Xu Aqiao, Chu Xiufeng, Zhang Shengjian, Zheng Jing, Shi Dabao, Lv Shasha, Li Feng, Weng Xiaobo
Department of Radiology, The Central Hospital Affiliated to Shaoxing University (Shaoxing Central Hospital), Shaoxing, China.
Department of Surgical, The Central Hospital Affiliated to Shaoxing University (Shaoxing Central Hospital), Shaoxing, China.
Front Oncol. 2022 May 19;12:799232. doi: 10.3389/fonc.2022.799232. eCollection 2022.
To investigate the feasibility of radiomics in predicting molecular subtype of breast invasive ductal carcinoma (IDC) based on dynamic contrast enhancement magnetic resonance imaging (DCE-MRI).
A total of 303 cases with pathologically confirmed IDC from January 2018 to March 2021 were enrolled in this study, including 223 cases from Fudan University Shanghai Cancer Center (training/test set) and 80 cases from Shaoxing Central Hospital (validation set). All the cases were classified as HR+/Luminal, HER2-enriched, and TNBC according to immunohistochemistry. DCE-MRI original images were treated by semi-automated segmentation to initially extract original and wavelet-transformed radiomic features. The extended logistic regression with least absolute shrinkage and selection operator (LASSO) penalty was applied to identify the optimal radiomic features, which were then used to establish predictive models combined with significant clinical risk factors. Receiver operating characteristic curve (ROC), calibration curve, and decision curve analysis were adopted to evaluate the effectiveness and clinical benefit of the models established.
Of the 223 cases from Fudan University Shanghai Cancer Center, HR+/Luminal cancers were diagnosed in 116 cases (52.02%), HER2-enriched in 71 cases (31.84%), and TNBC in 36 cases (16.14%). Based on the training set, 788 radiomic features were extracted in total and 8 optimal features were further identified, including 2 first-order features, 1 gray-level run length matrix (GLRLM), 4 gray-level co-occurrence matrices (GLCM), and 1 3D shape feature. Three multi-class classification models were constructed by extended logistic regression: clinical model (age, menopause, tumor location, Ki-67, histological grade, and lymph node metastasis), radiomic model, and combined model. The macro-average areas under the ROC curve (macro-AUC) for the three models were 0.71, 0.81, and 0.84 in the training set, 0.73, 0.81, and 0.84 in the test set, and 0.76, 0.82, and 0.83 in the validation set, respectively.
The DCE-MRI-based radiomic features are significant biomarkers for distinguishing molecular subtypes of breast cancer noninvasively. Notably, the classification performance could be improved with the fusion analysis of multi-modal features.
探讨基于动态对比增强磁共振成像（DCE-MRI）的影像组学在预测乳腺浸润性导管癌（IDC）分子亚型中的可行性。
纳入2018年1月至2021年3月共303例经病理确诊的IDC病例，其中223例来自复旦大学附属肿瘤医院（训练/测试集），80例来自绍兴市中心医院（验证集）。所有病例根据免疫组化结果分为HR+/Luminal型、HER2过表达型和三阴型乳腺癌。对DCE-MRI原始图像进行半自动分割，初步提取原始及小波变换后的影像组学特征。采用带最小绝对收缩和选择算子（LASSO）惩罚的扩展逻辑回归来识别最佳影像组学特征，然后将其与显著的临床危险因素相结合建立预测模型。采用受试者操作特征曲线（ROC）、校准曲线和决策曲线分析来评估所建立模型的有效性和临床获益情况。
在复旦大学附属肿瘤医院的223例病例中，HR+/Luminal型癌116例（52.02%），HER2过表达型71例（31.84%），三阴型36例（16.14%）。基于训练集，共提取788个影像组学特征，进一步确定8个最佳特征，包括2个一阶特征、1个灰度游程长度矩阵（GLRLM）、4个灰度共生矩阵（GLCM）和1个三维形状特征。通过扩展逻辑回归构建了三个多分类模型：临床模型（年龄、绝经状态、肿瘤位置、Ki-67、组织学分级和淋巴结转移）、影像组学模型和联合模型。三个模型在训练集、测试集和验证集中的ROC曲线下宏平均面积（macro-AUC）分别为0.71、0.81和0.84；0.73、0.81和0.84；0.76、0.82和0.83。
基于DCE-MRI的影像组学特征是无创区分乳腺癌分子亚型的重要生物标志物。值得注意的是，多模态特征的融合分析可提高分类性能。
