人工智能量化参数预测肺结节浸润程度的临床价值  

Value of artificial intelligence quantitative parameters in predicting the infiltration of pulmonary nodules

作　　者：梁云 谢宁[1] 刁晶艳 任蒙蒙 刘曙亮 LIANG Yun;XIE Ning;DIAO Jingyan;REN Mengmeng;LIU Shuliang(Department of Thoracic Surgery,The Affiliated Yantaishan Hospital of Binzhou Medical University,Yantai,264000,Shandong,P.R.China;Department of Epidemiology,School of Public Health and Management,Binzhou Medical University,Yantai,264000,Shandong,P.R.China)

机构地区：[1]滨州医学院附属烟台山医院胸外科,山东烟台264000 [2]滨州医学院公共卫生与管理学院流行病学教研室,山东烟台264000

出　　处：《中国胸心血管外科临床杂志》2022年第7期878-885,共8页Chinese Journal of Clinical Thoracic and Cardiovascular Surgery

摘　　要：目的探讨人工智能(artificial intelligence,AI)肺结节定量参数预测肺磨玻璃结节(ground-glass nodule,GGN)浸润程度的临床价值。方法回顾性分析2019年10月—2021年5月滨州医学院附属烟台山医院连续收治168例肺腺癌患者的临床资料,其中男43例、女125例,年龄21~78(55.76±10.88)岁。部分病例表现为多发GGN,且同一患者的不同病灶作为独立样本进行分析。178个GGN被分为两组,将原位腺癌(24个)和微浸润腺癌(77个)划分为非浸润组,浸润性腺癌(77个)划分为浸润组。比较两组间肺结节AI定量参数的差异,并以受试者工作特征曲线和二元logistic回归模型评估AI定量参数对GGN病灶侵袭程度的预测价值。结果(1)两组间参数比较:除性别因素(P=0.115)外,浸润组肺结节长径[15.10(11.50,21.60)mm vs.8.90(7.65,11.15)mm]、肺结节短径[10.80(8.85,15.20)mm vs.7.40(6.10,8.95)mm]、肿瘤实性成分比值[13.58%(1.61%,63.76%)vs.0.00%(0.00%,0.67%)]、平均CT值[–347.00(–492.00,–101.50)Hu vs.–598.00(–657.50,–510.00)Hu]、最大CT值[40.00(–40.00,94.50)Hu vs.–218.00(–347.00,–66.50)Hu]、最小CT值[–584.00(–690.50,–350.00)Hu vs.–753.00(–786.00,–700.00)Hu]、结节危险度(高危结节占比,92.2%vs.66.3%)、恶性概率[91.66%(85.62%,94.92%)vs.81.81%(59.98%,90.29%)]及年龄[(59.93±8.53)岁vs.(52.04±12.10)岁]明显大于或高于非浸润组(P均<0.001)。(2)单一量化参数的预测价值最高为肺结节长径(曲线下面积=0.843),最低为危险度(曲线下面积=0.627);3种参数中任意两两联合:肺结节长径、平均CT值、肿瘤实性成分比值均可提高AI的预测价值。(3)Logistic回归分析显示,肺结节长径及平均CT值是预测浸润性腺癌的独立危险因素。(4)当肿瘤实性成分比值阈值为1.775%时,诊断浸润性腺癌灵敏度为0.753、特异度为0.851。结论AI量化参数可有效预测GGN的浸润程度,为临床医生提供可靠的参考依据。Objective To explore the clinical value of artificial intelligence(AI)quantitative parameters of pulmonary ground-glass nodules(GGN)in predicting the degree of infiltration.Methods A retrospective analysis of168 consecutive patients with 178 GGNs in our hospital from October 2019 to May 2021 was performed,including 43males and 125 females,aged 21-78(55.76±10.88)years.Different lesions of the same patient were analyzed as independent samples.Totally,178 GGNs were divided into two groups,a non-invasive group(24 adenocarcinoma in situ and 77minimally invasive adenocarcinoma),and an invasive group(77 invasive adenocarcinoma).We compared the difference of AI quantitative parameters between the two groups,and evaluated predictive valve by receiver operating characteristic curve and binary logistic regression model.Results(1)Except for the gender(P=0.115),the other parameters,such as maximal diameter[15.10(11.50,21.60)mm vs.8.90(7.65,11.15)mm],minimum diameter[10.80(8.85,15.20)mm vs.7.40(6.10,8.95)mm],proportion of consolidation/tumor ratio[13.58%(1.61%,63.76%)vs.0.00%(0.00%,0.67%)],mean CT value[–347.00(–492.00,–101.50)Hu vs.–598.00(–657.50,–510.00)Hu],CT maximum value[40.00(–40.00,94.50)Hu vs.–218.00(–347.00,–66.50)Hu],CT minimum value[–584.00(–690.50,–350.00)Hu vs.–753.00(–786.00,–700.00)Hu],danger rating(proportion of high-risk nodules,92.2%vs.66.3%),malignant probability[91.66%(85.62%,94.92%)vs.81.81%(59.98%,90.29%)]and age(59.93±8.53 years vs.52.04±12.10 years)were statistically significant between the invasive group and the non-invasive group(all P<0.001).(2)The highest predictive value of a single quantitative parameter was the maximal diameter(area under the curve=0.843),the lowest one was the risk classification(area under the curve=0.627),the combination of two among the three parameters(maximal diameter,mean CT value,and consolidation/tumor ratio)improved the predictive value entirely.(3)Logistic regression analysis showed that maximal diameter and mean CT value both were t

关 键 词：人工智能 磨玻璃结节 量化分析 肺癌 高分辨率计算机体层成像 

分 类 号：R563[医药卫生—呼吸系统] TP18[医药卫生—内科学] TP391.41[医药卫生—临床医学]