Nomogram Based On Clinical,Pathologic And Imaging Features For Predicting The Pathological Complete Response From Minimal Residual Lesions After Neoadjuvant Therapy Of Breast Cancer

Objective To explore the value of nomogram based on clinical,pathologic and MRI features for predicting the pathological complete response(p CR)from minimal residual lesions after neoadjuvant therapy(NAT)of breast cancer patient.Methods A total of 232 consecutive women with breast cancer who underwent NAT followed by surgery from January 2018 to December 2023 were retrospectively enrolled.The women were divided into a development cohort between January 2018 and December 2021 and a validation cohort between January 2022 and December 2022.The clinicopathological factors,and pre-and post-NAT MRI variables were collected and analyzed.Logistic regression analysis was performed to identify independent factors associated with p CR,and the nomogram including the above factors was created.Nomogram performance was assessed with the area under the receiver operating characteristic curve(AUC)and calibration slope.Results A total of 167 women(mean age :48.36±9.35 years)were in the development cohort and 57(mean age : 49.03 ± 9.05 years)in the validation cohort.HER2 positivity(OR=0.18,95%CI: 0.05 ～0.73,P=0.016),high Ki-67index(OR=1.03,95 %CI: 1.01～1.06,P=0.021),and low early signal enhancement ratio(OR=0.01,95%CI: 0.00～0.12,P<0.001)were independently associated with p CR.The nomogram incorporating these variables showed good discrimination(AUC=0.87;95%CI: 0.77 ～0.94)and calibration abilities(calibration slope=0.87;95% CI: 0.77～0.97)in the validation cohort.Conclusion The nomogram based on clinical,pathological and MRI features showed good diagnostic performance in predicting p CR from minimal residual lesions after NAT of breast cancer patient.