文献速递甲状腺与浅表头颈US

基于ACR TI-RADS特征的甲状腺结节超声诊断人工智能模型

An Artificial Intelligence Model Based on ACR TI-RADS Characteristics for US Diagnosis of Thyroid Nodules.
PubMed 文献 · Radiology · 2022-03-22

回顾性研究纳入636例患者1588个手术病理证实的甲状腺结节,开发基于ACR TI-RADS特征的人工智能模型MTI-RADS,并与基于手术病理良恶性训练的模型MDiag及不同经验放射科医师比较。MTI-RADS的AUC为0.91,敏感度83%,特异度87%;AUC高于MDiag(0.91 vs 0.84,P=0.001),敏感度与经验丰富医师无显著差异,特异度高于经验丰富及初级医师。

要点

  • MTI-RADS诊断甲状腺结节的AUC为0.91,敏感度83%,特异度87%。
  • MTI-RADS的AUC高于基于手术病理训练的MDiag(0.91 vs 0.84,P=0.001)。
  • MTI-RADS特异度高于经验丰富医师(87% vs 80%,P=0.02)和初级医师(87% vs 75%,P=0.001)。

核心结论

  • 基于ACR TI-RADS特征的人工智能模型MTI-RADS的AUC高于基于手术病理良恶性训练的模型MDiag;MTI-RADS的AUC和敏感度超过初级医师,特异度高于经验丰富和初级医师。

研究设计与样本

  • 回顾性研究,纳入636例连续患者(平均年龄49岁±14[SD],女性485例)的1588个手术病理证实结节;MTI-RADS和MDiag在1345个结节(2018年1月至2019年12月)的超声图像上训练,在243个结节(2019年1月至2019年12月)的测试集上比较MTI-RADS、MDiag及不同经验水平放射科医师的表现,采用DeLong法和McNemar检验。

诊断标准与关键数值

  • 测试集243个结节中,MTI-RADS的AUC为0.91,敏感度83%(55/66个恶性结节),特异度87%(154/177个良性结节);经验丰富医师AUC为0.93(P=0.45)、敏感度92%(61/66,P=0.07)、特异度80%(141/177,P=0.02);初级医师AUC为0.78(P<0.001)、敏感度70%(46/66,P=0.04)、特异度75%(133/177,P=0.001);MDiag的AUC为0.84(与MTI-RADS比较P=0.001)。

临床应用与阅片要点

  • MTI-RADS与经验丰富组的一致性率高于与初级组的一致性率:成分79%(n=193)vs 73%(n=178),P=0.02;回声75%(n=183)vs 68%(n=166),P=0.04;形状93%(n=227)vs 88%(n=215),P=0.04;边缘光滑或界限不清72%(n=174)vs 63%(n=152),P=0.002。

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 US-based diagnosis of thyroid nodules is subjective and influenced by radiologists' experience levels. Purpose To develop an artificial intelligence model based on American College of Radiology Thyroid Imaging Reporting and Data System characteristics for diagnosing thyroid nodules and identifying nodule characteristics (hereafter, MTI-RADS) and to compare the performance of MTI-RADS, radiologists, and a model trained on benign and malignant status based on surgical histopathologic analysis (hereafter, MDiag). Materials and Methods In this retrospective study, 1588 surgically proven nodules from 636 consecutive patients (mean age, 49 years ± 14 [SD]; 485 women) were included. MTI-RADS and MDiag were trained on US images of 1345 nodules (January 2018 to December 2019). The performance of MTI-RADS was compared with that of MDiag and radiologists with different experience levels on the test data set (243 nodules, January 2019 to December 2019) with the DeLong method and McNemar test. Results The area under the receiver operating characteristic curve (AUC) and sensitivity of MTI-RADS were 0.91 and 83% (55 of 66 nodules), respectively, which were not significantly different from those of experienced radiologists (0.93 [P = .45] and 92% [61 of 66 nodules; P = .07]) and exceeded those of junior radiologists (0.78 [P < .001] and 70% [46 of 66 nodules; P = .04]). The specificity of MTI-RADS (87% [154 of 177 nodules]) was higher than that of both experienced and junior radiologists (80% [141 of 177 nodules; P = .02] and 75% [133 of 177 nodules; P = .001], respectively). The AUC of MTI-RADS was higher than that of MDiag (0.91 vs 0.84, respectively; P = .001). In the test set of 243 nodules, the consistency rates between MTI-RADS and the experienced group were higher than those between MTI-RADS and the junior group for composition (79% [n = 193] vs 73% [n = 178], respectively; P = .02), echogenicity (75% [n = 183] vs 68% [n = 166]; P = .04), shape (93% [n = 227] vs 88% [n = 215]; P = .04), and smooth or ill-defined margin (72% [n = 174] vs 63% [n = 152]; P = .002). Conclusion The area under the receiver operating characteristic curve (AUC) of an artificial intelligence model based on the American College of Radiology Thyroid Imaging Reporting and Data System (TI-RADS) was higher than that of a model trained on benign and malignant status based on surgical histopathologic analysis. The AUC and sensitivity of the model based on TI-RADS exceeded those of junior radiologists; the specificity of the model was higher than that of both experienced and junior radiologists. © RSNA, 2022.

来源:Radiology,查看原文。版权归原作者所有。

引用

  1. Chen, Gao, He, et al. An Artificial Intelligence Model Based on ACR TI-RADS Characteristics for US Diagnosis of Thyroid Nodules. Radiology. 2022. PMID: 35315719. doi:10.1148/radiol.211455

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。