PURPOSE

To develop a prediction model incorporating clinicopathological information, US, and MRI to diagnose axillary lymph node (LN) metastasis with acceptable false negative rate (FNR) in patients with early stage, clinically node-negative breast cancers.

METHODS

In this single center retrospective study, the inclusion criteria comprised women with clinical T1 or T2 and N0 breast cancers who underwent preoperative US and MRI between January 2017 and July 2018. Patients were temporally divided into the development and validation cohorts. Clinicopathological information, US, and MRI findings were collected. Two prediction models (US model and combined US and MRI model) were created using logistic regression analysis from the development cohort. FNRs of the two models were compared using the McNemar test.

RESULTS

A total of 964 women comprised the development (603 women, 54 ± 11 years) and validation (361 women, 53 ± 10 years) cohorts with 107 (18%) and 77 (21%) axillary LN metastases in each cohort, respectively. The US model consisted of tumor size and morphology of LN on US. The combined US and MRI model consisted of asymmetry of LN number, long diameter of LN, tumor type, and multiplicity of breast cancers on MRI, in addition to tumor size and morphology of LN on US. The combined model showed significantly lower FNR than the US model in both development (5% vs. 32%, P < .001) and validation (9% vs. 35%, P < .001) cohorts.

CONCLUSION

Our prediction model combining US and MRI characteristics of index cancer and LN lowered FNR compared to using US alone, and could potentially lead to avoid unnecessary SLNB in early stage, clinically node-negative breast cancers.