摘要
目的探讨双能CT(DECT)中定量碘浓度(IC)、肿瘤标志物及影像组学特征在诊断不同分化程度胃癌中的应用价值。资料与方法回顾性分析术后病理证实为胃癌,且术前接受DECT扫描的109例患者的临床资料。测量静脉期病灶IC和标准化碘浓度(NIC),并记录CA125、CA153、CA19-9、CA242、CA724、癌胚抗原(CEA)、神经元特异性烯醇化酶(NSE)等肿瘤标志物水平。根据病理分化程度将所有患者分为分化良好组23例与分化不良组86例,比较两组患者胃癌IC、NIC及各肿瘤标志物水平。绘制受试者工作特征(ROC)曲线,评价各参数诊断不同分化程度胃癌的效能。采用西门子syngo.via Frontier Radiomics软件的特征提取算法提取影像组学特征,按1︰1随机分成训练集和验证集,利用ROC曲线评价诊断不同分化程度胃癌的价值。结果86例分化不良组患者IC及NIC分别为(2.88±0.79)mg/ml和(0.60±0.18)mg/ml,均高于分化良好组的(1.94±0.46)mg/ml、(0.41±0.10)mg/ml;对应的ROC曲线下面积分别为0.861、0.848,差异有统计学意义(P<0.05)。影像组学训练集和验证集诊断不同分化程度胃癌的曲线下面积分别为0.81、0.57。两组各血清肿瘤标志物差异无统计学意义(P>0.05)。结论DECT的IC、NIC及影像组学特征有助于诊断不同分化程度的胃癌,可为术前评估其分化程度提供依据。
Purpose To explore the application value of iodine concentration(IC),tumor markers and radiomics features in the diagnosis of different degrees gastric cancer by double energy computed tomography(DECT).Materials and Methods 109 patients who underwent DECT scan and confirmed by pathology as gastric cancer after surgery were retrospectively analyzed.The IC and normalized iodine concentration(NIC)of venous stage lesions were measured,and the levels of tumor markers including CA125,CA153,CA19-9,CA242,CA724,carcinoembryonic antigen(CEA)and neuron-specific enolase(NSE)were recorded.According to the degree of pathological differentiation,all patients were divided into well-differentiated group of 23 cases and poorly-differentiated group of 86 cases,the levels of IC,NIC and various tumor markers of gastric cancer were compared between the two groups.Receiver operating characteristic(ROC)curve was drawn to evaluate the effectiveness of various parameters in diagnosing gastric cancer with different degrees of differentiation.The feature extraction algorithm of Siemens syngo.via Frontier Radiomics software was used to extract imaging radiomics features,and then were randomly divided into training set and verification set according to 1︰1 ratio,and ROC curve was used to evaluate the value of diagnosing gastric cancer with different differentiations.Results The IC and NIC of 86 patients in the poorly differentiated group were(2.88±0.79)mg/ml and(0.60±0.18)mg/ml,respectively,which were higher than those in the well-differentiated group(1.94±0.46)mg/ml and(0.41±0.10)mg/ml;the corresponding areas under the ROC curve were 0.861 and 0.848,respectively,with significant difference(P<0.05).The area under the curve of the imaging radiomics training set and the verification set for diagnosing different levels of gastric cancer were 0.81 and 0.57,respectively.There was no significant difference in serum tumor markers between the two groups(P>0.05).Conclusion The IC,NIC and imaging features of DECT are helpful for the diagnosis of differently differentiated gastric cancer,and can provide a basis for preoperative assessment of its differentiation.
作者
寸红丽
李华秀
张大福
石磊
王娜
王关顺
CUN Hongli;LI Huaxiu;ZHANG Dafu;SHI Lei;WANG Na;WANG Guanshun(Department of Radiology,Third Affiliated Hospital of Kunming Medical University,Yunnan Cancer Hospital,Kunming 650118,China)
出处
《中国医学影像学杂志》
CSCD
北大核心
2020年第9期669-672,687,共5页
Chinese Journal of Medical Imaging
基金
云南省科技厅科技计划项目[2018FE001(-251)]。
关键词
胃肿瘤
体层摄影术
X线计算机
图像处理
计算机辅助
影像组学
生物学标记
碘浓度
Stomach neoplasms
Tomography,X-ray computed
Image processing,computer-assisted
Radiomics
Biological markers
Iodine concentration