卷积神经网络对甲状腺结节恶性风险的分层:与经验丰富放射科医师实施的美国放射学会甲状腺影像报告和数据系统诊断性能比较
研究纳入2019年3月至9月757例患者的760个甲状腺结节(≥10 mm),以细针 aspiration、粗针活检或手术为参考标准,比较卷积神经网络与经验丰富放射科医师按美国放射学会TI-RADS分类的诊断性能。卷积神经网络在约登指数最佳阈值下敏感度和阴性预测值高于TI-RADS,特异度、准确度和阳性预测值低于TI-RADS,AUC高于TI-RADS。作者结论为卷积神经网络诊断性能与经验丰富放射科医师的TI-RADS分类相当。
要点
- 卷积神经网络诊断甲状腺癌的AUC为0.917,高于美国放射学会TI-RADS的0.891(P=.017)。
- 卷积神经网络敏感度81.8%、阴性预测值94.0%,分别高于TI-RADS的73.9%和92.2%。
- 卷积神经网络特异度86.1%、准确度85.1%、阳性预测值64.0%,均低于TI-RADS。
核心结论
- 卷积神经网络 based on sonographic images 提供的诊断性能与经验丰富放射科医师实施的美国放射学会TI-RADS分类相当。
研究设计与样本
- 研究类型为诊断性能比较研究;2019年3月至2019年9月纳入757例患者的760个甲状腺结节(≥10 mm),经细针 aspiration、粗针活检或手术诊断为良性或恶性;由经验丰富放射科医师评估超声描述符并分配5类美国放射学会TI-RADS类别之一;卷积神经网络基于超声图像提供结节恶性风险百分比;以约登指数确定截断值,计算并比较敏感度、特异度、准确度、阳性预测值、阴性预测值及ROC曲线下面积。
诊断标准与关键数值
- 760个结节中176个(23.2%)为恶性;在约登指数最佳阈值下,卷积神经网络 vs 美国放射学会TI-RADS:敏感度81.8% vs 73.9%(P=.009),阴性预测值94.0% vs 92.2%(P=.046),特异度86.1% vs 93.7%(P<.001),准确度85.1% vs 89.1%(P=.003),阳性预测值64.0% vs 77.8%(P<.001),AUC 0.917 vs 0.891(P=.017)。
临床应用与阅片要点
- 作者结论认为卷积神经网络 based on sonographic images 的诊断性能与经验丰富放射科医师实施的美国放射学会TI-RADS分类相当。
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
BACKGROUND AND PURPOSE: Comparison of the diagnostic performance for thyroid cancer on ultrasound between a convolutional neural network and visual assessment by radiologists has been inconsistent. Thus, we aimed to evaluate the diagnostic performance of the convolutional neural network compared with the American College of Radiology Thyroid Imaging Reporting and Data System (TI-RADS) for the diagnosis of thyroid cancer using ultrasound images.
MATERIALS AND METHODS: From March 2019 to September 2019, seven hundred sixty thyroid nodules (≥10 mm) in 757 patients were diagnosed as benign or malignant through fine-needle aspiration, core needle biopsy, or an operation. Experienced radiologists assessed the sonographic descriptors of the nodules, and 1 of 5 American College of Radiology TI-RADS categories was assigned. The convolutional neural network provided malignancy risk percentages for nodules based on sonographic images. Sensitivity, specificity, accuracy, positive predictive value, and negative predictive value were calculated with cutoff values using the Youden index and compared between the convolutional neural network and the American College of Radiology TI-RADS. Areas under the receiver operating characteristic curve were also compared.
RESULTS: Of 760 nodules, 176 (23.2%) were malignant. At an optimal threshold derived from the Youden index, sensitivity and negative predictive values were higher with the convolutional neural network than with the American College of Radiology TI-RADS (81.8% versus 73.9%, P = .009; 94.0% versus 92.2%, P = .046). Specificity, accuracy, and positive predictive values were lower with the convolutional neural network than with the American College of Radiology TI-RADS (86.1% versus 93.7%, P < .001; 85.1% versus 89.1%, P = .003; and 64.0% versus 77.8%, P < .001). The area under the curve of the convolutional neural network was higher than that of the American College of Radiology TI-RADS (0.917 versus 0.891, P = .017).
CONCLUSIONS: The convolutional neural network provided diagnostic performance comparable with that of the American College of Radiology TI-RADS categories assigned by experienced radiologists.
引用
- Kim GR, Lee E, Kim HR, et al. Convolutional Neural Network to Stratify the Malignancy Risk of Thyroid Nodules: Diagnostic Performance Compared with the American College of Radiology Thyroid Imaging Reporting and Data System Implemented by Experienced Radiologists. AJNR Am J Neuroradiol. 2021. PMID: 33985947. doi:10.3174/ajnr.A7149
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。