Nguyen Son, Polat Dogan, Karbasi Paniz, Moser Daniel, Wang Liqiang, Hulsey Keith, Çobanoğlu Murat Can, Dogan Basak, Montillo Albert
Lyda Hill Department of Bioinformatics, UT Southwestern Medical Center, Dallas, TX 75390, USA.
Department of Radiology, UT Southwestern Medical Center, Dallas, TX 75390, USA.
Med Image Comput Comput Assist Interv. 2020 Oct;12262:326-334. doi: 10.1007/978-3-030-59713-9_32. Epub 2020 Sep 29.
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 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.
在乳腺癌中，未被检测到的淋巴结转移可扩散至身体远端部位，其5年生存率仅为27%，因此在仍可通过手术和辅助治疗进行干预的早期阶段，准确诊断淋巴结转移对于减轻乳腺癌负担至关重要。目前，乳腺癌的治疗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仅对原发性肿瘤进行术前临床动态对比增强磁共振成像（DCE MRI）是否可用于通过深度学习模型预测临床淋巴结状态。如果可行，那么许多昂贵的步骤可以省去，或者仅用于那些淋巴结转移不确定或可能发生转移的患者。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357例患者术前4D动态对比增强磁共振成像（DCE MRI）的临床和影像特征来预测淋巴结转移。创新的深度学习分类器是从零开始训练的，包括2D、3D、4D和4D深度卷积神经网络（CNN），这些网络整合了多种数据类型，并预测淋巴结转移情况，区分淋巴结分期N0（无转移）与N1、N2和N3期。本文介绍了数据预处理和网络解释的适当方法，后者增强了放射科医生对模型已从原发性肿瘤中学习到相关特征的信心。严格的10折交叉验证提供了对模型性能的无偏估计。最佳模型在留出的测试数据上实现了72%的高灵敏度和71%的曲线下面积（AUROC）。结果有力地支持了DCE MRI与机器学习相结合在为诊断提供信息方面的潜力，这可以大幅减轻乳腺癌负担。
