文献速递腹部技术与安全CT

RSNA 2023腹部创伤AI挑战赛高性能机器学习模型在CT脾损伤检测与分级中的外部验证

External validation of an RSNA 2023 Abdominal Trauma AI Challenge high performing machine learning model in the detection and grading of splenic injuries on CT.
PubMed 文献 · Abdom Radiol (NY) · 2025-05-02

本研究用1216例CT(脾损伤阳性608例、阴性608例)外部数据集验证RSNA 2023腹部创伤AI挑战赛获奖模型。模型二分类脾损伤AUC 0.931,准确率0.849,敏感度0.747,特异度0.951;高级别脾损伤AUC 0.950,准确率0.928,敏感度0.719,特异度0.958。结论认为模型性能强、可靠且具泛化性,支持其潜在临床应用。

要点

  • 模型二分类脾损伤敏感度0.747、特异度0.951,阴性排除能力较强。
  • 高级别脾损伤分级AUC 0.950,准确率0.928,特异度0.958。
  • 外部数据集与训练集地理和时间上不同,支持模型泛化性。

核心结论

  • 该机器学习模型在外部数据集上检测和分级脾损伤表现出强而可靠的性能与泛化性,支持其在脾创伤患者快速准确诊断中的潜在临床应用。

研究设计与样本

  • 单中心回顾性研究,外部数据集含1216例CT扫描(脾损伤阳性608例、阴性608例);模型在RSNA腹部创伤性损伤CT(RATIC)数据集上训练,采用包含2D MaxVit和带LSTM的2.5D CoatNet的多组件流程进行研究级预测。

诊断标准与关键数值

  • 二分类脾损伤:AUC 0.931(95%CI 0.917, 0.945),准确率0.849(95%CI 0.827, 0.868),敏感度0.747(95%CI 0.711, 0.780),特异度0.951(95%CI 0.930, 0.965)。
  • 高级别脾损伤:AUC 0.950(95%CI 0.932, 0.968),准确率0.928(95%CI 0.912, 0.941),敏感度0.719(95%CI 0.643, 0.784),特异度0.958(95%CI 0.944, 0.968)。

临床应用与阅片要点

  • 作者认为模型性能支持其潜在临床应用,尤其用于脾创伤患者的快速准确诊断。
  • 作者指出RSNA AI挑战赛对推进医学影像临床研究和应用具有价值。

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

PURPOSE: This study aims to validate the performance of an award-winning machine learning (ML) model from the Radiological Society of North America (RSNA) 2023 Abdominal Trauma AI Challenge in detecting splenic injuries on CT scans using a large, geographically and temporally distinct external dataset.

METHOD: A single-center retrospective study was conducted using an external dataset comprising 1216 CT scans (608 positive and 608 negative for splenic injuries). The ML model, trained on the RSNA Abdominal Traumatic Injury CT (RATIC) dataset, employs a multi-component pipeline including 2D MaxVit, 2.5D CoatNet with LSTM for study-level predictions. Model performance was evaluated using sensitivity, specificity, PPV, NPV, accuracy, F1 score, and AUC.

RESULTS: The ML model achieved an AUC of 0.931 (95% CI: 0.917, 0.945) for binary classification of splenic injuries, with an accuracy of 0.849 (95% CI: 0.827, 0.868), sensitivity of 0.747 (95% CI: 0.711, 0.780), and specificity of 0.951 (95% CI: 0.930, 0.965). For high-grade splenic injuries, the model achieved an AUC of 0.950 (95% CI: 0.932, 0.968), accuracy of 0.928 (95% CI: 0.912, 0.941), sensitivity of 0.719 (95% CI: 0.643, 0.784), and specificity of 0.958 (95% CI: 0.944, 0.968).

CONCLUSION: The ML model shows strong, reliable performance and generalizability in detecting and grading splenic injuries on CT scans. This supports its potential clinical application, particularly for quick and accurate diagnosis in splenic trauma patients, and highlights the value of RSNA AI challenges in advancing clinical research and applications in medical imaging.

来源:Abdom Radiol (NY),查看原文。版权归原作者所有。

引用

  1. Kirpalani A, Viel T, Hu Z, et al. External validation of an RSNA 2023 Abdominal Trauma AI Challenge high performing machine learning model in the detection and grading of splenic injuries on CT. Abdom Radiol (NY). 2025. PMID: 40312490. doi:10.1007/s00261-025-04910-2

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。