深度学习辅助甲状腺结节成分分类与实性结节诊断:一项多中心诊断研究
本研究基于四家医院超声图像构建卷积神经网络模型,将甲状腺结节分为实性与非实性、良性与恶性,共使用6784个结节的11201幅图像进行训练、验证和测试。模型对实性甲状腺结节良恶性分级的AUC均高于0.91,Inception-ResNet最高达0.94;测试集中最佳算法敏感度0.88、特异度0.86,外部测试集敏感度0.90、特异度0.75。作者认为CNN可辅助甲状腺结节诊断并减少不必要的细针穿刺。
要点
- CNN模型对实性甲状腺结节良恶性分级的AUC均高于0.91,Inception-ResNet最高为0.94。
- 测试集中最佳算法鉴别甲状腺结节良恶性的敏感度为0.88、特异度为0.86。
- 人机对比测试集中最佳算法敏感度0.93、特异度0.86,Inception-ResNet模型表现优于高年资医师(p < 0.001)。
核心结论
- 卷积神经网络可辅助甲状腺结节诊断,并减少不必要的细针穿刺(FNA)。
研究设计与样本
- 回顾性多中心诊断研究,使用四家医院的超声图像,共11201幅图像、6784个结节用于训练、验证和测试,构建CNN模型将甲状腺结节分为实性与非实性、良性与恶性,以AUC为主要评价指标。
诊断标准与关键数值
- 实性甲状腺结节良恶性分级中模型AUC均高于0.91,Inception-ResNet的AUC最高为0.94;测试集中最佳算法鉴别良恶性的敏感度0.88、特异度0.86;人机对比测试集中最佳算法敏感度0.93、特异度0.86;外部测试集中最优模型敏感度0.90、特异度0.75。
临床应用与阅片要点
- 作者认为CNN可辅助甲状腺结节诊断并减少不必要的细针穿刺;Inception-ResNet模型在人机对比测试集中表现优于高年资医师(p < 0.001)。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
OBJECTIVES: This study aimed to propose a deep learning (DL)-based framework for identifying the composition of thyroid nodules and assessing their malignancy risk.
METHODS: We conducted a retrospective multicenter study using ultrasound images from four hospitals. Convolutional neural network (CNN) models were constructed to classify ultrasound images of thyroid nodules into solid and non-solid, as well as benign and malignant. A total of 11,201 images of 6784 nodules were used for training, validation, and testing. The area under the receiver-operating characteristic curve (AUC) was employed as the primary evaluation index.
RESULTS: The models had AUCs higher than 0.91 in the benign and malignant grading of solid thyroid nodules, with the Inception-ResNet AUC being the highest at 0.94. In the test set, the best algorithm for identifying benign and malignant thyroid nodules had a sensitivity of 0.88, and a specificity of 0.86. In the human vs. DL test set, the best algorithm had a sensitivity of 0.93, and a specificity of 0.86. The Inception-ResNet model performed better than the senior physicians (p < 0.001). The sensitivity and specificity of the optimal model based on the external test set were 0.90 and 0.75, respectively.
CONCLUSIONS: This research demonstrates that CNNs can assist thyroid nodule diagnosis and reduce the rate of unnecessary fine-needle aspiration (FNA).
CLINICAL RELEVANCE STATEMENT: High-resolution ultrasound has led to increased detection of thyroid nodules. This results in unnecessary fine-needle aspiration and anxiety for patients whose nodules are benign. Deep learning can solve these problems to some extent.
KEY POINTS: • Thyroid solid nodules have a high probability of malignancy. • Our models can improve the differentiation between benign and malignant solid thyroid nodules. • The differential performance of one model was superior to that of senior radiologists. Applying this could reduce the rate of unnecessary fine-needle aspiration of solid thyroid nodules.
引用
- Chen C, Jiang Y, Yao J, et al. Deep learning to assist composition classification and thyroid solid nodule diagnosis: a multicenter diagnostic study. Eur Radiol. 2023. PMID: 37819276. doi:10.1007/s00330-023-10269-z
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。