The construction and evaluation of the model combining ultrasound with MRI to predict the expression level of TNBC and Ki-67
CHENG Chen
WANG Yan
ZHAO Hongyan
YU Ming
HUANG Bufa
LI Honge
Abstract：Objective To set up models for predicting the expression level of triple-negative breast cancer(TNBC),Ki-67 by combining ultrasound with MRI,and to verify their diagnostic efficacy.Methods A total of 182 breast cancer patients who were treated in Lianyungang Hospital Affiliated to Xuzhou Medical University were retrospectively selected as the research ob-jects,including 80 patients with TNBC and 102 patients with non-triple-negative breast cancer(NTNBC).The clinicopathologi-cal data of all patients were collected,including age,pathological type,clinical stage,Ki-67 expression,etc.The postoperative pathological tissue was collected to detect Ki-67 expression.182 breast cancer patients were randomly divided into the modeling group and validating group by a ratio of 7:3.The independent risk factors predicting the high expression of TNBC Ki-67 were screened out by LASSO regression or Logistic regression analysis respectively and the predictive model was built up.The model was verified internally and externally in the validating group.The area under curve(AUC)of the receiver operating characteristic curve(ROC)was used to evaluate the discrimination of the model.The calibration curve was used to evaluate the model.Deci-sion curve analysis(DCA)was used to evaluate the clinical applicability of the model.Results 1)ADC,maximum slope,edge,boundary and RI were independent risk factors for TNBC(P<0.05).The model had good discrimination[In the validating group:AUC=0.887(95%CI:0.799-0.974)],calibration and clinical practicability(threshold probability:0%-92%);2)ADC,boundary and maximum diameter of the tumor were independent risk factors of Ki-67(P<0.05).The Ki-67 predictive model had good discrimination[AUC=0.974(95%CI:0.942-1.000)],calibration and clinical practicability(threshold probability value of 0%～100%).Conclusion The Nomogram model of TNBC and Ki-67 expression predicted by ultrasound combined with MRI pa-rameters has high diagnostic efficacy,which has good clinical application value for improving the preoperative diagnosis of TNBC and the prediction and evaluation of Ki-67 expression level.
Keywords：Triple-negative breast cancerUltrasoundMagnetic resonance imaging
Publication Date：2025-02-28
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：6( 68-73 )