The purpose of this study was to explore the value of pre-operative prediction of lymphovascular invasion (LVI) in primary breast cancer patients undergoing modified radical mastectomy and to develop a nomogram based on multiparametric ultrasound and clinicopathologic indicators. All patients with primary breast cancer confirmed by pre-operative biopsy underwent B-mode ultrasound and contrast-enhanced ultrasound examinations. Post-operative pathology was used as the gold standard to identify LVI. Lasso regression was used to select predictors most related to LVI. A nomogram was developed to calculate the diagnostic efficacy. We bootstrapped the data for 500 times to perform internal verification, drawing a calibration curve to verify prediction ability. A total of 244 primary breast cancer patients were included. LVI was observed in 77 patients. Ten predictors associated with LVI were selected by Lasso regression. The area under the curve, sensitivity, specificity and accuracy for the nomogram were 0.918, 92.2%, 76.7% and 81.6%, respectively. And the nomogram calibration curve showed good consistency between the predicted probability and the actual probability. The nomogram developed could be used to predict LVI in primary breast cancer patients undergoing modified radical mastectomy and to help in clinical decision-making.

本研究的目的是探讨术前预测淋巴血管浸润 (LVI) 在接受改良根治术的原发性乳腺癌患者中的价值，并开发基于多参数超声和临床病理指标的列线图。所有术前活检确诊的原发性乳腺癌患者均接受 B 型超声和超声造影检查。术后病理被用作鉴定 LVI 的金标准。套索回归用于选择与 LVI 最相关的预测变量。开发了列线图来计算诊断功效。我们对数据进行了 500 次自举以进行内部验证，绘制校准曲线以验证预测能力。共纳入 244 名原发性乳腺癌患者。在 77 名患者中观察到 LVI。通过套索回归选择了与 LVI 相关的 10 个预测变量。列线图的曲线下面积、灵敏度、特异性和准确度分别为 0.918、92.2%、76.7% 和 81.6%。并且列线图校准曲线显示预测概率与实际概率之间具有良好的一致性。开发的列线图可用于预测接受改良根治术的原发性乳腺癌患者的 LVI，并有助于临床决策。