Value of artificial intelligence-based weighted scoring system of CT findings for differentiating benign and malignant pulmo-nary nodules
Objective To explore the value of artificial intelligence(Al)-based weighted scoring system of CT findings for differentiating benign and malignant pulmonary nodules.Methods CT images of 187 patients with pulmonary nodules(215 nodules)confirmed by surgery and pathology in Hangzhou TCM Hospital Affiliated to Zhejiang Chinese Medical University from January 2021 to September 2022 were retrospectively analyzed.Pulmonary nodules on preoperative CT images were automatically identified by an Al pulmonary nodule imaging assistance diagnostic system,the related quantitative parameters were obtained,including nodule number,location,type,average diameter,volume;and the Al risk of malignancy probability for each nodule was assessed.Multivariate logistic regression analysis was used to screen for independent factors in the differential diagnosis of benign and malignant pulmonary nodules,and a primary model was constructed based on these factors;then a comprehensive weighted scoring system was developed.The diagnostic performance of various variables,primary models,and comprehensive weighted scoring system in distinguishing benign from malignant pulmonary nodules was assessed using ROC curves.Results Among 215 pulmonary nodules,69 were benign and 146 were malignant.Multivariate logistic regression analysis identified subsolid nodules(OR=4.732),Al malignancy probability＞0.6(OR=5.602),and physician's reading of malignancy(OR=28.654)as independent influencing factors in the differential diagnosis(all P＜0.01).A primary model was built based on these factors,and the Hosmer-Lemeshow test indicated good calibration of the primary model(P=0.486).In the comparison of diagnostic efficacy of comprehensive weighted scoring system,primary model,nodule characteristics,physician's reading and Al malignancy probability assessment,the area under ROC curve(AUC)of comprehensive weighted scoring system was the highest(0.929).There was no significant difference in AUC between comprehensive weighted scoring system and primary model(P＞0.05),but there were significant differences in AUC of comprehensive weighted scoring system with physician's reading,nodule characteristics and Al malignancy probability assessment(all P＜0.01).To simplify the process for radiologists to assess the malignancy risk of pulmonary nodules,the comprehensive weighted scores divided into three levels(＜4 points,4-6 points,＞6 points).The likelihood of a pulmonary nodule being diagnosed as malignant increased with higher comprehensive weighted scores.Conclusion The Al-based comprehensive weighted scoring system demonstrates high efficacy in differentiating benign and malignant pulmonary nodules,contributing to streamlining the evaluation process and clinical decision-making for radiologists.
万方数据
维普
