Objective To observe the efficacy of deep learning(DL)model based on PET/CT and its combination with Cox proportional hazard model for predicting progressive disease(PD)of lung invasive adenocarcinoma within 5 years a...Objective To observe the efficacy of deep learning(DL)model based on PET/CT and its combination with Cox proportional hazard model for predicting progressive disease(PD)of lung invasive adenocarcinoma within 5 years after surgery.Methods The clinical,PET/CT and 5-year follow-up data of 250 patients with lung invasive adenocarcinoma were retrospectively analyzed.According to PD or not,the patients were divided into the PD group(n=71)and non-PD group(n=179).The basic data and PET/CT findings were compared between groups,among which the quantitative variables being significant different between groups were transformed to categorical variables using receiver operating characteristic(ROC)curve and corresponding cut-off value.Multivariant Cox proportional hazard model was used to select independent predicting factors of PD of lung invasive adenocarcinoma within 5 years after surgery.The patients were divided into training,validation and test sets at the ratio of 6∶2∶2,and PET/CT data in training set and validation set were used to train model and tuning parameters to build the PET/CT DL model,and the combination model was built in serial connection of DL model and the predictive factors.In test set,the efficacy of each model for predicting PD of lung invasive adenocarcinoma within 5 years after surgery was assessed and compared using the area under the curve(AUC).Results Patients'gender and smoking status,as well as the long diameter,SUV max and SUV mean of lesions measured on PET images,the long diameter,short diameter and type of lesions showed on CT were statistically different between groups(all P<0.05).Smoking(HR=1.787[1.053,3.031],P=0.031)and lesion SUV max>4.15(HR=5.249[1.062,25.945],P=0.042)were both predictors of PD of lung invasive adenocarcinoma within 5 years after surgery.In test set,the AUC of PET/CT DL model for predicting PD was 0.847,of the combination model was 0.890,of the latter was higher than of the former(P=0.036).Conclusion DL model based on PET/CT had high efficacy for predicting PD of lung invasive adenocarcinoma within 5 years after surgery.Combining with Cox proportional hazard model could further improve its predicting efficacy.展开更多
OBJECTIVE To explore the role of resistin in lung adenocarcinoma progression and its mechanism.METHODS The effect of resistin on A549 cells proliferation was detected by MTS assay.Wound-healing and transwell assays we...OBJECTIVE To explore the role of resistin in lung adenocarcinoma progression and its mechanism.METHODS The effect of resistin on A549 cells proliferation was detected by MTS assay.Wound-healing and transwell assays were used to evaluate the influence of resistin on A549 migration and invasion.Protein expression was detected by western blot.NF-k B translocation was evaluated by immunofluorescence.The expression of resistin in tumor tissue was assayed by immunohisto-chemical staining.RESULTS Compared with para-carcinoma tissues,resistin was overexpressed in tumor tissues.Resistin didn′t significantly affect A549 proliferation,but induced migration and invasion of A549.TLR4was the functional receptor of resistin in A549 cells,and resistin can bind to the second domain of TLR4.Resistin could increase p-EGFR by TLR4,induce PI3K/Akt phosphorylation and NF-k B translocation to nuclear.High resistin expression in lung adenocarcinoma tissues was correlated significantly with metastasis.Resistin was an independent predictor of overall survival.CONCLUSION Resistin promoted A549 migration and invasion by TLR4/EGFR/NF-k B pathway.Resistin was an independent prognosis predictor of lung adenocarcinoma.展开更多
目的:探讨基于CT影像组学的机器学习模型预测肺腺癌(lung adenocarcinoma,LUAD)气腔播散(spread through air spaces,STAS)的价值,并确定最佳瘤周分析区域。方法:回顾性分析2013年1月至2017年1月浙江省肿瘤医院接受非小细胞肺癌手术治疗...目的:探讨基于CT影像组学的机器学习模型预测肺腺癌(lung adenocarcinoma,LUAD)气腔播散(spread through air spaces,STAS)的价值,并确定最佳瘤周分析区域。方法:回顾性分析2013年1月至2017年1月浙江省肿瘤医院接受非小细胞肺癌手术治疗的378例LUAD患者资料,构建肿瘤边缘外扩0、3、6、9、12 mm区域的逻辑回归、随机森林和XGBoost模型。结果:6 mm区域的XGB模型在测试集上表现最佳,其次为AUC-ROC达0.855(95%CI:0.756~0.950),9 mm区域的XGB模型。DCA分析显示6 mm和9 mm区域XGB模型临床净收益较高。特征分析显示部分小波变换特征对STAS预测贡献较大。结论:本研究初步表明基于CT影像组学的机器学习模型对预测STAS具有一定的预测价值,其中基于6 mm瘤周区域的XGB模型表现最优,有望辅助术前评估。展开更多
目的通过分析tsRNA在肺腺癌中的差异表达情况及其表达水平与患者预后的关系,进一步筛选并验证肺腺癌相关tsRNA,以了解其在肺腺癌发生和进展中的相关机制。方法基于计算医学中心数据库筛选出在肺腺癌组织和正常组织中差异表达的tsRNA;基...目的通过分析tsRNA在肺腺癌中的差异表达情况及其表达水平与患者预后的关系,进一步筛选并验证肺腺癌相关tsRNA,以了解其在肺腺癌发生和进展中的相关机制。方法基于计算医学中心数据库筛选出在肺腺癌组织和正常组织中差异表达的tsRNA;基于癌症基因组图谱(The Cancer Genome Atlas,TCGA)数据库分析tsRNA表达水平对肺腺癌患者预后的影响;基于TRFtarget2.0和tRFTar数据库预测靶基因;基于DAVID、KOBA KEGG在线网站进行基因本体论(Gene Ontology,GO)富集分析和京都基因和基因组百科全书(Kyoto Encyclopedia of Genes and Genomes,KEGG)通路分析;基于阿拉巴马大学伯明翰分校癌症数据分析门户(the University of Alabama at Birmingham CANcer data analysis Portal,UALCAN)分析靶基因在肺腺癌组织和正常组织中的表达水平。采用增殖实验、迁移实验、侵袭实验验证tRF-19-69M8LOJX在肺腺癌细胞中的生物学功能。结果与正常组织相比,tRF-19-69M8LOJX在肺腺癌组织中表达上调(log2FC=4.28,FDR<0.05)。高表达水平的tRF-19-69M8LOJX预示着更短的无进展生存期(HR=1.565,95%CI=1.142~2.145,P=0.005);过表达tRF-19-69M8LOJX促进A549细胞的增殖、迁移(P<0.001)和侵袭(P=0.009);COL1A1(P=0.002)和VCAN(P=0.022)在tRF-19-69M8LOJX过表达细胞模型中显著上调。结论tRF-19-69M8LOJX在肺腺癌组织的表达水平上调,与患者不良预后密切相关,可能在肺腺癌的发生发展中起着重要作用。展开更多
目的:基于肺腺癌原发灶的临床及影像学特征构建肺腺癌隐匿性纵隔淋巴结转移的预测模型。方法:回顾性分析南京医科大学第一附属医院2009—2019年行手术治疗和淋巴结清扫、病理结果为有/无隐匿性纵隔淋巴结转移的肺腺癌患者,收集患者的多...目的:基于肺腺癌原发灶的临床及影像学特征构建肺腺癌隐匿性纵隔淋巴结转移的预测模型。方法:回顾性分析南京医科大学第一附属医院2009—2019年行手术治疗和淋巴结清扫、病理结果为有/无隐匿性纵隔淋巴结转移的肺腺癌患者,收集患者的多个临床及影像学特征。采用单因素和多因素Logistic回归分析筛选独立预测因子,并构建多个CT特征的影像模型。建立受试者工作特征(receiver operating characteristic,ROC)曲线评估各模型的预测效能和临床实用价值。结果:在最终纳入的780例肺腺癌伴大小正常的淋巴结患者中,145例发生淋巴结转移。单因素分析结果提示,肿瘤大小、轴向位置、结节性质、形态学特征、胸膜牵拉征、胸膜毗邻类型与淋巴结转移显著相关。多因素分析结果提示,肿瘤大小(OR=1.019,95%CI:1.002~1.036,P=0.028)、结节性质(OR=0.361,95%CI:0.202~0.646,P=0.001)、胸膜牵拉(OR=1.835,95%CI:1.152~2.924,P=0.011)和纵隔胸膜毗邻(OR=1.796,95%CI:1.106~2.919,P=0.018)是隐匿性纵隔淋巴结转移的独立预测因子。基于预测因子建立的影像学模型,ROC曲线下面积(area under the curve,AUC)为0.75,灵敏度为86.2%,特异度为53.1%。结论:基于胸部CT平扫建立的影像学特征模型,在预测肺腺癌隐匿性纵隔淋巴结转移上具有较好的临床价值,可为临床医生的无创性术前决策及手术治疗方案选择提供依据。展开更多
文摘Objective To observe the efficacy of deep learning(DL)model based on PET/CT and its combination with Cox proportional hazard model for predicting progressive disease(PD)of lung invasive adenocarcinoma within 5 years after surgery.Methods The clinical,PET/CT and 5-year follow-up data of 250 patients with lung invasive adenocarcinoma were retrospectively analyzed.According to PD or not,the patients were divided into the PD group(n=71)and non-PD group(n=179).The basic data and PET/CT findings were compared between groups,among which the quantitative variables being significant different between groups were transformed to categorical variables using receiver operating characteristic(ROC)curve and corresponding cut-off value.Multivariant Cox proportional hazard model was used to select independent predicting factors of PD of lung invasive adenocarcinoma within 5 years after surgery.The patients were divided into training,validation and test sets at the ratio of 6∶2∶2,and PET/CT data in training set and validation set were used to train model and tuning parameters to build the PET/CT DL model,and the combination model was built in serial connection of DL model and the predictive factors.In test set,the efficacy of each model for predicting PD of lung invasive adenocarcinoma within 5 years after surgery was assessed and compared using the area under the curve(AUC).Results Patients'gender and smoking status,as well as the long diameter,SUV max and SUV mean of lesions measured on PET images,the long diameter,short diameter and type of lesions showed on CT were statistically different between groups(all P<0.05).Smoking(HR=1.787[1.053,3.031],P=0.031)and lesion SUV max>4.15(HR=5.249[1.062,25.945],P=0.042)were both predictors of PD of lung invasive adenocarcinoma within 5 years after surgery.In test set,the AUC of PET/CT DL model for predicting PD was 0.847,of the combination model was 0.890,of the latter was higher than of the former(P=0.036).Conclusion DL model based on PET/CT had high efficacy for predicting PD of lung invasive adenocarcinoma within 5 years after surgery.Combining with Cox proportional hazard model could further improve its predicting efficacy.
基金The project supported by National HighTech R&D Program of China(863 Program)(2012AA02A517)National Natural Science Foundation of China(81373490,81573508,81573463)Hunan Provincial Science and Technology Plan of China(2015TP1043)
文摘OBJECTIVE To explore the role of resistin in lung adenocarcinoma progression and its mechanism.METHODS The effect of resistin on A549 cells proliferation was detected by MTS assay.Wound-healing and transwell assays were used to evaluate the influence of resistin on A549 migration and invasion.Protein expression was detected by western blot.NF-k B translocation was evaluated by immunofluorescence.The expression of resistin in tumor tissue was assayed by immunohisto-chemical staining.RESULTS Compared with para-carcinoma tissues,resistin was overexpressed in tumor tissues.Resistin didn′t significantly affect A549 proliferation,but induced migration and invasion of A549.TLR4was the functional receptor of resistin in A549 cells,and resistin can bind to the second domain of TLR4.Resistin could increase p-EGFR by TLR4,induce PI3K/Akt phosphorylation and NF-k B translocation to nuclear.High resistin expression in lung adenocarcinoma tissues was correlated significantly with metastasis.Resistin was an independent predictor of overall survival.CONCLUSION Resistin promoted A549 migration and invasion by TLR4/EGFR/NF-k B pathway.Resistin was an independent prognosis predictor of lung adenocarcinoma.
文摘目的通过分析tsRNA在肺腺癌中的差异表达情况及其表达水平与患者预后的关系,进一步筛选并验证肺腺癌相关tsRNA,以了解其在肺腺癌发生和进展中的相关机制。方法基于计算医学中心数据库筛选出在肺腺癌组织和正常组织中差异表达的tsRNA;基于癌症基因组图谱(The Cancer Genome Atlas,TCGA)数据库分析tsRNA表达水平对肺腺癌患者预后的影响;基于TRFtarget2.0和tRFTar数据库预测靶基因;基于DAVID、KOBA KEGG在线网站进行基因本体论(Gene Ontology,GO)富集分析和京都基因和基因组百科全书(Kyoto Encyclopedia of Genes and Genomes,KEGG)通路分析;基于阿拉巴马大学伯明翰分校癌症数据分析门户(the University of Alabama at Birmingham CANcer data analysis Portal,UALCAN)分析靶基因在肺腺癌组织和正常组织中的表达水平。采用增殖实验、迁移实验、侵袭实验验证tRF-19-69M8LOJX在肺腺癌细胞中的生物学功能。结果与正常组织相比,tRF-19-69M8LOJX在肺腺癌组织中表达上调(log2FC=4.28,FDR<0.05)。高表达水平的tRF-19-69M8LOJX预示着更短的无进展生存期(HR=1.565,95%CI=1.142~2.145,P=0.005);过表达tRF-19-69M8LOJX促进A549细胞的增殖、迁移(P<0.001)和侵袭(P=0.009);COL1A1(P=0.002)和VCAN(P=0.022)在tRF-19-69M8LOJX过表达细胞模型中显著上调。结论tRF-19-69M8LOJX在肺腺癌组织的表达水平上调,与患者不良预后密切相关,可能在肺腺癌的发生发展中起着重要作用。
文摘目的:基于肺腺癌原发灶的临床及影像学特征构建肺腺癌隐匿性纵隔淋巴结转移的预测模型。方法:回顾性分析南京医科大学第一附属医院2009—2019年行手术治疗和淋巴结清扫、病理结果为有/无隐匿性纵隔淋巴结转移的肺腺癌患者,收集患者的多个临床及影像学特征。采用单因素和多因素Logistic回归分析筛选独立预测因子,并构建多个CT特征的影像模型。建立受试者工作特征(receiver operating characteristic,ROC)曲线评估各模型的预测效能和临床实用价值。结果:在最终纳入的780例肺腺癌伴大小正常的淋巴结患者中,145例发生淋巴结转移。单因素分析结果提示,肿瘤大小、轴向位置、结节性质、形态学特征、胸膜牵拉征、胸膜毗邻类型与淋巴结转移显著相关。多因素分析结果提示,肿瘤大小(OR=1.019,95%CI:1.002~1.036,P=0.028)、结节性质(OR=0.361,95%CI:0.202~0.646,P=0.001)、胸膜牵拉(OR=1.835,95%CI:1.152~2.924,P=0.011)和纵隔胸膜毗邻(OR=1.796,95%CI:1.106~2.919,P=0.018)是隐匿性纵隔淋巴结转移的独立预测因子。基于预测因子建立的影像学模型,ROC曲线下面积(area under the curve,AUC)为0.75,灵敏度为86.2%,特异度为53.1%。结论:基于胸部CT平扫建立的影像学特征模型,在预测肺腺癌隐匿性纵隔淋巴结转移上具有较好的临床价值,可为临床医生的无创性术前决策及手术治疗方案选择提供依据。
