Department of Radiology, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, No.106, Zhongshan 2nd road, Guangzhou 510080 Guangdong, PR China; Graduate College, Shantou University Medical College, Shantou, Guangdong, PR China.
The School of Computer Science and Engineering, South China University of Technology, Guangzhou, Guangdong, PR China.
Acad Radiol. 2021 Feb;28(2):e44-e53. doi: 10.1016/j.acra.2020.02.006. Epub 2020 Apr 8.
Ki-67 is one of the most important biomarkers of breast cancer traditionally measured invasively via immunohistochemistry. In this study, deep learning based radiomics models were established for preoperative prediction of Ki-67 status using multiparametric magnetic resonance imaging (mp-MRI).
Total of 328 eligible patients were retrospectively reviewed [training dataset (n = 230) and a temporal validation dataset (n = 98)]. Deep learning imaging features were extracted from T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), and contrast enhanced T1-weighted imaging (T1+C). Transfer learning techniques constructed four feature sets based on the individual three MR sequences and their combination (i.e., mp-MRI). Multilayer perceptron classifiers were trained for final prediction of Ki-67 status. Mann-Whitney U test compared the predictive performance of individual models.
The area under curve (AUC) of models based on T2WI,T1+C,DWI and mp-MRI were 0.727, 0.873, 0.674, and 0.888 in the training dataset, respectively, and 0.706, 0.829, 0.643, and 0.875 in the validation dataset, respectively. The predictive performance of mp-MRI classification model in the AUC value was significantly better than that of the individual sequence model (all p< 0.01).
In clinical practice, a noninvasive approach to improve the performance of radiomics in preoperative prediction of Ki-67 status can be provided by extracting breast cancer specific structural and functional features from mp-MRI images obtained from conventional scanning sequences using the advanced deep learning methods. This could further personalize medicine and computer aided diagnosis.
Ki-67 是乳腺癌最重要的生物标志物之一，传统上通过免疫组织化学进行侵袭性测量。本研究使用多参数磁共振成像（mp-MRI），基于深度学习的放射组学模型建立了用于术前预测 Ki-67 状态的模型。
回顾性纳入 328 例符合条件的患者（训练数据集，n=230；时间验证数据集，n=98）。从 T2 加权成像（T2WI）、弥散加权成像（DWI）和对比增强 T1 加权成像（T1+C）提取深度学习成像特征。基于个体三个 MR 序列及其组合（即 mp-MRI）的转移学习技术构建了四个特征集。多层感知机分类器用于最终预测 Ki-67 状态。采用 Mann-Whitney U 检验比较各模型的预测性能。
基于 T2WI、T1+C、DWI 和 mp-MRI 的模型在训练数据集的 AUC 分别为 0.727、0.873、0.674 和 0.888，在验证数据集的 AUC 分别为 0.706、0.829、0.643 和 0.875。mp-MRI 分类模型在 AUC 值上的预测性能明显优于各单序列模型（均 P<0.01）。
在临床实践中，通过使用先进的深度学习方法从常规扫描序列获得的 mp-MRI 图像中提取乳腺癌特定的结构和功能特征，可以提供一种非侵入性方法来提高术前预测 Ki-67 状态的放射组学性能。这可以进一步实现个性化医疗和计算机辅助诊断。
