Department of Radiology, Korea University Anam Hospital, Korea University College of Medicine, Seoul, Korea (S.E.S., Y.C., KRC).
Department of Radiology, Korea University Guro Hospital, Korea University College of Medicine, Seoul, Korea (O.H.W.).
Acad Radiol. 2023 Sep;30 Suppl 2:S25-S37. doi: 10.1016/j.acra.2023.05.025. Epub 2023 Jun 16.
To investigate whether machine learning (ML) approaches using breast magnetic resonance imaging (MRI)-derived multiparametric and radiomic features could predict axillary lymph node metastasis (ALNM) in stage I-II triple-negative breast cancer (TNBC).
Between 2013 and 2019, 86 consecutive patients with TNBC who underwent preoperative MRI and surgery were enrolled and divided into ALNM (N = 27) and non-ALNM (n = 59) groups according to histopathologic results. For multiparametric features, kinetic features using computer-aided diagnosis (CAD), morphologic features, and apparent diffusion coefficient (ADC) values at diffusion-weighted images were evaluated. For extracting radiomic features, three-dimensional segmentation of tumors using T2-weighted images (T2WI) and T1-weighted subtraction images were respectively performed by two radiologists. Each predictive model using three ML algorithms was built using multiparametric features or radiomic features, or both. The diagnostic performances of models were compared using the DeLong method.
Among multiparametric features, non-circumscribed margin, peritumoral edema, larger tumor size, and larger angio-volume at CAD were associated with ALNM in univariate analysis. In multivariate analysis, larger angio-volume was the sole statistically significant predictor for ALNM (odds ratio = 1.33, P = 0.008). Regarding ADC values, there were no significant differences according to ALNM status. The area under the receiver operating characteristic curve for predicting ALNM was 0.74 using multiparametric features, 0.77 using radiomic features from T1-weighted subtraction images, 0.80 using radiomic features from T2WI, and 0.82 using all features.
A predictive model incorporating breast MRI-derived multiparametric and radiomic features may be valuable in predicting ALNM preoperatively in patients with TNBC.
探讨基于乳腺磁共振成像（MRI）衍生的多参数和放射组学特征的机器学习（ML）方法是否可预测 I 期- II 期三阴性乳腺癌（TNBC）的腋窝淋巴结转移（ALNM）。
2013 年至 2019 年间，连续纳入 86 例接受术前 MRI 检查和手术的 TNBC 患者，根据组织病理学结果将其分为 ALNM（N=27）和非 ALNM（n=59）组。多参数特征方面，评估计算机辅助诊断（CAD）动力学特征、形态学特征及扩散加权图像上的表观扩散系数（ADC）值。提取放射组学特征时，由两位放射科医生分别对 T2 加权图像（T2WI）和 T1 加权减影图像进行三维肿瘤分割。使用三种 ML 算法分别基于多参数特征、放射组学特征或两者建立预测模型，采用 DeLong 方法比较模型的诊断性能。
多参数特征中，非环形边缘、瘤周水肿、肿瘤较大、CAD 下的血管容积较大与单因素分析中的 ALNM 相关。多因素分析中，血管容积较大是 ALNM 的唯一统计学显著预测因子（优势比=1.33，P=0.008）。ADC 值方面，根据 ALNM 状态无显著差异。基于多参数特征预测 ALNM 的受试者工作特征曲线下面积为 0.74，基于 T1 加权减影图像的放射组学特征为 0.77，基于 T2WI 的放射组学特征为 0.80，基于所有特征的为 0.82。
纳入乳腺 MRI 衍生的多参数和放射组学特征的预测模型可能有助于术前预测 TNBC 患者的 ALNM。
