Xie YaMie, Zhang Xiaoxiao
Department of CT/MRI, The Second Affiliated Hospital of Fujian Medical University, Quanzhou, China.
Department of Ultrasound, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
Front Oncol. 2024 Oct 17;14:1337265. doi: 10.3389/fonc.2024.1337265. eCollection 2024.
Given the inevitable trend of domestic imaging center mergers and the current lack of comprehensive imaging evaluation guidelines for non-mass breast lesions, we have developed a novel BI-RADS risk prediction and stratification system for non-mass breast lesions that integrates clinical characteristics with imaging features from ultrasound, mammography, and MRI, with the aim of assisting clinicians in interpreting imaging reports.
This study enrolled 350 patients with non-mass breast lesions (NMLs), randomly assigning them to a training set of 245 cases (70%) and a test set of 105 cases (30%). Radiologists conducted comprehensive evaluations of the lesions using ultrasound, mammography, and MRI. Independent predictors were identified using LASSO logistic regression, and a predictive risk model was constructed using a nomogram generated with R software, with subsequent validation in both sets.
LASSO logistic regression identified a set of independent predictors, encompassing age, clinical palpation hardness, distribution and morphology of calcifications, peripheral blood supply as depicted by color Doppler imaging, maximum lesion diameter, patterns of internal enhancement, distribution of non-mass lesions, time-intensity curve (TIC), and apparent diffusion coefficient (ADC) values. The predictive model achieved area under the curve (AUC) values of 0.873 for the training group and 0.877 for the testing group. The model's positive predictive values were as follows: BI-RADS 2 = 0%, BI-RADS 3 = 0%, BI-RADS 4A = 6.25%, BI-RADS 4B = 26.13%, BI-RADS 4C = 80.84%, and BI-RADS 5 = 97.33%.
The creation of a risk-predictive BI-RADS stratification, specifically designed for non-mass breast lesions and integrating clinical and imaging data from multiple modalities, significantly enhances the precision of diagnostic categorization for these lesions.
鉴于国内影像中心合并的必然趋势以及目前缺乏针对非肿块性乳腺病变的全面影像评估指南，我们开发了一种新型的非肿块性乳腺病变BI-RADS风险预测和分层系统，该系统将临床特征与超声、乳腺X线摄影和MRI的影像特征相结合，旨在协助临床医生解读影像报告。
本研究纳入了350例非肿块性乳腺病变（NMLs）患者，将他们随机分为训练集245例（70%）和测试集105例（30%）。放射科医生使用超声、乳腺X线摄影和MRI对病变进行了全面评估。使用LASSO逻辑回归确定独立预测因素，并使用R软件生成的列线图构建预测风险模型，随后在两组中进行验证。
LASSO逻辑回归确定了一组独立预测因素，包括年龄、临床触诊硬度、钙化的分布和形态、彩色多普勒成像显示的周边血供、病变最大直径、内部强化模式、非肿块性病变的分布、时间-强度曲线（TIC）和表观扩散系数（ADC）值。预测模型在训练组的曲线下面积（AUC）值为0.873，在测试组为0.877。该模型的阳性预测值如下：BI-RADS 2 = 0%，BI-RADS 3 = 0%，BI-RADS 4A = 6.25%，BI-RADS 4B = 26.13%，BI-RADS 4C = 80.84%，BI-RADS 5 = 97.33%。
创建专门针对非肿块性乳腺病变并整合多种模式临床和影像数据的风险预测BI-RADS分层，显著提高了这些病变诊断分类的准确性。
