基于增强CT影像组学鉴别胸腺瘤组织学分型

目的 观察基于增强CT影像组学鉴别胸腺瘤组织学分型的价值。方法 回顾性分析226例经病理证实的胸腺瘤患者,按7∶3比例将其分为训练集(n=159)及测试集(n=67);利用最大相关最小冗余(mRMR)及最小绝对收缩和选择算子(LASSO)算法筛选最佳影像组学特征,构建鉴别胸腺瘤组织学分型的影像组学模型;以单因素及多因素logistic回归分析筛选鉴别胸腺瘤组织学分型相关的临床及CT表现,构建临床模型和联合影像组学特征及临床、CT特征的影像组学列线图。绘制受试者工作特征(ROC)曲线,计算曲线下面积(AUC),评价3种模型鉴别胸腺瘤组织学分型的效能并比较其差异,评价影像组学列线图的临床价值。结果 最终基于增强动脉期及静脉期CT筛选出19个最佳影像组学特征,以建立影像组学模型。临床模型由患者年龄、重症肌无力、病灶CT表现形态、侵犯邻近组织及动脉期CT值构成。训练集中,影像组学列线图及影像组学模型区分低危组胸腺瘤与高危组胸腺瘤的AUC (0.91、0.89)均高于临床模型(0.79,Z=3.62、2.49,P均＜0.05),而影像组学列线图与影像组学模型AUC差异无统计学意义(Z=1.54,P=0.12);3种模型在测试集中的AUC差异均无统计学意义(P均＞0.05)。阈值概率为0.1~1.0时,影像组学列线图的临床获益均大于临床模型及影像组学模型。结论 基于增强CT影像组学模型和基于临床、CT表现及影像组学特征的影像组学列线图均有利于鉴别胸腺瘤组织学分型,后者临床获益更高。     

CT影像组学联合CT特征预测肺亚实性结节侵袭性

目的 观察CT影像组学联合CT特征预测肺亚实性结节侵袭性的价值。方法 回顾性分析170例肺亚实性结节患者资料,包括6例非典型腺瘤样增生(AAH)、12例原位腺癌(AIS)、58例微浸润性腺癌(MIA)及94例浸润性腺癌(IAC),将AAH、AIS和MIA归为非侵袭组、IAC归为侵袭组。按7∶3比例将患者分为训练集(n=119,含5例AAH、9例AIS、36例MIA及69例IAC)和验证集(n=51,含1例AAH、3例AIS、22例MIA及25例IAC)。采用单因素及logistic回归分析训练集患者一般资料及病灶CT表现,筛选预测肺亚实性结节侵袭性的独立危险因素并建立CT模型;基于训练集提取及筛选病灶最佳影像组学特征,以之构建影像组学模型。基于CT模型及影像组学模型构建联合模型,并以列线图将其可视化。绘制受试者工作特征(ROC)曲线,计算曲线下面积(AUC),基于验证集评估各模型诊断效能;以校准曲线评价联合模型的校准程度。结果 CT所示结节长径和最大CT值为预测肺亚实性结节为IAC的CT相关独立危险因素,以之构建CT模型。基于训练集筛选出6个最佳影像组学特征并构建影像组学模型。CT模型、影像组学模型及联合模型预测验证集肺亚实性结节侵袭性的AUC分别为0.772、0.785及0.869;联合模型的AUC高于CT模型(Z=2.336,P=0.019)而与影像组学模型差异无统计学意义(Z=1.925,P=0.054),其预测结果与实际结果的一致性较高。结论 CT影像组学联合CT特征可有效预测肺亚实性结节侵袭性。     

影像组学联合CT特征鉴别儿童支原体与非支原体肺炎

目的 观察影像组学联合CT特征鉴别儿童支原体肺炎(MP)与非MP的价值。方法 回顾性收集153例肺炎患儿,根据支原体RNA检测结果分为MP组(n=101)与非MP组(n=52);按7∶3比例分为训练集(n=107,含71例MP、36例非MP)和验证集(n=46,含30例MP、16例非MP)。比较2组CT表现,以F test算法基于训练集数据筛选6个最佳CT征象,以逻辑回归(LR)方法构建CT模型。基于训练集提取及筛选最佳影像组学特征,分别以LR、支持向量机(SVM)、随机森林(RF)、线性判别分析(LDA)及随机梯度下降法(SGD)分类器构建机器学习(ML)模型;基于最佳CT征象及影像组学特征构建CT-ML模型。绘制受试者工作特征曲线,计算曲线下面积(AUC)评估各模型鉴别MP与非MP的效能。结果 病变累及右肺上、中、下叶,支气管壁增厚、树芽征及边缘回缩征为最佳CT征象,以之构建的CT_LR在验证集的AUC为0.710。验证集中,ML_LR、ML_SVM、ML_RF、ML_LDA及ML<...     

基于CT影像组学预测临床ⅠA期老年非小细胞肺癌淋巴结转移

目的探讨基于胸部增强CT影像组学模型预测临床ⅠA期非小细胞肺癌(NSCLC)老年患者淋巴结转移(LNM)的价值。方法回顾性分析361例临床ⅠA期NSCLC老年患者术前增强CT及临床资料。术后病理显示其中87例LNM(LNM组)、274例无LNM(无LNM组),比较2组临床及影像学表现差异。提取术前增强CT影像学特征,进行归一化和降维,采用最小绝对收缩选择算子(LASSO)法筛选最优影像组学特征,建立影像组学模型。按7∶3比例将患者分为训练组和测试组,于训练组中以10次交叉验证法获得最佳影像组学预测模型。根据临床ⅠA期NSCLC老年患者LNM影响因素建立LNM临床预测模型,以之预测训练组和测试组LNM,并以ROC曲线评价2种模型对于训练组和测试组的诊断效能。结果共于所有病灶中提取396个影像组学特征,经归一化后采用LASSO法获得5个最佳影像组学特征建立影像组学模型,并获得最佳影像组学模型,以之预测训练组和测试组LNM的AUC值分别为0.816和0.797,均高于临床模型(0.650和0.686,P均<0.05)。结论基于胸部增强CT的影像组学模型可用于预测临床ⅠA期NSCLC老年患者LNM。     

基于CT影像组学模型鉴别腺性膀胱炎与膀胱癌

目的探讨基于CT的影像组学模型对腺性膀胱炎(CG)与膀胱癌的鉴别诊断效能。方法回顾性分析经病理证实的40例CG (CG组)和70例膀胱癌(膀胱癌组),均于术前接受盆腔平扫和三期增强CT扫描。分别在平扫、动脉期、静脉期及延迟期CT图像上勾画三维容积感兴趣区(VOI),提取影像组学特征。将按7∶3随机将患者分入训练集与测试集。对各期CT影像组学特征数据行归一化处理,以最小冗余最大相关法(mRMR)、最小绝对收缩和选择算法(LASSO)及5折交叉验证进行特征降维;采用多因素Logistic回归分析建立影像组学模型。以受试者工作特征(ROC)曲线评价各模型的诊断效能,采用Delong检验评价其效能差异,以决策曲线分析评估模型临床应用价值。采用Hosmer-Lemeshow检验和校正曲线评估模型拟合度。结果分别基于平扫、动脉期、静脉期、延迟期影像组学特征建立了模型1、2、3、4,各纳入4、7、5及6个特征;其鉴别诊断CG与膀胱癌的曲线下面积(AUC)均0.80,且Delong检验表明不同模型间AUC值差异无统计学意义(P均0.05)。模型2在测试组的AUC=0.939,高于其他模型。决策曲线分析表明,模型2用于临床鉴别CG与膀胱癌的净获益最高,Hosmer Lemeshow拟合优度检验显示模型2预测结果与实际结果差异无统计学意义(训练集:χ~2=8.75,P=0.36;测试集:χ~2=4.72,P=0.79);校正曲线显示模型2的拟合效果较好。结论基于各时相盆腔CT影像组学模型均可用于辅助临床鉴别诊断CG与膀胱癌,其中基于动脉期影像组学模型的诊断效能最高。     

增强CT影像组学鉴别卵巢良性与交界性浆液性肿瘤

目的建立基于增强CT的影像组学模型,探讨其鉴别卵巢浆液性囊腺瘤(SC)与交界性浆液性肿瘤(SBT)的诊断价值。方法回顾性分析经病理证实的49例卵巢SC患者及31例SBT患者的CT资料。由2名医师分别采用AK软件分析CT图像,勾画ROI,提取影像组学参数。对获得的影像组学特征参数进行多因素Logistic回归分析,建立预测模型;采用ROC曲线分析预测模型对卵巢SC与SBT的诊断效能。结果共提取396个影像组学参数,经降维处理后得到5个特征参数,分别为Percentile_(10)、Percentile_(15)、SA、LRHGLE_(a90,o1)及LRHGLE_(a90,o7)。2名医师提取参数的一致性良好(组内相关系数均0.75)。以上述5个特征参数构建Radscore预测模型,在训练集中Radscore模型对鉴别诊断卵巢SC与SBT的AUC、敏感度、特异度分别为0.90、0.91、0.79,在测试集的AUC、敏感度、特异度分别为0.86、0.90、0.73。结论基于增强CT的影像组学模型能够有效鉴别卵巢SC与SBT。     

基于CT影像组学鉴别良恶性肺结节应用进展

影像组学指自影像学图像中提取高通量影像学特征,通过筛选特征建立模型,实现诊断和鉴别诊断疾病、评估疗效及预测预后等的人工智能技术。应用CT影像组学为鉴别良恶性肺结节提供了新契机。本文就影像组学概念、CT成像方法及其在鉴别诊断良恶性肺结节中的应用进展进行综述。     

CT影像组学标签预测肺腺癌表皮生长因子受体基因敏感突变

目的建立基于CT平扫图像的影像组学标签,探讨其用于预测肺腺癌表皮生长因子受体(EGFR)基因敏感突变的可行性。方法根据EGFR基因突变情况将80例肺腺癌患者分为EGFR敏感组(n=37)及EGFR不敏感组(n=43)。收集2组肺部病灶CT平扫主观影像征象,并提取影像组学特征;采用LASSO法进行特征挑选,以多因素Logistic回归分别建立主观影像征象模型、影像组学标签及融合模型,采用ROC曲线评估各模型预测EGFR基因敏感突变的效能。结果 EGFR敏感组与不敏感组间CT主观影像征象差异均无统计学意义(P均0.05)。通过特征选择,确定CT影像组学标签由4个影像组学特征构成。主观影像征象模型(AUC=0.66)、影像组学标签(AUC=0.77)及融合模型(AUC=0.83)预测EGFR基因敏感突变的效能差异均有统计学意义(P均0.05),以融合模型预测的效能最优。结论基于CT平扫图像建立的影像组学标签能够预测肺腺癌EGFR基因敏感突变。     

基于CT平扫影像组学鉴别≤2 cm甲状腺良恶性结节

目的观察基于CT平扫影像组学模型鉴别直径≤2 cm甲状腺良恶性结节的价值。方法回顾性分析97例经手术病理证实直径≤2 cm甲状腺结节患者,按7∶3比例将其随机分为训练组(n=67)及验证组(n=30)。提取训练组病灶的影像组学特征并进行预处理,采用最小绝对收缩和选择算子(LASSO)方法筛选最优影像组学特征;以二元Logistic回归方法建立鉴别甲状腺结节良恶性的影像组学模型,计算训练组中良恶性结节的影像组学评分,于验证组中进行验证。以ROC曲线法评估影像组学模型在训练组及验证组中的诊断效能。结果训练组25例良性病变和42例恶性病变;验证组10例良性、20例恶性病变。共于训练组病灶中提取848个影像组学特征,经预处理及筛选获得8个最优影像组学特征,建立鉴别直径≤2 cm甲状腺良恶性结节的影像组学模型。2组良性结节影像组学评分[-0.08(-1.96,0.78)、0.11(-0.96,0.65)]均低于恶性结节[1.20(0.80,2.56)、1.03(0.80,2.47),t=-3.29、-3.12,P均<0.01]。影像组学模型鉴别训练组及验证组甲状腺良恶性病变的敏感度分别为0.77、0.74,特异度分别为0.79、0.91,AUC分别为0.84、0.88(D=0.35,P=0.73)。结论基于CT平扫影像组学鉴别直径≤2 cm甲状腺良恶性结节具有较好的应用价值。     

CT影像组学模型鉴别诊断肺淋巴瘤与肺浸润性黏液腺癌

目的观察CT影像组学模型鉴别诊断肺淋巴瘤与肺浸润性黏液腺癌(PIMA)的价值。方法回顾性分析经病理证实的34例肺淋巴瘤(淋巴瘤组)及64例PIMA患者(PIMA组),按7∶3比例将其随机分入训练集和验证集。于胸部CT纵隔窗图像上沿病灶边缘手动勾画三维容积感兴趣区(VOI),提取影像组学特征参数。以最小冗余最大相关、LASSO十折交叉验证进行特征降维,以多因素Logistic回归分别构建影像组学标签、影像学特征模型及二者融合的个体化预测模型(以列线图表示)。采用受试者工作特征(ROC)曲线评价各模型对肺淋巴瘤与PIMA的鉴别效能,以决策曲线分析(DCA)综合评价模型的临床效用价值。结果共获得15个影像组学参数用于构建影像组学标签;ROC曲线结果显示其鉴别训练集肺淋巴瘤与PIMA的AUC=0.84,验证集AUC=0.77。以空气支气管征、支气管扩张及胸腔积液构建影像学特征模型,训练集AUC=0.85,验证集AUC=0.81;融合列线图对训练集AUC=0.95,验证集AUC=0.92;列线图具有更高的临床效用价值。结论基于CT征象、影像组学标签构建的个体化预测模型可有效鉴别肺淋巴瘤与PIMA。     

Differentiating autoimmune pancreatitis from pancreatic ductal adenocarcinoma with CT radiomics features

PurposeThe purpose of this study was to determine whether computed tomography (CT)-based machine learning of radiomics features could help distinguish autoimmune pancreatitis (AIP) from pancreatic ductal adenocarcinoma (PDAC).Materials and MethodsEighty-nine patients with AIP (65 men, 24 women; mean age, 59.7 ± 13.9 [SD] years; range: 21–83 years) and 93 patients with PDAC (68 men, 25 women; mean age, 60.1 ± 12.3 [SD] years; range: 36–86 years) were retrospectively included. All patients had dedicated dual-phase pancreatic protocol CT between 2004 and 2018. Thin-slice images (0.75/0.5 mm thickness/increment) were compared with thick-slices images (3 or 5 mm thickness/increment). Pancreatic regions involved by PDAC or AIP (areas of enlargement, altered enhancement, effacement of pancreatic duct) as well as uninvolved parenchyma were segmented as three-dimensional volumes. Four hundred and thirty-one radiomics features were extracted and a random forest was used to distinguish AIP from PDAC. CT data of 60 AIP and 60 PDAC patients were used for training and those of 29 AIP and 33 PDAC independent patients were used for testing.ResultsThe pancreas was diffusely involved in 37 (37/89; 41.6%) patients with AIP and not diffusely in 52 (52/89; 58.4%) patients. Using machine learning, 95.2% (59/62; 95% confidence interval [CI]: 89.8–100%), 83.9% (52:67; 95% CI: 74.7–93.0%) and 77.4% (48/62; 95% CI: 67.0–87.8%) of the 62 test patients were correctly classified as either having PDAC or AIP with thin-slice venous phase, thin-slice arterial phase, and thick-slice venous phase CT, respectively. Three of the 29 patients with AIP (3/29; 10.3%) were incorrectly classified as having PDAC but all 33 patients with PDAC (33/33; 100%) were correctly classified with thin-slice venous phase with 89.7% sensitivity (26/29; 95% CI: 78.6–100%) and 100% specificity (33/33; 95% CI: 93–100%) for the diagnosis of AIP, 95.2% accuracy (59/62; 95% CI: 89.8–100%) and area under the curve of 0.975 (95% CI: 0.936–1.0).ConclusionsRadiomic features help differentiate AIP from PDAC with an overall accuracy of 95.2%.     

MRI影像组学及临床特征联合模型预测高强度聚焦超声治疗子宫肌瘤效果

目的 观察基于MRI影像组学及临床特征建立的联合模型预测高强度聚焦超声(HIFU)治疗子宫肌瘤效果的效能。方法 回顾性分析257例接受HIFU治疗的单发子宫肌瘤患者,基于治疗前盆腔轴位T2WI、T1WI、T1对比增强(T1C)及表观弥散系数(ADC)图提取病灶影像组学特征。分别以XGBoost特征选择算法及XGBoost分类器建立预测HIFU即刻消融率和随访肌瘤体积缩小率的影像组学联合临床特征模型A和B。按8∶2比例将数据集分为训练集(n=202)和测试集(n=52),采用受试者工作特征(ROC)曲线和混淆矩阵评估模型的预测效能。结果 经XGBoost算法选择后纳入10个影像组学特征,包括4个T1WI、2个T2WI、1个T1C及3个ADC图影像组学特征,结合肌瘤背侧距骶骨距离和T2WI信号强度构建模型A;纳入10个影像组学特征,含4个T1WI、3个TIC及3个ADC图影像组学特征,结合肌瘤T2WI信号强度构建模型B。ROC曲线结果显示,模型A预测训练集和测试集HIFU治疗肌瘤即刻消融率的曲线下面积(AUC)分别为0.94[95%CI(0.90,0.96)]和0.90[95%CI(0.81,0.97)],模型B预测训练集和测试集肌瘤体积缩小率的AUC分别为0.98[95%CI(0.97,0.99)]、0.91[95%CI(0.81,0.98)]。结论 MRI影像组学联合临床特征模型可有效预测HIFU治疗子宫肌瘤近期及远期效果。     

18F-FDG PET/CT影像组学预测恶性肿瘤预后

¹⁸F-FDG PET/CT影像组学可通过自动、高通量方法自PET/CT图像中提取大量定量特征。应用人工智能和机器学习技术进一步推动了¹⁸F-FDG PET/CT影像组学在恶性肿瘤预后研究的进展,有望更好地指导临床管理恶性肿瘤患者。本文对¹⁸F-FDG PET/CT影像组学用于评估常见恶性肿瘤预后进展进行综述。     

Ⅲ期结直肠癌分期分层及其临床意义探讨

目的 探讨结直肠癌新TNM分期系统的临床应用价值.方法 回顾性分析1997年11月至2002年7月诊治的192例Ⅲ期结直肠癌患者的临床病理资料,应用Log-rank检验和Cox比例风险模型分析Ⅲ期结直肠癌患者的预后因素.结果 选择根治性手术治疗的Ⅲ期结直肠癌患者192例,分为辅助化疗组和未化疗组.中位随访时间60个月,术后总5年生存率为51.0%.按AJCC第6版TNM分期标准进行分期后的5年生存率分别为ⅢA期77.8%、ⅢB期57.4%、ⅢC期33.3%,3组患者生存率比较差异有统计学意义（χ^2=17.99,P＜0.01）.辅助化疗组125例,未化疗组67例,按新TNM分期分组,ⅢA＋ⅢB患者辅助化疗组5年生存率71.4%,未化疗组38.1%,两组差异有统计学意义（χ^2=15.77,P＜0.01）,而ⅢC患者化疗和未化疗组预后差异无统计学意义（39.1%vs.24.0%,χ^2=1.94,P＞0.05）.新TNM分期对指导不同亚期的Ⅲ期患者进行个体化综合治疗具有临床实用价值.单因素分析显示：患者性别、年龄、原发肿瘤部位、手术方式与预后无关,而新TNM分期、肿瘤分化程度、CEA水平,是否接受化疗等因素与预后相关.Cox多因素分析表明,新TNM分期是反映Ⅲ期结直肠癌预后最主要的独立指标.结论 新TNM分期对估计Ⅲ期结直肠癌的预后更为精确、合理.ⅢC患者不论是否化疗预后均不满意.     

Correlation between tumor angiogenesis and invasiveness in thymic epithelial tumors

OBJECTIVE: Because it is difficult to predict the behavior of thymomas on the basis of morphology alone, other methods for determining tumor aggressiveness must be explored. This study investigated the correlation between angiogenic grade and invasiveness in thymic epithelial tumors. METHODS: Immunohistochemical studies of 46 surgically resected thymic epithelial tumors (18 noninvasive thymomas, 20 invasive thymomas, and 8 thymic carcinomas) were conducted. To highlight the microvessels, we used a specific monoclonal antibody against factor VIII. Expression of vascular endothelial growth factor and basic fibroblast growth factor was determined by using polyclonal antibodies. RESULTS: Mean microvessel density readings for noninvasive thymomas, invasive thymomas, and thymic carcinomas were 4.6 +/- 3.2, 12.4 +/- 7.5, and 34.4 +/- 16.7, respectively. Stages I, II, III, and IV of thymoma had microvessel density readings of 4.6 +/- 3.2, 8.5 +/- 4.3, 13.8 +/- 7.7, and 22.0 +/- 6.8, respectively. These findings suggest a significant correlation between microvessel density and tumor invasiveness. Vascular endothelial growth factor expression in noninvasive thymomas, invasive thymomas, and thymic carcinomas was present in 1 (5.6%) of 18, 11 (55.0%) of 20, and 5 (62.5%) of 8 patients, respectively, thereby indicating a distinct association between vascular endothelial growth factor expression and increased microvessel density. Basic fibroblast growth factor expression was present in only 8 patients. CONCLUSIONS: In patients with thymic epithelial tumors, there appears to be a significant correlation between tumor angiogenesis and invasiveness. Furthermore, our data suggests that this angiogenesis in thymic epithelial tumors might be, at least in part, dependent on vascular endothelial growth factor expression.     

Analysis of surgical treatment of Masaoka stage III-IV thymic epithelial tumors

Objective

The purpose of this study is to elucidate the outcomes after surgical resection of Masaoka stage III-IV thymic epithelial tumors.

Methods

We retrospectively reviewed patients with Masaoka stage III-IV thymic epithelial tumor who underwent surgical resection from January 1995 to January 2017. The clinicopathological features, surgical procedures, and postoperative outcomes were investigated.

Results

Thirteen patients with thymoma and 18 patients with thymic carcinoma were assessed. The postoperative Masaoka stages were III/IVa/IVb?=?8/4/1 in thymoma and III/IVa/IVb?=?11/2/5 in thymic carcinoma. In patients with thymoma, the World Health Organization pathological subtypes were A/B1/B2/B3?=?2/1/4/6. We performed combined resection and reconstruction for brachiocephalic vein or superior vena cava in 3 patients with thymoma and 7 patients with thymic carcinoma. In all patients, the patency rate of the grafts was very low for the left brachiocephalic vein and well maintained for the right brachiocephalic vein. Macroscopically and pathologically complete resection was achieved in 11 and 6 patients with thymoma, respectively, and in 15 and 9 patients with thymic carcinoma, respectively. The 10-year survival rates were 85.7% in thymoma and 70.3% in thymic carcinoma. Postoperative recurrences were observed in 2 and 9 patients with thymoma and thymic carcinoma, respectively. Recurrences were observed within 5 and 10 years after surgery in 2 patients with thymoma and within 2 years in all patients with thymic carcinoma.

Conclusions

Patients with Masaoka stage III-IV thymic epithelial tumor showed relatively favorable long-term survival after surgical treatment. Therefore, aggressive surgical resection for complete resection may be a treatment option for these conditions.

     

临床和MRI影像组学及深度学习联合模型预测初发前列腺癌骨转移

目的 基于临床、MRI影像组学及深度学习(DL)构建联合模型,评估其预测初发前列腺癌(PCa)骨转移(BM)的价值。方法 回顾性分析286例经病理证实的初发PCa,根据患者来源将其分为训练集(53例BM、121例无BM)和测试集(29例BM、83例无BM)。采用单因素分析及多因素logistic回归分析筛选初发PCa BM的临床独立风险因素,构建临床模型;基于MR T2WI和弥散加权成像(DWI)提取并筛选最佳影像组学特征,构建影像组学标签评分(Rad-score),以最佳DL特征建立DL标签评分(DL-score),进而构建影像组学-DL模型;最后基于临床独立风险因素、Rad-score及DL-score构建联合模型。绘制受试者工作特征(ROC)曲线,计算曲线下面积(AUC),评估各模型预测初发PCa BM的效能,以决策曲线分析(DCA)对比其临床获益。结果 血清前列腺特异抗原(PSA)(OR=1.003,P<0.01)及国际泌尿病理学会(ISUP)评分(OR=3.023,P=0.01)为初发PCa BM的临床独立风险因素;以之构建的临床模型预测训练集及测试集初发PCa BM的...     

肺腺癌病人血清蛋白质组构型与病理分期的关系

目的用表面增强激光解析离子化飞行时间质谱技术(SELDI-TOF-MS)建立肺腺癌病人血清蛋白质组构型,筛选相对特异标记物,并探讨其与病理分期的关系。方法肺腺癌病人71例,均经手术病理证实;正常人71名,按照性别,年龄,吸烟史与71例肺腺癌病人配对。用WCX2芯片检测各血清标本,筛选肺腺癌相对特异性蛋白质峰,并分析肺腺癌相对特异性蛋白与病理分期的关系。结果与正常人比较发现5个肺腺癌显著高表达的潜在标记物,相对分子量分别为4047.79±1.60、4203.99±1.91、4959.81±2.13、5329.30±2.55和7760.12±4.11,其中分子量为4047.79±1.60和7760.12±4.11的肺腺癌相对特异性蛋白与病理分期呈正相关。结论SELDI-TOF-MS蛋白质质谱技术是一种快速、简便易行且高通量的分析方法,能直接筛选出肺腺癌病人血清中相对特异的潜在标记物。