Department of Radiology, Duke University, USA.
Department of Radiology and Department of Electrical and Computer Engineering, Duke University, USA.
Comput Biol Med. 2019 Jun;109:85-90. doi: 10.1016/j.compbiomed.2019.04.018. Epub 2019 Apr 25.
To determine whether deep learning models can distinguish between breast cancer molecular subtypes based on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI).
In this institutional review board-approved single-center study, we analyzed DCE-MR images of 270 patients at our institution. Lesions of interest were identified by radiologists. The task was to automatically determine whether the tumor is of the Luminal A subtype or of another subtype based on the MR image patches representing the tumor. Three different deep learning approaches were used to classify the tumor according to their molecular subtypes: learning from scratch where only tumor patches were used for training, transfer learning where networks pre-trained on natural images were fine-tuned using tumor patches, and off-the-shelf deep features where the features extracted by neural networks trained on natural images were used for classification with a support vector machine. Network architectures utilized in our experiments were GoogleNet, VGG, and CIFAR. We used 10-fold crossvalidation method for validation and area under the receiver operating characteristic (AUC) as the measure of performance.
The best AUC performance for distinguishing molecular subtypes was 0.65 (95% CI:[0.57,0.71]) and was achieved by the off-the-shelf deep features approach. The highest AUC performance for training from scratch was 0.58 (95% CI:[0.51,0.64]) and the best AUC performance for transfer learning was 0.60 (95% CI:[0.52,0.65]) respectively. For the off-the-shelf approach, the features extracted from the fully connected layer performed the best.
Deep learning may play a role in discovering radiogenomic associations in breast cancer.
旨在确定深度学习模型是否可以基于动态对比增强磁共振成像（DCE-MRI）区分乳腺癌分子亚型。
在这项获得机构审查委员会批准的单中心研究中，我们分析了 270 例我院患者的 DCE-MRI 图像。由放射科医生确定感兴趣的病变。任务是基于代表肿瘤的 MRI 图像斑块自动确定肿瘤是否为 Luminal A 亚型或其他亚型。我们使用了三种不同的深度学习方法来根据肿瘤的分子亚型对其进行分类：从头开始学习，仅使用肿瘤斑块进行训练；迁移学习，使用肿瘤斑块微调预先在自然图像上训练的网络；以及现成的深度特征，使用在自然图像上训练的神经网络提取的特征，使用支持向量机进行分类。我们的实验中使用的网络架构包括 GoogleNet、VGG 和 CIFAR。我们使用 10 折交叉验证方法进行验证，以接收者操作特征曲线下的面积（AUC）作为性能衡量标准。
区分分子亚型的最佳 AUC 性能为 0.65（95%CI：[0.57,0.71]），是通过现成的深度特征方法实现的。从头开始训练的最高 AUC 性能为 0.58（95%CI：[0.51,0.64]），而迁移学习的最佳 AUC 性能为 0.60（95%CI：[0.52,0.65]）。对于现成的方法，从全连接层提取的特征表现最佳。
深度学习可能在发现乳腺癌的放射基因组关联方面发挥作用。
