Background
The noninvasive prediction of sentinel lymph node (SLN) metastasis using quantitative magnetic resonance imaging (MRI), particularly with synthetic MRI (syMRI), is an emerging field. This study aimed to explore the potential added benefits of syMRI over conventional MRI and diffusion-weighted imaging (DWI) in predicting metastases in SLNs.
Methods
This retrospective study consecutively enrolled 101 patients who were diagnosed with breast cancer (BC) and underwent SLN biopsy from December 2022 to October 2023 at the Affiliated Hospital of Jiangnan University. These patients underwent preoperative MRI including conventional MRI, DWI, and syMRI and were categorized into two groups according to the postoperative pathological results: those with and without metastatic SLNs. MRI morphological features, DWI, and syMRI-derived quantitative parameters of breast tumors were statistically compared between these two groups. Binary logistic regression was used to separately develop predictive models for determining the presence of SLN involvement, with variables that exhibited significant differences being incorporated. The performance of each model was evaluated through receiver operating characteristic (ROC) curve analysis, including the area under the curve (AUC), sensitivity, and specificity.
Results
Compared to the group of 54 patients with BC but no metastatic SLNs, the group of 47 patients with BC and metastatic SLNs had a significantly larger maximum axis diameter [metastatic SLNs: median 2.40 cm, interquartile range (IQR) 1.50–3.00 cm; no metastatic SLNs: median 1.80 cm, IQR 1.37–2.50 cm; P=0.03], a higher proton density (PD) (78.44±11.92
vs.
69.20±10.63 pu; P<0.001), and a lower apparent diffusion coefficient (ADC) (metastatic SLNs: median 0.91×10
−3
mm
2
/s, IQR 0.79–1.01 mm
2
/s; no metastatic SLNs: median 1.02×10
−3
mm
2
/s, IQR 0.92–1.12 mm
2
/s; P=0.001). Moreover, the prediction model with maximum axis diameter and ADC yielded an AUC of 0.71 [95% confidence interval (CI): 0.618–0.802], with a sensitivity of 78.72% and a specificity of 51.85%; After addition of syMRI-derived PD to the prediction model, the AUC increased significantly to 0.86 (AUC: 0.86
vs.
0.71; 95% CI: 0.778–0.922; P=0.002), with a sensitivity of 80.85% and a specificity of 81.50%.
Conclusions
Combined with conventional MRI and DWI, syMRI can offer additional value in enhancing the predictive performance of determining SLN status before surgery in patients with BC.