文献速递腹部儿科影像外周血管CT

深度学习模型在儿童先天性胆管扩张症增强CT中自动识别腹侧位右肝动脉:开发与临床应用

Deep learning model for automated identification of ventrally positioned right hepatic artery in contrast-enhanced computed tomography of pediatric congenital biliary dilatation: development and clinical application.
PubMed 文献 · Pediatr Radiol · 2026-03-23

本研究基于YOLOv12构建模型,在儿童先天性胆管扩张症增强CT的关键动脉期层面自动识别腹侧位右肝动脉。232例患者分为训练集186例和测试集46例,YOLOv12n模型AUC达0.977,显著优于初级放射科医生(AUC 0.737,P<0.001),与高级放射科医生(AUC 0.947,P=0.515)表现相当。

要点

  • YOLOv12n模型在关键动脉期层面识别腹侧位右肝动脉的AUC为0.977(95%CI 0.913-1.000)。
  • 模型表现显著优于初级放射科医生(AUC 0.737,P<0.001),与高级放射科医生(AUC 0.947,P=0.515)相当。
  • 所有YOLOv12子模型精确率均为1.000,召回率范围0.684-0.895。

核心结论

  • YOLOv12n模型在关键CT层面上对腹侧位右肝动脉识别具有优异诊断性能,达到高级放射科医生水平,支持其在术前评估中的潜在作用。

研究设计与样本

  • 回顾性单中心研究,纳入232例先天性胆管扩张症患者(116例腹侧位右肝动脉,116例对照),分为训练集186例和测试集46例;使用1452个由放射科医生选择的动脉期关键层面训练五个YOLOv12子模型作为第二阶段分类器;以精确率、召回率、F1分数、平均精度均值(mAP)和AUC评估性能,并用DeLong检验与两名放射科医生比较诊断性能。

诊断标准与关键数值

  • YOLOv12n模型召回率0.842、F1分数0.914、mAP50 0.989、AUC 0.977(95%CI 0.913-1.000);初级放射科医生AUC 0.737(P<0.001 vs 模型),高级放射科医生AUC 0.947(P=0.515 vs 模型)。

临床应用与阅片要点

  • 作者认为该模型支持其在术前评估中的潜在作用;原文未据此给出具体阅片或报告推荐。

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)。

英文原文(摘要)· 点击展开

BACKGROUND: Preoperative identification of a ventrally positioned right hepatic artery (vRHA) is critical in congenital biliary dilatation (CBD), as unrecognized variants increase surgical risk. Detection on computed tomography (CT) is challenging in routine pediatric practice.

OBJECTIVE: To develop and validate a You Only Look Once version 12 (YOLOv12)-based model for vRHA identification in contrast-enhanced CT using a targeted key-slice strategy.

MATERIALS AND METHODS: In this retrospective single-center study, 232 CBD patients (116 vRHA, 116 controls) were divided into training (n=186) and test (n=46) sets. Five YOLOv12 sub-models were trained as second-stage classifiers using 1,452 radiologist-selected key arterial-phase slices. Performance was assessed by precision, recall, F1-score, mean average precision (mAP), and area under the curve (AUC). Diagnostic performance was compared with two radiologists using DeLong's test.

RESULTS: All sub-models showed perfect precision (1.000) with recall ranging from 0.684 to 0.895. YOLOv12n achieved the best performance (recall 0.842, F1-score 0.914, mAP50 0.989, AUC 0.977; 95% confidence interval, 0.913-1.000). It significantly outperformed the junior radiologist (AUC 0.737, P<0.001) and demonstrated comparable performance to the senior radiologist (AUC 0.947, P=0.515).

CONCLUSION: The YOLOv12n model achieved excellent diagnostic performance for vRHA identification on key CT slices and performed at a senior radiologist level, supporting its potential role in preoperative assessment.

来源:Pediatr Radiol,查看原文。版权归原作者所有。

引用

  1. Luo J, Wang H, Huang K, et al. Deep learning model for automated identification of ventrally positioned right hepatic artery in contrast-enhanced computed tomography of pediatric congenital biliary dilatation: development and clinical application. Pediatr Radiol. 2026. PMID: 41870581. doi:10.1007/s00247-026-06588-0

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。