Wang Shuo, Xu Jiajun, Tahmasebi Aylin, Daniels Kelly, Liu Ji-Bin, Curry Joseph, Cottrill Elizabeth, Lyshchik Andrej, Eisenbrey John R
Department of Radiology, Thomas Jefferson University, Philadelphia, PA, United States.
Department of Ultrasound, Nanjing First Hospital, Nanjing Medical University, Nanjing, China.
Front Oncol. 2020 Nov 12;10:591846. doi: 10.3389/fonc.2020.591846. eCollection 2020.
The role of next generation sequencing (NGS) for identifying high risk mutations in thyroid nodules following fine needle aspiration (FNA) biopsy continues to grow. However, ultrasound diagnosis even using the American College of Radiology's Thyroid Imaging Reporting and Data System (TI-RADS) has limited ability to stratify genetic risk. The purpose of this study was to incorporate an artificial intelligence (AI) algorithm of thyroid ultrasound with object detection within the TI-RADS scoring system to improve prediction of genetic risk in these nodules.
Two hundred fifty-two nodules from 249 patients that underwent ultrasound imaging and ultrasound-guided FNA with NGS with or without resection were retrospectively selected for this study. A machine learning program (Google AutoML) was employed for both automated nodule identification and risk stratification. Two hundred one nodules were used for model training and 51 reserved for testing. Three blinded radiologists scored the images of the test set nodules using TI-RADS and assigned each nodule as high or low risk based on the presence of highly suspicious imaging features on TI-RADS (very hypoechoic, taller-than-wide, extra-thyroidal extension, punctate echogenic foci). Subsequently, the TI-RADS classification was modified to incorporate AI for T4 nodules while treating T1-3 as low risk and T5 as high risk. All diagnostic predictions were compared to the presence of a high-risk mutation and pathology when available.
The AI algorithm correctly located all nodules in the test dataset (100% object detection). The model predicted the malignancy risk with a sensitivity of 73.9%, specificity of 70.8%, positive predictive value (PPV) of 70.8%, negative predictive value (NPV) of 73.9% and accuracy of 72.4% during the testing. The radiologists performed with a sensitivity of 52.1 ± 4.4%, specificity of 65.2 ± 6.4%, PPV of 59.1 ± 3.5%, NPV of 58.7 ± 1.8%, and accuracy of 58.8 ± 2.5% when using TI-RADS and sensitivity of 53.6 ± 17.6% (p=0.87), specificity of 83.3 ± 7.2% (p=0.06), PPV of 75.7 ± 8.5% (p=0.13), NPV of 66.0 ± 8.8% (p=0.31), and accuracy of 68.7 ± 7.4% (p=0.21) when using AI-modified TI-RADS.
Incorporation of AI into TI-RADS improved radiologist performance and showed better malignancy risk prediction than AI alone when classifying thyroid nodules. Employing AI in existing thyroid nodule classification systems may help more accurately identifying high-risk nodules.
在细针穿刺（FNA）活检后，下一代测序（NGS）在识别甲状腺结节高风险突变方面的作用不断增强。然而，即使使用美国放射学会的甲状腺影像报告和数据系统（TI-RADS）进行超声诊断，对遗传风险进行分层的能力也有限。本研究的目的是在TI-RADS评分系统中纳入一种具有目标检测功能的甲状腺超声人工智能（AI）算法，以改善对这些结节遗传风险的预测。
本研究回顾性选取了249例接受超声成像以及超声引导下FNA并进行NGS检测（有或无手术切除）的患者的252个结节。采用机器学习程序（谷歌自动机器学习）进行自动结节识别和风险分层。201个结节用于模型训练，51个留作测试。三名不知情的放射科医生使用TI-RADS对测试集结节的图像进行评分，并根据TI-RADS上高度可疑的影像特征（极低回声、纵横比大于1、甲状腺外延伸、点状强回声灶）将每个结节分为高风险或低风险。随后，对TI-RADS分类进行修改，将AI纳入T4结节的评估，同时将T1-3视为低风险，T5视为高风险。所有诊断预测均与高风险突变的存在情况以及可用的病理结果进行比较。
AI算法正确定位了测试数据集中的所有结节（目标检测率100%）。在测试期间，该模型预测恶性风险的灵敏度为73.9%，特异度为70.8%，阳性预测值（PPV）为70.8%，阴性预测值（NPV）为73.9%，准确率为72.4%。放射科医生使用TI-RADS时的灵敏度为52.1±4.4%，特异度为65.2±6.4%，PPV为59.1±3.5%，NPV为58.7±1.8%，准确率为58.8±2.5%；使用AI修改后的TI-RADS时，灵敏度为53.6±17.6%（p=0.87），特异度为83.3±7.2%（p=0.06），PPV为75.7±8.5%（p=0.13），NPV为66.0±8.8%（p=0.31），准确率为68.7±7.4%（p=0.21）。
将AI纳入TI-RADS可提高放射科医生的表现，并且在对甲状腺结节进行分类时，比单独使用AI显示出更好的恶性风险预测能力。在现有的甲状腺结节分类系统中应用AI可能有助于更准确地识别高风险结节。
