Whole-tumor histogram models based on quantitative maps from synthetic MRI for predicting axillary lymph node status in invasive ductal breast cancer.

Purpose: To investigate the potential of using histogram analysis of synthetic MRI (SyMRI) images before and after contrast enhancement to predict axillary lymph node (ALN) status in patients with invasive ductal carcinoma (IDC).

Methods: From January 2022 to October 2022, a total of 212 patients with IDC underwent breast MRI examination including SyMRI. Standard T2 weight images, DCE-MRI and quantitative maps of SyMRI were obtained. 13 features of the entire tumor were extracted from these quantitative maps, standard T2 weight images and DCE-MRI. Statistical analyses, including Student's t-test, Mann-Whiney U test, logistic regression, and receiver operating characteristic (ROC) curves, were used to evaluate the data. The mean values of SyMRI quantitative parameters derived from the conventional 2D region of interest (ROI) were also evaluated.

Results: The combined model based on T1-Gd quantitative map (energy, minimum, and variance) and clinical features (age and multifocality) achieved the best diagnostic performance in the prediction of ALN between N (with non-metastatic ALN) and N group (metastatic ALN ≥ 1) with the AUC of 0.879. Among individual quantitative maps and standard sequence-derived models, the synthetic T1-Gd model showed the best performance for the prediction of ALN between N and N groups (AUC = 0.823). Synthetic T2_entropy and PD-Gd_energy were useful for distinguishing N group (metastatic ALN ≥ 1 and ≤ 3) from the N group (metastatic ALN > 3) with an AUC of 0.722.

Conclusions: Whole-tumor histogram features derived from quantitative parameters of SyMRI can serve as a complementary noninvasive method for preoperatively predicting ALN metastases.