A Computer-Aided Diagnosis System Using Artificial Intelligence for the Diagnosis and Characterization of Thyroid Nodules on Ultrasound: Initial Clinical Assessment
A Computer-Aided Diagnosis System Using Artificial Intelligence for the Diagnosis and Characterization of Thyroid Nodules on Ultrasound: Initial Clinical Assessment
复制标题
基于人工智能的甲状腺结节超声诊断与表征计算机辅助诊断系统的初步临床评估
DOI：
10.1089/thy.2016.0372
复制
发表时间：
2017-04-01
期刊：
影响因子：
6.6
通讯作者：
Lee, Jeong Hyun
中科院分区：
文献类型：
--
作者：
Choi, Young Jun;Baek, Jung Hwan;Lee, Jeong Hyun
背景资料：描述了一种新的、市售的、使用人工智能（AI）的计算机辅助诊断（CAD）系统用于甲状腺超声的初步临床评估，并评估了其在恶性甲状腺结节诊断和结节特征分类中的性能。方法：2015年11月至2016年2月连续入组了确诊为甲状腺结节（无论是良性还是恶性）的患者。一名经验丰富的放射科医生审查了甲状腺结节的超声图像特征，而另一名放射科医生使用CAD系统评估了相同的甲状腺结节，提供了超声特征并诊断结节是良性还是恶性。结果：共纳入89例患者的102个甲状腺结节，其中良性结节59个（57.8%），恶性结节43个（42.2%）。CAD系统显示出与有经验的放射科医师相似的灵敏度（90.7% vs. 88.4%，p > 0.99），但特异性较低，受试者工作特征（AUROC）曲线下面积较低（特异性：74.6% vs. 94.9%，p = 0.002; AUROC：0.83 vs. 0.92，p = 0.021）。超声特征分类放射科医师和CAD系统之间的成分、方向、回声和海绵状）基本一致（分别为j = 0.659、0.740、0.733和0.658），而差值显示了公平的一致性结论：应用AI的CAD系统对恶性甲状腺结节诊断的敏感性与有经验的放射科医师相当，但特异性和准确性低于有经验的放射科医师。CAD系统与经验丰富的放射科医生在甲状腺结节的定性方面表现出可接受的一致性。
Background: An initial clinical assessment is described of a new, commercially available, computer-aided diagnosis (CAD) system using artificial intelligence (AI) for thyroid ultrasound, and its performance is evaluated in the diagnosis of malignant thyroid nodules and categorization of nodule characteristics.Methods: Patients with thyroid nodules with decisive diagnosis, whether benign or malignant, were consecutively enrolled from November 2015 to February 2016. An experienced radiologist reviewed the ultrasound image characteristics of the thyroid nodules, while another radiologist assessed the same thyroid nodules using the CAD system, providing ultrasound characteristics and a diagnosis of whether nodules were benign or malignant. The diagnostic performance and agreement of US characteristics between the experienced radiologist and the CAD system were compared.Results: In total, 102 thyroid nodules from 89 patients were included; 59 (57.8%) were benign and 43 (42.2%) were malignant. The CAD system showed a similar sensitivity as the experienced radiologist (90.7% vs. 88.4%, p > 0.99), but a lower specificity and a lower area under the receiver operating characteristic (AUROC) curve (specificity: 74.6% vs. 94.9%, p = 0.002; AUROC: 0.83 vs. 0.92, p = 0.021). Classifications of the ultrasound characteristics (composition, orientation, echogenicity, and spongiform) between radiologist and CAD system were in substantial agreement (j = 0.659, 0.740, 0.733, and 0.658, respectively), while the margin showed a fair agreement (j = 0.239).Conclusion: The sensitivity of the CAD system using AI for malignant thyroid nodules was as good as that of the experienced radiologist, while specificity and accuracy were lower than those of the experienced radiologist. The CAD system showed an acceptable agreement with the experienced radiologist for characterization of thyroid nodules.