Kil Jieun, Kim Kwang Gi, Kim Young Jae, Koo Hye Ryoung, Park Jeong Seon
Taehan Yongsang Uihakhoe Chi. 2020 Sep;81(5):1164-1174. doi: 10.3348/jksr.2019.0147. Epub 2020 Apr 23.
To evaluate a deep learning model to predict recurrence of thyroid tumor using preoperative ultrasonography (US).
We included representative images from 229 US-based patients (male:female = 42:187; mean age, 49.6 years) who had been diagnosed with thyroid cancer on preoperative US and subsequently underwent thyroid surgery. After selecting each representative transverse or longitudinal US image, we created a data set from the resulting database of 898 images after augmentation. The Python 2.7.6 and Keras 2.1.5 framework for neural networks were used for deep learning with a convolutional neural network. We compared the clinical and histological features between patients with and without recurrence. The predictive performance of the deep learning model between groups was evaluated using receiver operating characteristic (ROC) analysis, and the area under the ROC curve served as a summary of the prognostic performance of the deep learning model to predict recurrent thyroid cancer.
Tumor recurrence was noted in 49 (21.4%) among the 229 patients. Tumor size and multifocality varied significantly between the groups with and without recurrence ( < 0.05). The overall mean area under the curve (AUC) value of the deep learning model for prediction of recurrent thyroid cancer was 0.9 ± 0.06. The mean AUC value was 0.87 ± 0.03 in macrocarcinoma and 0.79 ± 0.16 in microcarcinoma.
A deep learning model for analysis of US images of thyroid cancer showed the possibility of predicting recurrence of thyroid cancer.
评估一种深度学习模型，用于利用术前超声（US）预测甲状腺肿瘤复发。
我们纳入了229例基于超声检查的患者的代表性图像（男∶女 = 42∶187；平均年龄49.6岁），这些患者术前超声诊断为甲状腺癌，随后接受了甲状腺手术。在选择每幅代表性横向或纵向超声图像后，我们对增强后的898幅图像的数据库创建了一个数据集。使用Python 2.7.6和Keras 2.1.5神经网络框架，通过卷积神经网络进行深度学习。我们比较了复发患者和未复发患者的临床和组织学特征。使用受试者操作特征（ROC）分析评估深度学习模型在两组之间的预测性能，ROC曲线下面积作为深度学习模型预测复发性甲状腺癌预后性能的总结。
229例患者中有49例（21.4%）出现肿瘤复发。复发组和未复发组之间的肿瘤大小和多灶性差异有统计学意义（<0.05）。深度学习模型预测复发性甲状腺癌的总体曲线下平均面积（AUC）值为0.9±0.06。在大癌中平均AUC值为0.87±0.03，在微小癌中为0.79±0.16。
一种用于分析甲状腺癌超声图像的深度学习模型显示了预测甲状腺癌复发的可能性。
