Clinical application of an artificial intelligence system in predicting benign or malignant pulmonary nodules and pathological subtypes_Chinese Journal of Clinical Thoracic and Cardiovascular Surgery

Authors：

YANG Zhuowen ¹ , ZHENG Zhizhong ¹ ,  LI Bin ¹ , HUI Yiming ¹ , LIN Mingzhi ¹ , DANG Jiying ² , LI Suiyang ³ , ZHANG Chunjiao ⁴ , YANG Long ⁵ , SI Liang ⁶ , SONG Tieniu ¹ , MENG Yuqi ¹

1. Department of Thoracic Surgery, The Second Hospital & Clinical Medical School, Lanzhou University, Lanzhou, 730030, P. R. China;
2. Department of Thoracic Surgery, Liangzhou Hospital, Wuwei, 733000, Gansu, P. R. China;
3. Department of Thoracic Surgery, Jingning County People's Hospital, Jingning, 743400, Gansu, P. R. China;
4. Department of Thoracic Surgery, Jinchang People's Hospital, Jinchang, 737100, Gansu, P. R. China;
5. Department of Thoracic Surgery, Affiliated Hospital of Gansu Medical College, Pingliang, 744000, Gansu, P. R. China;
6. Department of Thoracic Surgery, The First People's Hospital of Longnan, Longnan, 746000, Gansu, P. R. China;

Corresponding?author：

LI Bin, Email: leebin@lzu.edu.cn

Keywords：

Artificial intelligence; pulmonary nodule; lung neoplasms; pathological subtype; predictive performance

DOI：

10.7507/1007-4848.202504074

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Objective To evaluate the predictive ability and clinical application value of artificial intelligence (AI) systems in the benign and malignant differentiation and pathological type of pulmonary nodules, and to summarize clinical application experience. Methods A retrospective analysis was conducted on the clinical data of patients with pulmonary nodules admitted to the Department of Thoracic Surgery, Second Hospital of Lanzhou University, from February 2016 to February 2025. Firstly, pulmonary nodules were divided into benign and non-benign groups, and the discriminative abilities of AI systems and clinicians were compared. Subsequently, lung nodules reported as precursor glandular lesions (PGL), microinvasive adenocarcinoma (MIA), and invasive adenocarcinoma (IAC) in postoperative pathological results were analyzed, comparing the efficacy of AI systems and clinicians in predicting the pathological type of pulmonary nodules. Results In the analysis of benign/non-benign pulmonary nodules, clinical data from a total of 638 patients with pulmonary nodules were included, of which there were 257 males (10 patients and 1 patient of double and triple primary lesions, respectively) and 381 females (18 patients and 1 patient of double and triple primary lesions, respectively), with a median age of 55.0 (47.0, 61.0) years. Different lesions in the same patient were analyzed as independent samples. Univariate analysis of the two groups of variables showed that, except for nodule location, the differences in the remaining variables were statistically significant (P<0.05). Multivariate logistic regression analysis showed that age, nodule type (subsolid pulmonary nodule), average density, spicule sign, and vascular convergence sign were independent influencing factors for non-benign pulmonary nodules, among which age, nodule type (subsolid pulmonary nodule), spicule sign, and vascular convergence sign were positively correlated with non-benign pulmonary nodules, while average density was negatively correlated with the occurrence of non-benign pulmonary nodules. The area under the receiver operating characteristic curve (AUC) of the malignancy risk value given by the AI system in predicting non-benign pulmonary nodules was 0.811, slightly lower than the 0.898 predicted by clinicians. In the PGL/MIA/IAC analysis, clinical data from a total of 411 patients with pulmonary nodules were included, of which there were 149 males (8 patients of double primary lesions) and 262 females (17 patients of double primary lesions), with a median age of 56.0 (50.0, 61.0) years. Different lesions in the same patient were analyzed as independent samples. Univariate analysis results showed that, except for gender, nodule location, and vascular convergence sign, the differences in the remaining variables among the three groups of PGL, MIA, and IAC patients were statistically significant (P<0.05). Multinomial multivariate logistic regression analysis showed that the differences between the parameters in the PGL group and the MIA group were not statistically significant (P>0.05), and the maximum diameter and average density of the nodules were statistically different between the PGL and IAC groups (P<0.05), and were positively correlated with the occurrence of IAC as independent risk factors. The average AUC value, accuracy, recall rate, and F1 score of the AI system in predicting lung nodule pathological type were 0.807, 74.3%, 73.2%, and 68.5%, respectively, all better than the clinical physicians’ prediction of lung nodule pathological type indicators (0.782, 70.9%, 66.2%, and 63.7% respectively). The AUC value of the AI system in predicting IAC was 0.853, and the sensitivity, specificity, and optimal cutoff value were 0.643, 0.943, and 50.0%, respectively. Conclusion This AI system has demonstrated high clinical value in predicting the benign and malignant nature and pathological type of lung nodules, especially in predicting lung nodule pathological type, its ability has surpassed that of clinical physicians. With the optimization of algorithms and the adequate integration of multimodal data, it can better assist clinical physicians in formulating individualized diagnostic and treatment plans for patients with lung nodules.

Citation： YANG Zhuowen, ZHENG Zhizhong, LI Bin, HUI Yiming, LIN Mingzhi, DANG Jiying, LI Suiyang, ZHANG Chunjiao, YANG Long, SI Liang, SONG Tieniu, MENG Yuqi. Clinical application of an artificial intelligence system in predicting benign or malignant pulmonary nodules and pathological subtypes. Chinese Journal of Clinical Thoracic and Cardiovascular Surgery, 2025, 32(8): 1086-1095. doi: 10.7507/1007-4848.202504074 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.	Xu J, Ren H, Cai S, et al. An improved faster R-CNN algorithm for assisted detection of lung nodules. Comput Biol Med, 2023, 153: 106470.
3.	Petousis P, Han SX, Aberle D, et al. Prediction of lung cancer incidence on the low-dose computed tomography arm of the National Lung Screening Trial: a dynamic Bayesian network. Artif Intell Med, 2016, 72: 42-55.
4.	National Lung Screening Trial Research Team. Reduced lung-cancer mortality with low-dose computed tomographic screening. N Engl J Med, 2011, 365(5): 395-409.
5.	Nooreldeen R, Bach H. Current and future development in lung cancer diagnosis. Int J Mol Sci, 2021, 22(16): 8661.
6.	Sauter JL, Dacic S, Galateau-Salle F, et al. The 2021 WHO classification of tumors of the pleura: advances since the 2015 classification. J Thorac Oncol, 2022, 17(5): 608-622.
7.	Murakami S, Ito H, Tsubokawa N, et al. Prognostic value of the new IASLC/ATS/ERS classification of clinical stageⅠA lung adenocarcinoma. Lung Cancer, 2015, 90(2): 199-204.
8.	周清華, 范亞光, 王穎, 等. 中國肺癌低劑量螺旋CT篩查指南(2018年版). 中國肺癌雜志, 2018, 21(2): 67-75.Zhou QH, Fan YG, Wang Y, et al. China national lung cancer screening guideline with low-dose computed tomography (2018 version). Chin J Lung Cancer, 2018, 21(2): 67-75.
9.	中華醫學會呼吸病學分會, 中國肺癌防治聯盟專家組, 白春學, 等. 肺結節診治中國專家共識(2024年版). 中華結核和呼吸雜志, 2024, 47(8): 716-729.Chinese Thoracic Society, Chinese Medical Association, Chinese Alliance Against Lung Cancer Expert Group, Bai CX, et al. Chinese expert consensus on diagnosis and treatment of pulmonary nodules (2024). Chin J Tuberc Respir Dis, 2024, 47(8): 716-729.
10.	林耀彬, 林勇斌, 趙澤銳, 等. 《人工智能在肺結節診治中的應用專家共識(2022年版)》解讀. 中國胸心血管外科臨床雜志, 2023, 30(5): 665-671.Lin YB, Lin YB, Zhao ZR, et al. Interpretation of Chinese expert consensus on artificial intelligence in diagnosis and treatment of pulmonary nodules (2022 version). Chin J Clin Thorac Cardiovasc Surg, 2023, 30(5): 665-671.
11.	Song J, Hwang EJ, Yoon SH, et al. Emerging trends and innovations in radiologic diagnosis of thoracic diseases. Invest Radiol, 2025. [Epub ahead of print].
12.	高超, 周小昀, 郭超, 等. 人工智能在胸外科規范化培訓教學中肺結節分析與肺段切除規劃的應用效果研究. 中國胸心血管外科臨床雜志, 2025, 32(4): 469-472.Gao C, Zhou XY, Guo C, et al. Application of artificial intelligence in pulmonary nodule analysis and lung segmentresection planning for standardized training in thoracic surgery. Chin J Clin Thorac Cardiovasc Surg, 2025, 32(4): 469-472.
13.	Fang W, Zhang G, Yu Y, et al. Identification of pathological subtypes of early lung adenocarcinoma based on artificial intelligence parameters and CT signs. Biosci Rep, 2022, 42(1): BSR20212416.
14.	Tong L, Yang DW, Bai CX. Revelation of American lung cancer prevention and control to China. Int J Respir, 2021, 41(5): 321-324.
15.	尹泚, 毛文杰, 李斌, 等. 人工智能系統在肺結節檢出及良惡性鑒別中的應用研究. 中華胸心血管外科雜志, 2020, 36(9): 553-556.Yin C, Mao WJ, Li B, et al. Study on the application of artificial intelligence system in the detection and differentiation of benign and malignant pulmonary nodules. Chin J Thorac Cardiovasc Surg, 2020, 36(9): 553-556.
16.	蘇志鵬, 毛文杰, 李斌, 等. 人工智能輔助診斷系統預測肺結節早期肺腺癌浸潤亞型的臨床研究. 中國肺癌雜志, 2022, 25(4): 245-252.Su ZP, Mao WJ, Li B, et al. Clinical study of artificial intelligence-assisted diagnosis system in predicting the invasive subtypes of early-stage lung adenocarcinoma appearing as pulmonary nodules. Chin J Lung Cancer, 2022, 25(4): 245-252.
17.	梁長虹, 謝辰儀, 吳磊. 腫瘤診療新方向: 人工智能與數字化醫學圖像. 蘭州大學學報(醫學版), 2023, 49(2): 1-5.Liang CH, Xie CY, Wu L. New direction in cancer diagnosis and treatment: artificial intelligence and digital medical imaging. J Lanzhou Univ Med Sci, 2023, 49(2): 1-5.
18.	Salahuddin Z, Woodruff HC, Chatterjee A, et al. Transparency of deep neural networks for medical image analysis: a review of interpretability methods. Comput Biol Med, 2022, 140: 105111.
19.	Reid M, Choi HK, Han X, et al. Development of a risk prediction model to estimate the probability of malignancy in pulmonary nodules being considered for biopsy. Chest, 2019, 156(2): 367-375.
20.	Liu HY, Zhao XR, Chi M, et al. Risk assessment of malignancy in solitary pulmonary nodules in lung computed tomography: a multivariable predictive model study. Chin Med J, 2021, 134(14): 1687-1694.
21.	Xu DM, van Klaveren RJ, de Bock GH, et al. Role of baseline nodule density and changes in density and nodule features in the discrimination between benign and malignant solid indeterminate pulmonary nodules. Eur J Radiol, 2009, 70(3): 492-498.
22.	Yang R, Hui D, Li X, et al. Prediction of single pulmonary nodule growth by CT radiomics and clinical features: a one-year follow-up study. Front Oncol, 2022, 12: 1034817.
23.	Amrane K, Thuillier P, Bourhis D, et al. Prognostic value of pre-therapeutic FDG-PET radiomic analysis in gastro-esophageal junction cancer. Sci Rep, 2023, 13(1): 5789.
24.	Heidinger BH, Anderson KR, Nemec U, et al. Lung adenocarcinoma manifesting as pure ground-glass nodules: correlating CT size, volume, density, and roundness with histopathologic invasion and size. J Thorac Oncol, 2017, 12(8): 1288-1298.
25.	Zhu J, Fan Y, Xiong Y, et al. Delineating the dynamic evolution from preneoplasia to invasive lung adenocarcinoma by integrating single-cell RNA sequencing and spatial transcriptomics. Exp Mol Med, 2022, 54(11): 2060-2076.

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. Xu J, Ren H, Cai S, et al. An improved faster R-CNN algorithm for assisted detection of lung nodules. Comput Biol Med, 2023, 153: 106470.
3. Petousis P, Han SX, Aberle D, et al. Prediction of lung cancer incidence on the low-dose computed tomography arm of the National Lung Screening Trial: a dynamic Bayesian network. Artif Intell Med, 2016, 72: 42-55.
4. National Lung Screening Trial Research Team. Reduced lung-cancer mortality with low-dose computed tomographic screening. N Engl J Med, 2011, 365(5): 395-409.
5. Nooreldeen R, Bach H. Current and future development in lung cancer diagnosis. Int J Mol Sci, 2021, 22(16): 8661.
6. Sauter JL, Dacic S, Galateau-Salle F, et al. The 2021 WHO classification of tumors of the pleura: advances since the 2015 classification. J Thorac Oncol, 2022, 17(5): 608-622.
7. Murakami S, Ito H, Tsubokawa N, et al. Prognostic value of the new IASLC/ATS/ERS classification of clinical stageⅠA lung adenocarcinoma. Lung Cancer, 2015, 90(2): 199-204.
8. 周清華, 范亞光, 王穎, 等. 中國肺癌低劑量螺旋CT篩查指南(2018年版). 中國肺癌雜志, 2018, 21(2): 67-75.Zhou QH, Fan YG, Wang Y, et al. China national lung cancer screening guideline with low-dose computed tomography (2018 version). Chin J Lung Cancer, 2018, 21(2): 67-75.
9. 中華醫學會呼吸病學分會, 中國肺癌防治聯盟專家組, 白春學, 等. 肺結節診治中國專家共識(2024年版). 中華結核和呼吸雜志, 2024, 47(8): 716-729.Chinese Thoracic Society, Chinese Medical Association, Chinese Alliance Against Lung Cancer Expert Group, Bai CX, et al. Chinese expert consensus on diagnosis and treatment of pulmonary nodules (2024). Chin J Tuberc Respir Dis, 2024, 47(8): 716-729.
10. 林耀彬, 林勇斌, 趙澤銳, 等. 《人工智能在肺結節診治中的應用專家共識(2022年版)》解讀. 中國胸心血管外科臨床雜志, 2023, 30(5): 665-671.Lin YB, Lin YB, Zhao ZR, et al. Interpretation of Chinese expert consensus on artificial intelligence in diagnosis and treatment of pulmonary nodules (2022 version). Chin J Clin Thorac Cardiovasc Surg, 2023, 30(5): 665-671.
11. Song J, Hwang EJ, Yoon SH, et al. Emerging trends and innovations in radiologic diagnosis of thoracic diseases. Invest Radiol, 2025. [Epub ahead of print].
12. 高超, 周小昀, 郭超, 等. 人工智能在胸外科規范化培訓教學中肺結節分析與肺段切除規劃的應用效果研究. 中國胸心血管外科臨床雜志, 2025, 32(4): 469-472.Gao C, Zhou XY, Guo C, et al. Application of artificial intelligence in pulmonary nodule analysis and lung segmentresection planning for standardized training in thoracic surgery. Chin J Clin Thorac Cardiovasc Surg, 2025, 32(4): 469-472.
13. Fang W, Zhang G, Yu Y, et al. Identification of pathological subtypes of early lung adenocarcinoma based on artificial intelligence parameters and CT signs. Biosci Rep, 2022, 42(1): BSR20212416.
14. Tong L, Yang DW, Bai CX. Revelation of American lung cancer prevention and control to China. Int J Respir, 2021, 41(5): 321-324.
15. 尹泚, 毛文杰, 李斌, 等. 人工智能系統在肺結節檢出及良惡性鑒別中的應用研究. 中華胸心血管外科雜志, 2020, 36(9): 553-556.Yin C, Mao WJ, Li B, et al. Study on the application of artificial intelligence system in the detection and differentiation of benign and malignant pulmonary nodules. Chin J Thorac Cardiovasc Surg, 2020, 36(9): 553-556.
16. 蘇志鵬, 毛文杰, 李斌, 等. 人工智能輔助診斷系統預測肺結節早期肺腺癌浸潤亞型的臨床研究. 中國肺癌雜志, 2022, 25(4): 245-252.Su ZP, Mao WJ, Li B, et al. Clinical study of artificial intelligence-assisted diagnosis system in predicting the invasive subtypes of early-stage lung adenocarcinoma appearing as pulmonary nodules. Chin J Lung Cancer, 2022, 25(4): 245-252.
17. 梁長虹, 謝辰儀, 吳磊. 腫瘤診療新方向: 人工智能與數字化醫學圖像. 蘭州大學學報(醫學版), 2023, 49(2): 1-5.Liang CH, Xie CY, Wu L. New direction in cancer diagnosis and treatment: artificial intelligence and digital medical imaging. J Lanzhou Univ Med Sci, 2023, 49(2): 1-5.
18. Salahuddin Z, Woodruff HC, Chatterjee A, et al. Transparency of deep neural networks for medical image analysis: a review of interpretability methods. Comput Biol Med, 2022, 140: 105111.
19. Reid M, Choi HK, Han X, et al. Development of a risk prediction model to estimate the probability of malignancy in pulmonary nodules being considered for biopsy. Chest, 2019, 156(2): 367-375.
20. Liu HY, Zhao XR, Chi M, et al. Risk assessment of malignancy in solitary pulmonary nodules in lung computed tomography: a multivariable predictive model study. Chin Med J, 2021, 134(14): 1687-1694.
21. Xu DM, van Klaveren RJ, de Bock GH, et al. Role of baseline nodule density and changes in density and nodule features in the discrimination between benign and malignant solid indeterminate pulmonary nodules. Eur J Radiol, 2009, 70(3): 492-498.
22. Yang R, Hui D, Li X, et al. Prediction of single pulmonary nodule growth by CT radiomics and clinical features: a one-year follow-up study. Front Oncol, 2022, 12: 1034817.
23. Amrane K, Thuillier P, Bourhis D, et al. Prognostic value of pre-therapeutic FDG-PET radiomic analysis in gastro-esophageal junction cancer. Sci Rep, 2023, 13(1): 5789.
24. Heidinger BH, Anderson KR, Nemec U, et al. Lung adenocarcinoma manifesting as pure ground-glass nodules: correlating CT size, volume, density, and roundness with histopathologic invasion and size. J Thorac Oncol, 2017, 12(8): 1288-1298.
25. Zhu J, Fan Y, Xiong Y, et al. Delineating the dynamic evolution from preneoplasia to invasive lung adenocarcinoma by integrating single-cell RNA sequencing and spatial transcriptomics. Exp Mol Med, 2022, 54(11): 2060-2076.

Chinese Journal of Clinical Thoracic and Cardiovascular Surgery

Clinical application of an artificial intelligence system in predicting benign or malignant pulmonary nodules and pathological subtypes

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content