动态对比增强磁共振成像（DCE-MRI）放射组学已用于评估乳腺癌患者的淋巴血管侵犯（LVI）。然而，尚无研究探讨延迟期和多期 DCE-MRI 特征与 LVI 状态之间的关联。因此，我们的目的是开发一种基于多相 DCE-MRI 的有效列线图来预测浸润性 (IBC) 乳腺癌患者的 LVI 状态。对 173 例乳腺癌患者的术前临床、病理和 DCE-MRI 数据进行回顾性分析。所有患者按 7:3 的比例随机分配到训练集 (n=121) 和验证集 (n=52)。然后对临床、病理和常规MRI特征进行单因素和多因素Logistic回归分析，并采用多因素Logistic回归中P<0.05的临床危险因素建立临床模型。建立了不同的单相模型（早期阶段、峰值阶段和末期）以及整合多个阶段的放射组学特征的多阶段模型。此外，通过将多相模型的rad评分与临床病理独立危险因素相结合，构建了术前放射组学列线图模型。最后，使用受试者工作特征 (ROC) 曲线、曲线下面积 (AUC) 值和决策曲线分析 (DCA) 比较多相模型、临床模型和 rad 评分的性能。使用校准曲线评估rad评分的临床实用性，并使用Delong检验比较不同模型之间AUC值的差异。腋窝淋巴结（ALN）状态和Ki-67已被确定为临床病理学独立预测因子并建立了临床模型。与其他单相的特征相比，从 DCE-MRI 末期提取的图像特征表现出明显优越的预测性能。特别是，在多相模型中，终末相特征被认为有可能提供更多的预测信息。在多相模型中发现与 LVI 相关的九个特征中，一个来自早期阶段，两个来自峰值阶段，六个来自末期，这表明末期特征为预测 LVI 提供了更多信息。对列线图性能的评估揭示了训练集（AUC：临床模型与多相模型与列线图=0.734 vs. 0.840 vs. 0.876）和验证集（AUC：临床模型与多相模型与列线图）的有希望的结果=0.765 vs. 0.753 vs. 0.832）。基于 DCE-MRI 的放射组学模型在预测 LVI 状态方面表现出实用性，尤其是终末期的特征提供了更有价值的信息。术前放射组学列线图增强了识别 IBC 患者 LVI 状态的诊断能力，并可能帮助临床医生做出个性化治疗决策。版权所有 © 2024 大学放射科医生协会。由爱思唯尔公司出版。保留所有权利。

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) radiomics had been used to evaluate lymphovascular invasion (LVI) in patients with breast cancer. However, no studies had explored the associations between features from delayed phase as well as multiphases DCE-MRI and the LVI status. Thus, we aimed to develop an efficient nomogram based on multiphases DCE-MRI to predict the LVI status in invasive (IBC) breast cancer patients.A retrospective analysis was conducted on preoperative clinical, pathological, and DCE-MRI data of 173 breast cancer patients. All patients were randomly assigned into training set (n=121) and validation set (n=52) in 7:3 ratio. The clinical, pathologic, and conventional MRI characteristics were then subjected to univariate and multivariate logistic regression analysis, and the clinical risk factors with P < 0.05 in the multivariate logistic regression were used to build clinical models. Different single-phase models (early phase, peak phase, and terminal phase), as well as a multiphases model integrating radiomics features from multiple phases, were established. Furthermore, a preoperative radiomics nomogram model was constructed by combining the rad-score of the multiphases model with clinicopathologic independent risk factors. Finally, the performance of the multiphases model, clinical model, and rad-score was compared using receiver operating characteristic (ROC) curves, area under the curve (AUC) values, and decision curve analysis (DCA). The clinical utility of the rad-score was evaluated using calibration curves, and Delong test was used to compare the differences in AUC values among the different models.The axillary lymph nodes (ALN) status and Ki-67 had been identified as clinicopathologic independent predictors and a clinical model had been constructed. Image features that were extracted from the terminal phase of the DCE-MRI exhibited notably superior predictive performances compared to features from the other single phases. Particularly, in the multiphases model, terminal phase features were identified as potentially providing more predictive information. Among the nine features that were found to be associated with LVI in the multiphase model, one was derived from the early phase, two from the peak phase, and six from the terminal phase, indicating that terminal phase features contributed significantly more information towards predicting LVI. Evaluation of the nomogram performance revealed promising results in both the training set (AUCs: clinical model vs. multiphase model vs. nomogram=0.734 vs. 0.840 vs. 0.876) and the validation set (AUCs: clinical model vs. multiphase model vs. nomogram=0.765 vs. 0.753 vs. 0.832).The DCE-MRI-based radiomics model demonstrated utility in predicting LVI status, features of the terminal phase offered more valuable information particularly. The preoperative radiomics nomogram enhanced the diagnostic capability of identifying LVI status in IBC patients, and might aid clinicians in making personalized treatment decisions.Copyright © 2024 The Association of University Radiologists. Published by Elsevier Inc. All rights reserved.