陕西医学杂志2024，Vol.53Issue(1)：72-76,5.DOI:10.3969/j.issn.1000-7377.2024.01.016
基于瘤体及瘤周多参数MRI对乳腺病变良恶性诊断列线图预测模型的构建与评价
Construction and evaluation of nomogram prediction model for benign and malignant breast lesions based on tumor and peritumoral multi-parameter MRI
摘要
Abstract
Objective:To establish a nomogram model for differential diagnosis of benign and malignant breast lesions based on multi-parameter MRI of tumor and peritumor,and to verify its predictive efficacy.Methods:A total of 100 patients with breast lesions confirmed by pathological examination were included in the study.All patients un-derwent magnetic resonance imaging(MRI)examination and pathological examination.According to the results of pathological examination,they were divided into benign breast lesions group(n=62)and malignant breast lesions group(n=38).The clinical data,tumor parameters,peritumoral parameters and benign and malignant breast lesions were collected.Multivariate Logistic regression analysis was used to screen the risk factors of breast malignant le-sions and construct a nomogram prediction model.The receiver operating characteristic(ROC)curve and Hosmer-Lemeshow goodness of fit test were used to verify the prediction efficiency and goodness of fit of the model.Boot-strap was used for internal validation.Results:The lesion diameter,mean kurtosis(MK),MDp/t,MKp/n of peritu-moral and tumor in malignant breast lesions group were higher than those in benign breast lesions group(all P＜0.05).The apparent diffusion coefficient(ADC)value,mean diffusivity(MD),asymmetric magnetization transfer rate(MTRasym),MKp/t and MDp/n in the malignant breast lesions group were lower than those in the benign breast lesions group(all P＜0.05).Multivariate analysis showed that the increase of lesion diameter,MK,MDp/t and MKp/n,and the decrease of ADC value,MD,MTRasym,MKp/t and MDp/n were independent influencing fac-tors for breast malignant lesions(all P＜0.05).Based on the above independent influencing factors,a nomogram pre-diction model of breast malignant lesions was constructed,and the area under the curve(AUC)was 0.827.The Hos-mer-Lemeshow goodness-of-fit test showed a P value of 0.004.Using the Bootstrap method,the generated calibra-tion curve fits well.Conclusion:Tumor and peritumoral multi-parameter MRI has important predictive value for the differential diagnosis of benign and malignant breast lesions.The nomogram constructed based on the independent in-fluencing factors of malignant breast lesions has a good predictive effect and can directly predict the probability of malignant breast lesions.关键词
乳腺病变/良恶性/鉴别诊断/瘤体参数/瘤周参数/核磁共振/列线图Key words
Breast lesions/Benign and malignant/Differential diagnosis/Tumor parameters/Peritumoral pa-rameters/MRI/Nomogram分类
医药卫生引用本文复制引用
张春福,彭波,黄崎,张雪峰,才春红,海洋,张巍巍..基于瘤体及瘤周多参数MRI对乳腺病变良恶性诊断列线图预测模型的构建与评价[J].陕西医学杂志,2024,53(1):72-76,5.基金项目
黑龙江省科研基金资助项目(2021-KYYWFMY-0049) （2021-KYYWFMY-0049）
