文献速递腹部CT

基于增强CT图像深度学习自动检测化脓性肝脓肿并诊断肺炎克雷伯菌感染的多中心研究

Automated detection of pyogenic liver abscess and diagnosis of Klebsiella pneumoniae infection based on CECT images with deep learning: A multicenter study.
PubMed 文献 · Eur J Radiol · 2025-10-01

本研究从三家医疗中心纳入2011年4月至2024年4月的492例化脓性肝脓肿患者,开发并验证了模拟临床工作流程的人工智能模型PLADA,用V-Net分割病灶并提取影像组学特征,构建临床、影像组学及临床-影像整合模型诊断肺炎克雷伯菌肝脓肿,AdaBoost临床-影像模型外部验证AUC为0.847,敏感度71.9%、特异度86.4%。

要点

  • PLADA系统用V-Net自动分割肝脓肿病灶,平均戴斯系数0.941(95%CI 0.899-0.983)。
  • 临床-影像整合模型在训练队列各算法平均AUC均超过0.9。
  • AdaBoost临床-影像模型外部验证AUC 0.847(95%CI 0.753-0.940),敏感度71.9%、特异度86.4%。

核心结论

  • PLADA系统通过临床可解释的两阶段AI框架,为肺炎克雷伯菌肝脓肿诊断提供准确、无创的方法,在资源有限地区对早期检测显示出前景。

研究设计与样本

  • 多中心研究,纳入三家医疗中心2011年4月至2024年4月的492例化脓性肝脓肿患者,使用增强CT图像,以V-Net深度神经网络自动分割病灶,提取影像组学特征并用六种机器学习算法构建临床、影像组学及临床-影像整合模型,在训练队列开发并在多中心框架下外部验证。

诊断标准与关键数值

  • PLADA算法自动分割病灶的平均戴斯系数为0.941(95%CI 0.899-0.983)。
  • 临床-影像模型在训练队列中各算法平均AUC均超过0.9。
  • AdaBoost临床-影像模型在外部验证队列AUC为0.847(95%CI 0.753-0.940),敏感度71.9%,特异度86.4%。
  • 决策曲线分析证实临床实用性。

局限性

  • 原文指出该研究受限于回顾性、单一国家数据集。

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: Accurate identification of bacterial pathogens in pyogenic liver abscess (PLA) remains challenging in low- and middle-income countries (LMICs). We developed and validated an artificial intelligence (AI) model that replicates clinical workflow to detect and diagnose Klebsiella pneumoniae liver abscess (KPLA) using contrast-enhanced computerized tomography (CECT).

METHODS: Patients with PLA were enrolled from three medical centers between April 2011 and April 2024. The Pyogenic Liver Abscess Detection with AI (PLADA) system employed a V-Net deep neural network for automated lesion segmentation. Radiomics features were subsequently extracted and ranked by importance. Six machine learning algorithms were used to develop clinical, radiomics, and integrated clinical-imaging models for KPLA diagnosis in the training cohort, with external validation in a multicenter framework.

RESULTS: A total of 492 PLA patients were identified. The PLADA algorithm accurately segments the lesions with a mean dice coefficient of 0.941 (95 % confidence interval: 0.899-0.983). The clinical-imaging model demonstrated strong discriminatory performance, with a mean area under the curve (AUC) of over 0.9 across all algorithms in the training cohort. The AdaBoost-based clinical-imaging model achieved an AUC of 0.847 (95 % CI: 0.753-0.940) in the external validation cohort, with high sensitivity (71.9 %) and specificity (86.4 %). Decision curve analysis (DCA) confirmed clinical utility.

CONCLUSIONS: The PLADA system provides an accurate, non-invasive method for KPLA diagnosis through a clinically interpretable two-stage AI framework. While limited by a retrospective, single-country dataset, this approach shows particular promise for early detectionof KPLA in resource-limited settings.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Zhou J, Peng X, Yang Y, et al. Automated detection of pyogenic liver abscess and diagnosis of Klebsiella pneumoniae infection based on CECT images with deep learning: A multicenter study. Eur J Radiol. 2025. PMID: 41072135. doi:10.1016/j.ejrad.2025.112462

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。