文献速递神经儿科影像CT

成人训练AI工具对6-17岁儿童头颅CT颅内出血检测性能

Performance of an adult-trained AI tool for intracranial hemorrhage detection on head CT in children aged 6-17 years.
PubMed 文献 · Pediatr Radiol · 2026-01-31

这项回顾性多中心研究纳入1996例6-17岁儿童平扫头颅CT,评估成人训练并经FDA批准的AI工具对颅内出血的检测性能。以三位放射科医师仲裁结果为金标准,AI的敏感度为94.2%、特异度为94.7%、准确率为94.6%。研究提示成人训练的AI工具在部分儿童人群中可能具备与成人相当的检测性能,但临床部署前仍需前瞻性验证。

要点

  • AI对6-17岁儿童颅内出血有高敏感度和高阴性预测值,可辅助初筛。
  • AI假阳性较多,最常见原因是线束硬化伪影和解剖结构误判。
  • 儿童人群使用成人训练AI工具仍需前瞻性验证,不宜直接临床部署。

核心结论

  • 该成人训练AI工具对6-17岁儿童头颅CT颅内出血检测显示高敏感度、特异度和准确率,与成人性能相当。
  • 选择性引入成人训练AI工具有望扩大部分儿童人群的AI辅助分诊可及性,但部署前仍需前瞻性验证。

研究设计与样本

  • 共纳入1996例平扫头颅CT,其中女性768例、男性1223例、性别未知5例。
  • 采用经验证的自然语言处理工具对放射学报告进行颅内出血阳性或阴性分类。
  • AI工具独立分析DICOM图像,三名放射科医师对AI与NLP不一致病例进行盲法仲裁作为金标准。

关键影像表现/征象

  • AI假阳性最常见由线束硬化伪影导致,占21.6%。
  • AI假阳性其次由解剖结构误判导致,占18.6%。
  • AI正确识别了放射科医师漏诊的部分颅内出血病例。

诊断标准与关键数值

  • 颅内出血患病率为8.6%,即1996例中172例为阳性。
  • AI敏感度为94.2%,即172例中162例被正确识别,95%CI为89.6-97.2%。
  • AI特异度为94.7%,即1824例阴性中1727例被正确排除,95%CI为93.6-95.7%。
  • AI准确率为94.6%,即1996例中1889例分类正确,95%CI为93.6-95.6%。
  • AI阳性预测值为62.5%,即259例AI阳性中162例为真阳性,95%CI为57.8-67.0%。

临床应用与阅片要点

  • AI可作为6-17岁儿童头颅CT颅内出血的辅助初筛工具,高阴性预测值有助于降低漏诊风险。
  • 阅片时需重点复核AI阳性病例,警惕线束硬化伪影和解剖结构误判造成的假阳性。
  • 该AI工具仍有假阴性,AI阴性不能完全排除颅内出血,最终诊断需依靠放射科医师。

局限性

  • 原文指出临床部署前需要前瞻性验证。
  • 研究为回顾性设计,阳性预测值偏低提示假阳性较多。
  • 仅纳入6-17岁儿童,未覆盖更小年龄儿童。

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: Most commercially available artificial intelligence (AI) tools in radiology are trained and approved for adult use, creating an access gap for pediatric patients. Intracranial hemorrhage (ICH) detection is a common adult AI application without pediatric FDA clearance.

OBJECTIVE: To evaluate the performance of an FDA-cleared, adult-trained AI tool for ICH detection on non-contrast head CT (NCHCT) in pediatric patients aged 6-17 years.

MATERIALS AND METHODS: This retrospective, multi-institution study analyzed consecutive pediatric NCHCTs performed between January 2017 and November 2022 across 21 sites. Inclusion criteria were patient age 6-17 years and adequate imaging quality. Radiology reports were classified as ICH-positive or ICH-negative using a validated natural language processing (NLP) tool. The AI tool analyzed DICOM images independently. Discordant AI-NLP cases underwent blinded adjudication by three radiologists to establish ground truth. Performance metrics includingsensitivity, specificity, accuracy, positive predictive value (PPV), and negative predictive value (NPV) were calculated with Wilson 95% confidence intervals (CIs).

RESULTS: The cohort included 1,996 NCHCTs (768 females, 1,223 males, 5 unknown). ICH prevalence was 8.6% (172/1,996). Compared with ground truth, AI achieved 94.2% sensitivity (162/172, 95% CI, 89.6-97.2%), 94.7% specificity (1,727/1,824, 95% CI, 93.6-95.7%), 94.6% accuracy (1,889/1,996, 95% CI, 93.6-95.6%), 62.5% PPV (162/259, 95% CI, 57.8-67.0%), and 99.4% NPV (1,727/1,737, 95% CI, 99.0-99.7%). AI correctly identified ICH in cases missed by radiologists, but false positives were common, most often due to streak artifact (21.6%) and misclassified anatomy (18.6%). Interrater agreement for ground truth adjudication was substantial (κ=0.683).

CONCLUSION: An adult-trained AI tool demonstrated high sensitivity, specificity, and accuracy for ICH detection in pediatric patients aged 6-17 years, comparable to its adult performance. Selective adaptation of adult-trained AI tools could expand access to AI-assisted triage for certain pediatric populations, potentially reducing delays in critical imaging interpretation. However, prospective validation is required before clinical deployment.

来源:Pediatr Radiol,查看原文。版权归原作者所有。

引用

  1. Cavallo, Sher, Chen, et al. Performance of an adult-trained AI tool for intracranial hemorrhage detection on head CT in children aged 6-17 years. Pediatr Radiol. 2026. PMID: 41619014. doi:10.1007/s00247-026-06527-z

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。