Enhancing pathological complete response prediction in stage II/III breast cancer: the role of radiomics signatures of MRI and its association with tumor microenvironment heterogeneity

The pathological factors for predicting the benefit of Neoadjuvant chemotherapy (NACT) in breast cancer remains limited and challenged by substantial intertumoral heterogeneity. We want to explore and compare the value of radiomic features derived from both the tumor and the peritumoral region on MRI in the early prediction of pathological complete response(pCR) and identify radiomic characteristics associated with pathological complete response (pCR) among patients receiving neoadjuvant chemotherapy (NACT). In this study, we trained and validated 2 radiomics machine learning models based on different ROIs: tumor only and tumor with peritumoral region. The training dataset consists of 351 patients with complete MRI data and electronic health records. Area under Curve (AUC) is used to quantify the overall accuracy of the model and DeLong’s test determines if there is a significant difference between the ROC curves of two models.Then we performed subgroup analysis to identify the subgroup who could benefit from NACT. Finally, we analyzed the global feature importance for the model to identify the important factors. A total of 351 patients were included in this study. We identified that if the value of Informational Measure of Correlation(IMC1) < -0.188 in triple negative breast patients(TNBC), the pCR is likely to be positive(pCR vs. non-pCR, P = 0.044 ). Meanwhile, among HER2-positive patients, an IMC1 value below − 0.247 was associated with a higher likelihood of achieving pCR after NACT (pCR vs. non-pCR, P = 0.046). The model based on the tumor with peritumoral region outperforms that based on tumor only in AUC(0.71 vs. 0.60), with statistically significant difference (p-value = 0.023).Besides, the model identified several key factors that significantly influence patient pCR, including HR, IMC1, and Large Dependence High Grade Level Emphasis (LDHGLE).TNBC patients with IMC1 <-0.188(pCR vs. non-pCR, p-value = 0.044 ) and HER2-positive patients with IMC1 <-0.247(pCR vs. non-pCR, p-value = 0.046) showed higher probabilities of achieving pCR after NACT. The model incorporating both tumor and peritumoral region radiomics features outperformed the tumor-only model (AUC 0.71 vs. 0.60, p-value = 0.023). HR status, IMC1, and LDHGLE were identified as the most significant predictors of pCR. MRI radiomics incorporating information from the tumor and peritumoral region may provide a more comprehensive characterization of breast cancer heterogeneity and improve early prediction of response to NACT. The identified radiomic patterns may help support treatment stratification in molecularly distinct breast cancer subgroups, although further prospective validation is required before clinical implementation.