文献速递头颈甲状腺与浅表US

利用人工智能修订甲状腺结节ACR TI-RADS风险分层:诊断准确性与实用性

Using Artificial Intelligence to Revise ACR TI-RADS Risk Stratification of Thyroid Nodules: Diagnostic Accuracy and Utility.
PubMed 文献 · Radiology · 2019-05-21

本研究回顾性分析1425个经活检证实的甲状腺结节,用遗传人工智能算法在训练集1325个结节上优化ACR TI-RADS评分,构建AI TI-RADS,并在测试集100个结节中与专家读者、八位非专家放射科医师及专家组比较。AI TI-RADS对八个ACR TI-RADS特征赋予新分值,其中六个特征赋零分以简化分类;专家读者使用AI TI-RADS的AUC为0.93,与ACR TI-RADS的0.91相近,特异度65%(55/85)高于ACR TI-RADS的47%(40/85)(P < .001),八位非专家放射科医师平均特异度55%亦高于ACR TI-RADS的48%(P < .001)。

要点

  • AI TI-RADS对八个ACR TI-RADS特征重新赋分,其中六个特征赋零分,简化了分类。
  • 专家读者使用AI TI-RADS的AUC为0.93,ACR TI-RADS为0.91。
  • 专家读者AI TI-RADS特异度65%(55/85)高于ACR TI-RADS 47%(40/85)(P < .001)。

核心结论

  • 人工智能优化的甲状腺影像报告和数据系统(TI-RADS)验证了ACR TI-RADS,同时略微提高特异度并保持敏感度;此外,它简化了特征赋值,可能提高易用性。

研究设计与样本

  • 回顾性研究,共纳入1264例连续患者的1425个经活检证实的甲状腺结节(1026例女性;平均年龄52.9岁,范围18-93岁),由专家读者按五个ACR TI-RADS类别(成分、回声、形态、边缘、强回声灶)赋分,遗传AI算法应用于训练集1325个结节,以测试集最后100个结节比较系统性能。

诊断标准与关键数值

  • 专家读者使用ACR TI-RADS的AUC为0.91,使用AI TI-RADS的AUC为0.93。
  • 同一专家使用AI TI-RADS的特异度为65%(55/85),高于ACR TI-RADS的47%(40/85)(P < .001)。
  • 八位非专家放射科医师使用AI TI-RADS的平均特异度为55%,高于ACR TI-RADS的48%(P < .001)。

临床应用与阅片要点

  • 原文指出AI TI-RADS简化了特征赋值,可能提高易用性。
  • 原文提供交互式AI TI-RADS计算器,网址为http://deckard.duhs.duke.edu/∼ai-ti-rads。

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 Risk stratification systems for thyroid nodules are often complicated and affected by low specificity. Continual improvement of these systems is necessary to reduce the number of unnecessary thyroid biopsies. Purpose To use artificial intelligence (AI) to optimize the American College of Radiology (ACR) Thyroid Imaging Reporting and Data System (TI-RADS). Materials and Methods A total of 1425 biopsy-proven thyroid nodules from 1264 consecutive patients (1026 women; mean age, 52.9 years [range, 18-93 years]) were evaluated retrospectively. Expert readers assigned points based on five ACR TI-RADS categories (composition, echogenicity, shape, margin, echogenic foci), and a genetic AI algorithm was applied to a training set (1325 nodules). Point and pathologic data were used to create an optimized scoring system (hereafter, AI TI-RADS). Performance of the systems was compared by using a test set of the final 100 nodules with interpretations from the expert reader, eight nonexpert readers, and an expert panel. Initial performance of AI TI-RADS was calculated by using a test for differences between binomial proportions. Additional comparisons across readers were conducted by using bootstrapping; diagnostic performance was assessed by using area under the receiver operating curve. Results AI TI-RADS assigned new point values for eight ACR TI-RADS features. Six features were assigned zero points, which simplified categorization. By using expert reader data, the diagnostic performance of ACR TI-RADS and AI TI-RADS was area under the receiver operating curve of 0.91 and 0.93, respectively. For the same expert, specificity of AI TI-RADS (65%, 55 of 85) was higher (P < .001) than that of ACR TI-RADS (47%, 40 of 85). For the eight nonexpert radiologists, mean specificity for AI TI-RADS (55%) was also higher (P < .001) than that of ACR TI-RADS (48%). An interactive AI TI-RADS calculator can be viewed at http://deckard.duhs.duke.edu/∼ai-ti-rads . Conclusion An artificial intelligence-optimized Thyroid Imaging Reporting and Data System (TI-RADS) validates the American College of Radiology TI-RADS while slightly improving specificity and maintaining sensitivity. Additionally, it simplifies feature assignments, which may improve ease of use. © RSNA, 2019 Online supplemental material is available for this article.

来源:Radiology,查看原文。版权归原作者所有。

引用

  1. Wildman-Tobriner B, Buda M, Hoang JK, et al. Using Artificial Intelligence to Revise ACR TI-RADS Risk Stratification of Thyroid Nodules: Diagnostic Accuracy and Utility. Radiology. 2019. PMID: 31112088. doi:10.1148/radiol.2019182128

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。