【摘要】 目的:构建并验证基于磁共振T2加权像(T2 weighted MRI,T2W-MRI)压脂序列图像术前预测浸润性乳腺癌组织学分级(I/II级、III级)的影像组学标签。方法:回顾性收集2011年6月至2017年2月在广东省人民医院行MRI检查并经病理诊断证实的浸润性乳腺癌患者202例,并进一步将其分为训练组152例(I/II级91例, III级61例)和验证组50例(I/II级30例, III级20例)。通过导出T2加权成像(T2 weighted imaging,T2WI)压脂序列中肿瘤最大层面图像并手动勾画肿瘤感兴趣区、提取影像组学特征后,应用最小绝对收缩和选择算子(the least absolute shrinkage and selection operator,LASSO)-logistic回归模型筛选特征并构建影像组学标签。使用Mann-Whitney U检验分析影像组学标签与浸润性乳腺癌组织学分级之间的关系;应用受试者工作特征(receiver operating characteristic,ROC)曲线并计算曲线下面积(area under curve,AUC)、敏感度、特异度及准确度以评价影像组学标签术前预测浸润性乳腺癌组织学分级的效能;并在验证组中验证其效能。结果:在训练组中提取并筛选出8个特征用于构建影像组学标签,其在术前预测浸润性乳腺癌组织学分级的效能在训练组中AUC值为0.802(95%CI:0.729～0.875),敏感度、特异度和准确度分别为78.7%,70.3%和73.7%;在验证组中,AUC值为0.812(95%CI:0.686～0.938),敏感度、特异度及准确度分别为80.0%,73.3%和76.0%。结论:基于T2W-MRI压脂序列图像的影像组学标签可术前预测浸润性乳腺癌组织学分级,有望协助临床决策。更多还原

【Abstract】 Objective: To develop and validate a fat-suppressed(T2 weighted-magnetic resonance imaging,T2 W-MRI) based radiomics signature to preoperatively evaluate the histologic grade(grade I/II VS. grade III) of invasive breast cancer.Methods: A total of 202 patients with MRI examination and pathologically confirmed invasive breast cancer from June 2011 to February 2017 were retrospectively enrolled. After retrieving fatsuppressed T2 W images and tumor segmentation, radiomics features were extracted and valuable features were selected to build a radiomic signature with the least absolute shrinkage and selection operator(LASSO) method. Mann-Whitney U test was used to explore the correlation between radiomics signature and histologic grade. Receiver operating characteristics(ROC) curve was applied to determine the discriminative performance of the radiomics signature [area under curre(AUC), sensitivity, specificity, and accuracy]. An independent validation dataset was used to confirm the discriminatory power of radiomics signature.Results: Eight radiomics features were selected to build a radiomics signature, which showed good performance for preoperatively evaluating histologic grade of invasive breast cancer, with an AUC of 0.802(95% CI 0.729 to 0.875), sensitivity of 78.7%, specificity of 70.3% and accuracy of 73.7%in training dataset and AUC of 0.812(95% CI 0.686 to 0.938), sensitivity of 80.0%, specificity of73.3% and accuracy of 76.0% in the validation dataset.Conclusion: The fat-suppressed T2 W-MRI based radiomics signature can be used to preoperatively evaluate the histologic grade of invasive breast cancer, which may assist clinical decision-maker.更多还原