Lymph Node Metastasis Prediction from Primary Breast Cancer US Images Using Deep Learning
Lymph Node Metastasis Prediction from Primary Breast Cancer US Images Using Deep Learning
复制标题
DOI：
10.1148/radiol.2019190372
复制
发表时间：
2020-01-01
期刊：
影响因子：
19.7
通讯作者：
Dietrich, Christoph F.
中科院分区：
文献类型：
--
作者：
Zhou, Li-Qiang;Wu, Xing-Long;Dietrich, Christoph F.
背景：深度学习算法因其在图像识别任务中的优异性能而受到广泛关注。目的：探讨从超声图像中预测临床阴性乳腺癌腋窝淋巴结转移的可行性。材料与方法：收集同济医院临床腋窝淋巴结阴性乳腺癌患者的超声图像数据(2016~2018年共974项影像研究，756例患者)和湖北省肿瘤医院独立测试集(2018~2019年81项影像研究，78例患者)。腋窝淋巴结状况经病理检查证实。三种不同的卷积神经网络(CNN)在同济医院90%的数据集上进行了训练，并在其余10%的数据集上以及在独立的测试集上进行了测试。将模型的性能与五位放射科医生的性能进行了比较。从准确性、敏感性、特异性、接收者工作特征曲线、接收者工作特征曲线下面积(AUC)和热图等方面分析模型的性能。结果：在独立测试集中，表现最好的CNN模型初始V3在预测最终临床诊断腋窝淋巴结转移方面的AUC为0.89(95%可信区间：0.83，0.95)。模型的敏感度为85%(35/41)，特异度为75%(95%CI：70%，94%)，特异度为73%(29/40；95%CI：56%，85%)，放射科医生的灵敏度为73%(30/41，95%CI：57%，85%；P=.17)，特异度为63%(25/40，95%CI：46%，77%；P=.34)。人工智能可能为临床淋巴结阴性乳腺癌患者的淋巴结转移提供早期诊断策略。在CC by 4.0许可下发布。
Background: Deep learning (DL) algorithms are gaining extensive attention for their excellent performance in image recognition tasks. DL models can automatically make a quantitative assessment of complex medical image characteristics and achieve increased accuracy in diagnosis with higher efficiency.Purpose: To determine the feasibility of using a DL approach to predict clinically negative axillary lymph node metastasis from US images in patients with primary breast cancer.Materials and Methods: A data set of US images in patients with primary breast cancer with clinically negative axillary lymph nodes from Tongji Hospital (974 imaging studies from 2016 to 2018, 756 patients) and an independent test set from Hubei Cancer Hospital (81 imaging studies from 2018 to 2019, 78 patients) were collected. Axillary lymph node status was confirmed with pathologic examination. Three different convolutional neural networks (CNNs) of Inception V3, Inception-ResNet V2, and ResNet-101 architectures were trained on 90% of the Tongji Hospital data set and tested on the remaining 10%, as well as on the independent test set. The performance of the models was compared with that of five radiologists. The models' performance was analyzed in terms of accuracy, sensitivity, specificity, receiver operating characteristic curves, areas under the receiver operating characteristic curve (AUCs), and heat maps.Results: The best-performing CNN model, Inception V3, achieved an AUC of 0.89 (95% confidence interval [CI]: 0.83, 0.95) in the prediction of the final clinical diagnosis of axillary lymph node metastasis in the independent test set. The model achieved 85% sensitivity (35 of 41 images; 95% CI: 70%, 94%) and 73% specificity (29 of 40 images; 95% CI: 56%, 85%), and the radiologists achieved 73% sensitivity (30 of 41 images; 95% CI: 57%, 85%; P = .17) and 63% specificity (25 of 40 images; 95% CI: 46%, 77%; P = .34).Conclusion: Using US images from patients with primary breast cancer, deep learning models can effectively predict clinically negative axillary lymph node metastasis. Artificial intelligence may provide an early diagnostic strategy for lymph node metastasis inpatients with breast cancer with clinically negative lymph nodes. Published under a CC BY 4.0 license.