Non-invasive prediction of lymph node status for patients with early-stage invasive breast cancer based on a morphological feature from ultrasound images

Background: This study aimed to estimate the value of a morphological feature on ultrasound (US) for preoperative diagnosis of axillary lymph node (ALN) status in patients with early-stage invasive breast cancer (ESIBC).

Methods: In this retrospective work, a total of 239 ESIBC patients, were recruited, and their preoperative US images and postoperative pathology results were collected. The relationship between US images based on morphological features and ALN metastasis was investigated. The tumor circularity and US-reported ALN status were developed as a nomogram to predict the ALN status.

Results: Among the 239 participants, 82 (34.31%) had ALN metastasis, and 157 (65.69%) did not. There was a statistically significant difference in tumors between participants diagnosed with and without ALN metastasis. The median value was 0.47 vs. 0.62 (P<0.001) in the training group, respectively, and the value was 0.50 vs. 0.60 (P<0.001) in the validation group, respectively. The clinical model nomogram was shown to have high efficiency in predicting ALN status among our research population. The area under the curve (AUC) was 0.89 in the training group and 0.90 in the validation group and the accuracy was 85.79% and 81.63%, respectively.

Conclusions: The clinical model nomogram based on tumor circularity and US-reported ALN status is a non-invasive approach for ALN metastasis prediction in ESIBC patients with high efficacy.