文献速递甲状腺疾病

基于深度学习的人工智能模型辅助甲状腺结节诊断与管理:儿科队列中评估甲状腺恶性的初步结果

A Deep Learning-Based Artificial Intelligence Model Assisting Thyroid Nodule Diagnosis and Management: Pilot Results for Evaluating Thyroid Malignancy in Pediatric Cohorts.
PubMed 文献 · Thyroid · 2025-06-02

该研究回顾性纳入两个儿科队列共128例患儿(平均年龄15.5±2.4岁,女童103例)的156个甲状腺结节,评估基于成人数据训练的AI-Thyroid深度学习模型在儿科结节中的诊断性能。模型在三种超声图像场景下AUROC为0.913-0.929,敏感度78.7-89.4%,特异度79.8-91.7%,且AUROC高于ACR-TIRADS和K-TIRADS。

要点

  • AI-Thyroid模型在儿科甲状腺结节中AUROC达0.913-0.929,敏感度78.7-89.4%,特异度79.8-91.7%。
  • 不同超声切面及两个儿科队列间AUROC无显著差异(均p>0.05;队列间p=0.804)。
  • AI-Thyroid的AUROC最高,优于ACR-TIRADS(p=0.016)和K-TIRADS(p<0.001)。

核心结论

  • AI-Thyroid在诊断儿童甲状腺癌方面表现出高性能,未来研究应聚焦于优化AI-Thyroid的儿科应用并探索其与组织取样在临床实践中的协同作用。

研究设计与样本

  • 回顾性识别两个儿科队列,共128例患儿(平均年龄15.5±2.4岁,女童103例),在两家机构接受甲状腺结节超声检查并有组织学确认,分析156个结节。
  • 将基于成人数据训练的AI-Thyroid深度学习模型在儿科结节上测试,场景包括轴位超声图像、纵位超声图像及两者联合。
  • 基于两个儿科队列及年龄组(≥14岁 vs <14岁)进行亚组分析,并与放射科医生使用甲状腺影像报告和数据系统(TIRADS)的判读进行比较。

主要发现

  • 156个结节中47个(30.1%)为恶性。
  • AI-Thyroid的AUROC、敏感度和特异度分别为0.913-0.929、78.7-89.4%和79.8-91.7%。
  • AUROC在不同图像平面间无显著差异(均p>0.05),在两个儿科队列间亦无显著差异(p=0.804)。
  • 年龄组间敏感度和特异度无显著差异(均p>0.05),但<14岁患者的AUROC值高于≥14岁患者(均p<0.01)。
  • AI-Thyroid的AUROC值最高,其次为ACR-TIRADS和K-TIRADS(分别为p=0.016和p<0.001)。

临床怎么用

  • 原文结论未据此给出具体临床推荐。

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)。

原文

Purpose: Artificial intelligence (AI) models have shown promise in predicting malignant thyroid nodules in adults; however, research on deep learning (DL) for pediatric cases is limited. We evaluated the applicability of a DL-based model for assessing thyroid nodules in children. Methods: We retrospectively identified two pediatric cohorts (n = 128; mean age 15.5 ± 2.4 years; 103 girls) who had thyroid nodule ultrasonography (US) with histological confirmation at two institutions. The AI-Thyroid DL model, originally trained on adult data, was tested on pediatric nodules in three scenarios axial US images, longitudinal US images, and both. We conducted a subgroup analysis based on the two pediatric cohorts and age groups (≥14 years vs. < 14 years) and compared the model's performance with radiologist interpretations using the Thyroid Imaging Reporting and Data System (TIRADS). Results: Out of 156 nodules analyzed, 47 (30.1%) were malignant. AI-Thyroid demonstrated respective area under the receiver operating characteristic (AUROC), sensitivity, and specificity values of 0.913-0.929, 78.7-89.4%, and 79.8-91.7%, respectively. The AUROC values did not significantly differ across the image planes (all p > 0.05) and between the two pediatric cohorts (p = 0.804). No significant differences were observed between age groups in terms of sensitivity and specificity (all p > 0.05) while the AUROC values were higher for patients aged <14 years compared to those aged ≥14 years (all p < 0.01). AI-Thyroid yielded the highest AUROC values, followed by ACR-TIRADS and K-TIRADS (p = 0.016 and p < 0.001, respectively). Conclusion: AI-Thyroid demonstrated high performance in diagnosing pediatric thyroid cancer. Future research should focus on optimizing AI-Thyroid for pediatric use and exploring its role alongside tissue sampling in clinical practice.

来源:Thyroid,查看原文。版权归原作者所有。

引用

  1. Ha EJ, Lee JH, Mak N, et al. A Deep Learning-Based Artificial Intelligence Model Assisting Thyroid Nodule Diagnosis and Management: Pilot Results for Evaluating Thyroid Malignancy in Pediatric Cohorts. Thyroid. 2025. PMID: 40454939. doi:10.1089/thy.2024.0627

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。