Diagnostic value of artificial intelligence based on lung CT for benign and malignant pulmonary nodules
10.3969/j.issn.1673-9701.2024.23.010
- VernacularTitle:基于肺CT的人工智能对良恶性肺结节的诊断价值
- Author:
Dankun ZHANG
1
;
Feng CUI
;
Yongsheng ZHANG
;
Liang DU
;
Huanguo LI
;
Caiyong ZHAO
;
Zhiping LI
Author Information
1. 浙江中医药大学附属杭州市中医院放射科,浙江杭州 3100071
- Keywords:
Artificial intelligence;
Pulmonary nodules;
Computer tomography;
Benign and malignant;
Diagnostic efficacy
- From:
China Modern Doctor
2024;62(23):44-47
- CountryChina
- Language:Chinese
-
Abstract:
Objective To explore the value of artificial intelligence(AI)in the diagnosis of pulmonary nodules in terms of consistency and efficiency compared with two radiologists(physician 1 is a chief physician and physician 2 is a deputy chief physician)in the diagnosis of benign and malignant pulmonary nodules using computed tomography(CT).Methods Retrospective analysis of 201 patients with pulmonary nodules confirmed by surgery pathology at Hangzhou Municipal Hospital affiliated to Zhejiang Chinese Medical University from January 2021 to October 2022,including a total of 229 pulmonary nodules,of which 74 were benign and 155 were malignant.The consistency of AI diagnosis with two radiologists was evaluated by weighted Kappa test,and the diagnostic performance of AI with the two radiologists was evaluated by the receiver operating characteristic curve(ROC).Results In the diagnosis of the benign and malignant nature of partial solid nodules,ground-glass nodules,solid nodules,and partial ground-glass and solid plus ground-glass nodules,the consistency between AI and physician 2 was higher than that between AI and physician 1.Additionally,the area under the curve(AUC)of physician 2 was higher than that of AI and physician 1 with statistically significant differences between the AUCs of ground-glass nodules,solid nodules,and partial ground-glass and solid plus ground-glass nodules(P<0.05).In the diagnosis of the benign and malignant nature of partial solid nodules and ground-glass nodules,the AUC of physician 1 was higher than that of AI,but there was no statistically significant difference between the two(P>0.05).In the diagnosis of the benign and malignant nature of solid nodules and partial ground-glass and solid plus ground-glass nodules,the AUC of AI was higher than that of physician 1 with statistically significant differences between the two(P<0.05).In the diagnosis of the benign and malignant nature of ground-glass nodules,solid nodules,and partial ground-glass and solid plus ground-glass nodules,AI's sensitivity(97%,92%,and 94%)was higher than that of physician 1(58%,89%,and 72%)and physician 2(83%,84%,and 85%).Conclusion AI has a certain diagnostic efficacy in the diagnosis of pulmonary nodules malignancy.The overall diagnostic efficacy of the AI system used in this study is between that of physician 1 and physician 2,but its sensitivity is higher than that of the latter two.
