基于MRI的影像组学特征联合NLR、SIRI对三阴性乳腺癌患者术后复发转移的预测价值OA

Objective To investigate the predictive value of magnetic resonance imaging(MRI)-based radiomics features combined with neutrophil-to-lymphocyte ratio(NLR)and systemic inflammation response index(SIRI)for postoperative recurrence and metastasis in patients with triple-negative breast cancer(TNBC).Methods A total of 95 patients pathologically diagnosed with triple-negative breast cancer(TNBC)after surgery admitted to our hospital from January 2019 to December 2022 were retrospectively enrolled.All patients underwent preoperative breast MRI examination;radiomics features were screened and radiomics scores were calculated.Meanwhile,preoperative peripheral blood test results were collected to calculate NLR and SIRI.All patients completed a 3-year postoperative follow-up and were divided into recurrence/metastasis group and non-recurrence/metastasis group based on whether recurrence or metastasis occurred during the follow-up period.General data,disease-related information,MRI radiomics scores,NLR,and SIRI levels were compared between the two groups.information,MRI radiomics scores,NLR,and SIRI were compared between the two groups.Multivariate Logistic regression analysis was used to identify independent risk factors for postoperative recurrence and metastasis in TNBC patients.Receiver operating characteristic(ROC)curves were drawn to evaluate the predictive efficacy of MRI radiomics score,NLR,SIRI alone and their combination for postoperative recurrence and metastasis in TNBC patients.Results During the 3-year follow-up,29 case of the 95 TNBC patients(30.53％)developed recurrence or metastasis,while 66 cases(69.47％)did not.There were statistically significant differences in tumor size,lymph node status,histological grade,Ki-67 index,MRI radiomics score,NLR,and SIRI between the recurrence/metastasis group and the non-recurrence/metastasis group(P＜0.05).Multivariate Logistic regression analysis showed that high MRI radiomics score,high NLR,and high SIRI were independent risk factors for postoperative recurrence and metastasis in TNBC patients(P＜0.05).The area under the curve(AUC),sensitivity,and specificity of the combined prediction using MRI radiomics score,NLR,and SIRI were all superior to those of any single indicator(P＜0.05).Conclusions MRI-based radiomics features combined with NLR and SIRI can effectively predict the risk of postoperative recurrence and metastasis in TNBC patients,providing an objective reference for individualized stratified follow-up and adjuvant treatment decision-making.