Objective To explore the application value of artificial intelligence and imaging doctor in pulmonary nodule detection.Methods A retrospective analysis was performed on 100 cases of chest CT.The patients were divided into 3 groups according to the different subjects.Manual film reading and 2 artificial intelligence(AI)medical image assisted diagnosis software were used for film reading diagnosis.The detection rate,missed diagnosis rate and false positive rate of pulmonary nodules in the 3 groups were calculated and compared.Results A total of 652 pulmonary nodules were detected by screening in 100 patients.The detection rate and the detection rate of nodules at different positions in the 2 AI groups were higher than those in the artificial group(P all＜0.05),while the missed diagnosis rate in the 2 AI groups was all in the artifiicial group.The detection rates of medium nodules and nodules in the two AI groups were higher than those in the artificial group(Pall＜0.05),but there was no significant difference in the detection rates of large nodules among all groups(x2=2.891,P=0.086).Conclusion AI is more effective in detecting lung nodules than imaging doctors,and can assist imaging doctors in screening and diagnosis of lung nodules.
维普
万方数据