Keywords
Pulmonary nodule
CT diagnosis
Submitted : 2024-12-17
Accepted : 2025-01-01
Published : 2025-01-16
Abstract
Objective: To explore the application value of artificial intelligence-assisted diagnostic systems in the computed tomography (CT) diagnosis of pulmonary nodules. Methods: A total of 80 patients with pulmonary nodules, treated from June 2023 to May 2024, were included. All patients underwent pathological examination and CT scans, with pathological results serving as the gold standard. The diagnostic performance of CT alone and CT combined with the artificial intelligence-assisted diagnostic system was analyzed, and differences in CT imaging features and evaluation results of benign and malignant pulmonary nodules were compared. Results: The sensitivity, specificity, and accuracy of CT combined with the artificial intelligence-assisted diagnostic system were significantly higher than those of CT alone (P < 0.05). Moreover, the false-positive and false-negative rates were significantly lower for the combined approach compared to CT alone (P < 0.05). Conclusion: The artificial intelligence-assisted diagnostic system effectively identifies malignant features in pulmonary nodules, providing valuable clinical reference data and enhancing diagnostic accuracy and efficiency.
References
Liu YB, Li Q, Zhou W, et al., 2022, The Diagnostic and Nodule-Type Assessment Value of Artificial Intelligence-Based Chest CT Combined with AI Diagnostic Systems in Patients with Suspected Pulmonary Nodules. Artif Intell Mod Biomed Prog, 22(5): 955–959.
Jin CW, Guo YM, 2019, Application and Quality Control of Artificial Intelligence-Assisted Diagnostic Technology in Low-Dose CT Screening for Pulmonary Nodules. Chin J Radiol, 53(1): 6–8.
Wang HS, Shen JK, Zan PF, et al., 2021, Imaging Characteristics and Prognosis Analysis of Pulmonary Nodules of Uncertain Nature in Osteosarcoma Patients Using Artificial Intelligence. Chin J Bone Joint, 10(11): 834–839.
Zhou YP, Li S, Zhang X, et al., 2019, Clinical Application Value Study of an Artificial Intelligence-Based Deep Neural Network-Assisted Diagnostic System for High-Resolution MRI Rectal Lymph Nodes. Chin J Surg, 57(2): 108–113.
Huang L, Li YX, Wu LL, et al., 2020, Research on an Artificial Intelligence-Assisted Diagnostic System Based on Deep Learning for Benign and Malignant Gastric Ulcers. Chin J Dig Endosc, 37(7): 476–480.
Yi L, Zuo MJ, 2023, Research Progress of CT Radiomics-Based Artificial Intelligence in the Differential Diagnosis of Pulmonary Nodules. Pract Radiol, 39(11): 1894–1896.
Qiu L, Fang XM, Chen HW, 2019, Research Progress in Artificial Intelligence-Assisted CT for Distinguishing Benign and Malignant Pulmonary Nodules. Clin Radiol J, 38(12): 2453–2456.
Mao YX, Ren CY, Li SZ, et al., 2021, Diagnostic Value of Artificial Intelligence Combined with Low-Dose CT in the Screening of Pulmonary In Situ Carcinoma. Chin Med Equip, 18(12): 45–48.
Luo YM, Zhao L, Jiang YL, et al., 2022, Evaluation of the Application Value of Artificial Intelligence Diagnostic Systems in Pulmonary Nodule CT Screening. South China J Def Med, 36(7): 521–524.
Shen J, Liu YJ, Mo M, et al., 2023, Effectiveness Study of Artificial Intelligence-Assisted Ultrasound for Identifying Breast Lesions in Chinese Women. Chin J Cancer, 33(11): 1002–1008.
Liu HL, Chen GP, Tao JS, et al., 2022, Application Value of a CT Thin-Slice Imaging Feature-Based Pulmonary Nodule Grading Assessment System in Distinguishing Benign and Malignant Pulmonary Nodules. Clin Pulmonol, 27(1): 102–105.
Yang F, Fan J, Tian ZJY, et al., 2020, Preliminary Study on Artificial Intelligence-Based CT Screening for Subsolid Pulmonary Nodules in a Population. Chin J Thorac Cardiovasc Surg, 36(3): 145–150.
Chinese Medical Association Respiratory Disease Branch Lung Cancer Group, Chinese Lung Cancer Prevention and Treatment Alliance Expert Group, 2018, Chinese Expert Consensus on the Diagnosis and Treatment of Pulmonary Nodules (2018 Version). Chin J Tuberc Respir Dis, 41(10): 763–771.