In this prospective study, 117 female patients (mean age = 53 years) with 127 histologically proven breast cancer lesions (lymph node (LN) positive = 85, LN negative = 42) underwent simultaneous 18F-FDG PET/MRI of the breast. Quantitative parameters were calculated from dynamic contrast-enhanced (DCE) imaging (tumor Mean Transit Time, Volume Distribution, Plasma Flow), diffusion-weighted imaging (DWI) (tumor ADCmean), and PET (tumor SUVmax, mean and minimum, SUVmean of ipsilateral breast parenchyma). Manual whole-lesion segmentation was also performed on DCE, T2-weighted, DWI, and PET images, and radiomic features were extracted. The dataset was divided into a training (70%) and a test set (30%). Multi-step feature selection was performed, and a support vector machine classifier was trained and tested for predicting axillary LN status. 13 radiomic features from DCE, DWI, T2-weighted, and PET images were selected for model building. The classifier obtained an accuracy of 79.8 (AUC = 0.798) in the training set and 78.6% (AUC = 0.839), with sensitivity and specificity of 67.9% and 100%, respectively, in the test set. A machine learning-based radiomics model comprising 18F-FDG PET/MRI radiomic features extracted from the primary breast cancer lesions allows high accuracy in non-invasive identification of axillary LN metastasis.
在这项前瞻性研究中，117例女性患者（平均年龄53岁）共127处经组织学证实的乳腺癌病灶（淋巴结阳性85处，淋巴结阴性42处）接受了同步18F-FDG PET/MRI乳腺检查。研究从动态对比增强成像（肿瘤平均通过时间、容积分布、血浆流量）、扩散加权成像（肿瘤ADC平均值）及PET成像（肿瘤SUV最大值、平均值与最小值，同侧乳腺实质SUV平均值）中提取定量参数。同时对DCE、T2加权、DWI和PET图像进行全病灶手动分割并提取影像组学特征。数据集按7:3比例划分为训练集与测试集。通过多步骤特征筛选，建立支持向量机分类器进行腋窝淋巴结状态预测。最终从DCE、DWI、T2加权及PET图像中筛选出13个影像组学特征构建模型。该分类器在训练集中准确率达79.8%（AUC=0.798），在测试集中准确率为78.6%（AUC=0.839），敏感度与特异度分别为67.9%和100%。基于机器学习构建的影像组学模型，通过提取原发性乳腺癌病灶的18F-FDG PET/MRI影像组学特征，能够以较高准确率实现腋窝淋巴结转移的无创识别。
肿瘤(癌症)患者之家