 2 junior thoracic surgery attendings based on chest CT. Results: A total of 27 cases were included in this study. The overall case-wise accuracy of the AI model was 82.8% in pulmonary vessels, compared to 78.8% and 77.0% for the 2 surgeons, respectively. Segmental artery accuracy was 79.7%, 73.6%, and 72.7%; lobular vein accuracy was 96.3%, 96.3%, and 92.6% by AI model and 2 surgeons respectively. No statistical significance was found. In subgroup analysis, the anatomic structure-wise analysis of the AI algorithm showed a significant difference in accuracies between different lobes (p = 0.012). Higher AI accuracy in the right upper lobe and left lower lobe arteries was shown. A trend of better performance in non-contrast CT was also detected. Most recognition errors by the algorithm were the misclassification of LA1+2, and LA3. Radiological parameters didn’t exhibit a significant impact on the performance of both AI and surgeons. Conclusion: The semantic segmentation algorithm achieves the recognition of segmental pulmonary artery and lobular pulmonary vein. The performance of the model approximates that of junior thoracic surgery attendings. Our work provides a novel semi-automated surgery planning approach that is potentially beneficial to lung cancer patients.