摘要
目的:探讨磁共振弥散加权成像(DWI)影像组学列线图预测乳腺癌Ki-67表达的可行性。方法:回顾性收集广东医科大学附属第二医院手术病理证实的乳腺癌患者资料,所有患者均进行Ki-67表达染色检测。将Ki-67低表达为A组(n=28),Ki-67高表达为B组(n=73),以DWI图像生成表观弥散系数(ADC)图,比较两组患者ADC图像影像组学特征与临床数据,采用LASSO降维后特征进行预测乳腺癌Ki-67表达高低并建立列线图模型。对列线图预测模型进行受试者工作特征曲线分析诊断效能。结果:两组患者ADC值、年龄、糖类抗原199、糖类抗原153、糖类抗原125、癌胚抗原均无统计学差异(P>0.05)。经过LASSO回归后共2个影像组学特征因子纳入评估预测乳腺癌Ki-67表达,LASSO的最佳调谐Lambda为-0.125 690 135 478 682,纳入影像组学特征为MinIntensity、Quantile95,并建立列线图,列线图ROC曲线下面积为0.917,最佳敏感度和特异性分别为91.7%、83.3%。结论:基于ADC图像影像组学特征可预测乳腺癌Ki-67表达高低程度,可为评估乳腺癌增殖程度和治疗预后提供无创性检测手段。
Objective To explore the feasibility of radiomics nomogram based on magnetic resonance diffusion weighted imaging for predicting the expression of Ki-67 in breast cancer.Methods A retrospective study was conducted on patients with breast cancer confirmed by surgery and pathology in the Second Affiliated Hospital of Guangdong Medical University.All patients were detected by Ki-67 expression staining,and then divided into group A(n=28,low-level expression of Ki-67)and group B(n=73,high-level expression of Ki-67).The apparent diffusion coefficient(ADC)graph was generated from diffusion weighted images,and the two groups were compared for radiomics features of ADC images and clinical data.The expression level of Ki-67 in breast cancer was predicted using the features of LASSO after dimensionality reduction,and a nomogram model was established,whose diagnostic efficiency was analyzed with receiver operating characteristic curve.Results No significant difference was observed in ADC value,age,carbohydrate antigen 199,carbohydrate antigen 153,carbohydrate antigen 125 and carcinoembryonic antigen between two groups(P>0.05).LASSO regression identified two radiomics features as predictors for the expression level of Ki-67 in breast cancer.The best tuning Lambda of LASSO was-0.125690135478682,and the included radiomics features for nomogram establishment were MinIntensity and Quantile95.The established nomogram had an area under ROC curve of 0.917,achieving a sensitivity of 91.7%and a specificity of 83.3%.Conclusion The expression of Ki-67 in breast cancer can be predicted based on the radiomics features of ADC images,which can provide a noninvasive detection method for evaluating the proliferation degree and treatment prognosis of breast cancer.
作者
许俊丽
谭学渊
温志玲
梁钰笛
XU Junli;TAN Xueyuan;WEN Zhiling;LIANG Yudi(Department of Radiology and Imaging,the Second Affiliated Hospital of Guangdong Medical University,Zhanjiang 524000,China)
出处
《中国医学物理学杂志》
2025年第7期929-934,共6页
Chinese Journal of Medical Physics
基金
湛江市科技发展专项(2022A01121)。
关键词
乳腺癌
磁共振成像
弥散加权成像
表观弥散系数
KI-67表达
列线图
breast cancer
magnetic resonance imaging
diffusion weighted imaging
apparent diffusion coefficient
Ki-67 expression
nomogram
作者简介
许俊丽,主管技师,E-mail:zjxujunli@163.com。
