Department of Radiology, Columbia University Irving Medical Center, 622 West 168th Street, PB-1-301, New York, NY, 10032, USA.
Division of Radiation Oncology, Columbia University Medical Center, Presbyterian Hospital Building, 622 West 168th Street, Level B, New York, NY, 10032, USA.
J Digit Imaging. 2019 Oct;32(5):693-701. doi: 10.1007/s10278-018-0144-1.
We hypothesize that convolutional neural networks (CNN) can be used to predict neoadjuvant chemotherapy (NAC) response using a breast MRI tumor dataset prior to initiation of chemotherapy. An institutional review board-approved retrospective review of our database from January 2009 to June 2016 identified 141 locally advanced breast cancer patients who (1) underwent breast MRI prior to the initiation of NAC, (2) successfully completed adriamycin/taxane-based NAC, and (3) underwent surgical resection with available final surgical pathology data. Patients were classified into three groups based on their NAC response confirmed on final surgical pathology: complete (group 1), partial (group 2), and no response/progression (group 3). A total of 3107 volumetric slices of 141 tumors were evaluated. Breast tumor was identified on first T1 postcontrast dynamic images and underwent 3D segmentation. CNN consisted of ten convolutional layers, four max-pooling layers, and dropout of 50% after a fully connected layer. Dropout, augmentation, and L2 regularization were implemented to prevent overfitting of data. Non-linear functions were modeled by a rectified linear unit (ReLU). Batch normalization was used between the convolutional and ReLU layers to limit drift of layer activations during training. A three-class neoadjuvant prediction model was evaluated (group 1, group 2, or group 3). The CNN achieved an overall accuracy of 88% in three-class prediction of neoadjuvant treatment response. Three-class prediction discriminating one group from the other two was analyzed. Group 1 had a specificity of 95.1% ± 3.1%, sensitivity of 73.9% ± 4.5%, and accuracy of 87.7% ± 0.6%. Group 2 (partial response) had a specificity of 91.6% ± 1.3%, sensitivity of 82.4% ± 2.7%, and accuracy of 87.7% ± 0.6%. Group 3 (no response/progression) had a specificity of 93.4% ± 2.9%, sensitivity of 76.8% ± 5.7%, and accuracy of 87.8% ± 0.6%. It is feasible for current deep CNN architectures to be trained to predict NAC treatment response using a breast MRI dataset obtained prior to initiation of chemotherapy. Larger dataset will likely improve our prediction model.
我们假设卷积神经网络 (CNN) 可以用于在开始化疗之前使用乳腺 MRI 肿瘤数据集来预测新辅助化疗 (NAC) 的反应。对我们 2009 年 1 月至 2016 年 6 月的数据库进行了机构审查委员会批准的回顾性审查，确定了 141 名局部晚期乳腺癌患者，这些患者：(1) 在开始 NAC 之前接受了乳腺 MRI；(2) 成功完成了阿霉素/紫杉烷类 NAC；以及 (3) 接受了手术切除并获得了最终的手术病理数据。根据最终的手术病理结果，患者根据 NAC 反应分为三组：完全缓解 (第 1 组)、部分缓解 (第 2 组) 和无反应/进展 (第 3 组)。共评估了 141 个肿瘤的 3107 个容积切片。在首次 T1 对比后动态图像上识别出乳腺肿瘤，并进行了 3D 分割。CNN 由十个卷积层、四个最大池化层和全连接层后的 50%dropout 组成。实施了 dropout、增强和 L2 正则化以防止数据过拟合。使用修正线性单元 (ReLU) 对非线性函数进行建模。在卷积层和 ReLU 层之间使用批量归一化以限制训练过程中层激活的漂移。评估了三分类新辅助预测模型 (第 1 组、第 2 组或第 3 组)。CNN 在三分类新辅助治疗反应预测中总体准确率达到 88%。分析了三分类预测区分一组与其他两组的情况。第 1 组的特异性为 95.1%±3.1%，敏感性为 73.9%±4.5%，准确性为 87.7%±0.6%。第 2 组 (部分缓解) 的特异性为 91.6%±1.3%，敏感性为 82.4%±2.7%，准确性为 87.7%±0.6%。第 3 组 (无反应/进展) 的特异性为 93.4%±2.9%，敏感性为 76.8%±5.7%，准确性为 87.8%±0.6%。使用化疗前获得的乳腺 MRI 数据集训练当前的深度 CNN 架构来预测 NAC 治疗反应是可行的。更大的数据集可能会提高我们的预测模型。
