Preoperative Prediction of Lymph Node Metastasis from Clinical DCE MRI of the Primary Breast Tumor Using a 4D CNN.
Preoperative Prediction of Lymph Node Metastasis from Clinical DCE MRI of the Primary Breast Tumor Using a 4D CNN.
复制标题
DOI：
10.1007/978-3-030-59713-9_32
复制
发表时间：
2020-10
期刊：
影响因子：
--
通讯作者：
Montillo A
中科院分区：
文献类型：
--
作者：
Nguyen S;Polat D;Karbasi P;Moser D;Wang L;Hulsey K;Çobanoğlu MC;Dogan B;Montillo A
在乳腺癌中，未被发现的淋巴结转移可以扩散到身体的远端部位，其5年生存率仅为27%，这使得准确的淋巴结转移诊断对于减轻乳腺癌的负担至关重要，此时仍然可以及早进行手术和辅助治疗。目前，乳腺癌管理需要一系列耗时且昂贵的步骤来临床诊断腋窝淋巴结转移状态。本研究的目的是确定原发性肿瘤的术前临床DCE MRI是否可用于通过深度学习模型预测临床淋巴结状态。如果可能的话，许多昂贵的步骤可以取消或保留只有那些不确定或可能的淋巴结转移。本研究开发了一种数据驱动的方法，通过明智地整合来自两家医院的357例患者的术前4D动态对比增强（DCE）MRI的临床和成像特征来预测淋巴结转移。创新的深度学习分类器是从头开始训练的，包括2D、3D、4D和4D深度卷积神经网络（CNN），它们集成了多种数据类型，并预测区分N0（非转移性）与N1、N2和N3期的淋巴结转移。适当的数据预处理和网络解释的方法，后者支持放射科医生的信心，该模型已经从原发性肿瘤的相关功能。严格的嵌套10重交叉验证提供了模型性能的无偏估计。最好的模型实现了72%的高灵敏度和71%的AUROC的测试数据。结果强烈支持DCE MRI和机器学习相结合的潜力，为诊断提供信息，可以大大减少乳腺癌的负担。
In breast cancer, undetected lymph node metastases can spread to distal parts of the body for which the 5-year survival rate is only 27%, making accurate nodal metastases diagnosis fundamental to reducing the burden of breast cancer, when it is still early enough to intervene with surgery and adjuvant therapies. Currently, breast cancer management entails a time consuming and costly sequence of steps to clinically diagnose axillary nodal metastases status. The purpose of this study is to determine whether preoperative, clinical DCE MRI of the primary tumor alone may be used to predict clinical node status with a deep learning model. If possible then many costly steps could be eliminated or reserved for only those with uncertain or probable nodal metastases. This research develops a data-driven approach that predicts lymph node metastasis through the judicious integration of clinical and imaging features from preoperative 4D dynamic contrast enhanced (DCE) MRI of 357 patients from 2 hospitals. Innovative deep learning classifiers are trained from scratch, including 2D, 3D, 4D and 4D deep convolutional neural networks (CNNs) that integrate multiple data types and predict the nodal metastasis differentiating nodal stage N0 (non metastatic) against stages N1, N2 and N3. Appropriate methodologies for data preprocessing and network interpretation are presented, the later of which bolster radiologist confidence that the model has learned relevant features from the primary tumor. Rigorous nested 10-fold cross-validation provides an unbiased estimate of model performance. The best model achieves a high sensitivity of 72% and an AUROC of 71% on held out test data. Results are strongly supportive of the potential of the combination of DCE MRI and machine learning to inform diagnostics that could substantially reduce breast cancer burden.