Department of Radiology, 622 West 168th Street, PB-1-301, New York, NY, 10032, USA.
Department of Radiology, T32 Training Grant (NIH T32EB001631), UC San Francisco Medical Center, 505 Parnassus Ave, San Francisco, CA, 94143, USA.
J Digit Imaging. 2018 Dec;31(6):851-856. doi: 10.1007/s10278-018-0086-7.
The aim of this study is to evaluate the role of convolutional neural network (CNN) in predicting axillary lymph node metastasis, using a breast MRI dataset. An institutional review board (IRB)-approved retrospective review of our database from 1/2013 to 6/2016 identified 275 axillary lymph nodes for this study. Biopsy-proven 133 metastatic axillary lymph nodes and 142 negative control lymph nodes were identified based on benign biopsies (100) and from healthy MRI screening patients (42) with at least 3 years of negative follow-up. For each breast MRI, axillary lymph node was identified on first T1 post contrast dynamic images and underwent 3D segmentation using an open source software platform 3D Slicer. A 32 × 32 patch was then extracted from the center slice of the segmented tumor data. A CNN was designed for lymph node prediction based on each of these cropped images. The CNN consisted of seven convolutional layers and max-pooling layers with 50% dropout applied in the linear layer. In addition, data augmentation and L2 regularization were performed to limit overfitting. Training was implemented using the Adam optimizer, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments. Code for this study was written in Python using the TensorFlow module (1.0.0). Experiments and CNN training were done on a Linux workstation with NVIDIA GTX 1070 Pascal GPU. Two class axillary lymph node metastasis prediction models were evaluated. For each lymph node, a final softmax score threshold of 0.5 was used for classification. Based on this, CNN achieved a mean five-fold cross-validation accuracy of 84.3%. It is feasible for current deep CNN architectures to be trained to predict likelihood of axillary lymph node metastasis. Larger dataset will likely improve our prediction model and can potentially be a non-invasive alternative to core needle biopsy and even sentinel lymph node evaluation.
本研究旨在利用乳腺 MRI 数据集评估卷积神经网络（CNN）在预测腋窝淋巴结转移中的作用。通过对我们 2013 年 1 月至 2016 年 6 月数据库的机构审查委员会（IRB）批准的回顾性分析，本研究共纳入 275 个腋窝淋巴结。根据良性活检（100 例）和至少 3 年阴性随访的健康 MRI 筛查患者（42 例）的活检结果，确定了 133 个腋窝淋巴结转移和 142 个阴性对照淋巴结。对于每例乳腺 MRI，在首幅 T1 对比后动态图像上识别腋窝淋巴结，并使用开源软件平台 3D Slicer 进行 3D 分割。然后从分割的肿瘤数据的中心切片中提取 32x32 的斑块。基于这些裁剪图像，设计了用于淋巴结预测的 CNN。CNN 由 7 个卷积层和最大池化层组成，在线性层中应用 50%的辍学率。此外，还进行了数据扩充和 L2 正则化以限制过拟合。使用 Adam 优化器进行训练，该优化器是一种用于随机目标函数的一阶梯度优化的算法，基于对较低阶矩的自适应估计。本研究的代码是使用 Python 编写的，使用 TensorFlow 模块（1.0.0）。实验和 CNN 训练在具有 NVIDIA GTX 1070 Pascal GPU 的 Linux 工作站上进行。评估了两种腋窝淋巴结转移预测模型。对于每个淋巴结，使用最终的 softmax 分数阈值为 0.5 进行分类。基于此，CNN 的五重交叉验证准确率为 84.3%。目前，深 CNN 架构可以被训练来预测腋窝淋巴结转移的可能性。更大的数据集可能会提高我们的预测模型，并可能成为核心针活检的非侵入性替代方法，甚至是前哨淋巴结评估的替代方法。
