文献速递神经儿科影像US

基于颅脑超声影像的深度学习模型用于脑室周围-脑室内出血检测与分级的开发与验证:一项双中心研究

Development and validation of a cranial ultrasound imaging-based deep learning model for periventricular-intraventricular haemorrhage detection and grading: a two-centre study.
PubMed 文献 · Pediatr Radiol · 2025-07-29

该双中心观察性研究纳入两家医院的1060例受试者,开发了整合卷积块注意力模块的深度学习模型(periventricular IVH net),用于颅脑超声图像检测和分级脑室周围-脑室内出血(IVH)。回顾性建模数据集773例(2020年1月至2023年7月),前瞻性双中心验证集287例(2023年8月至2024年1月);回顾性数据AUC 0.99(95%CI 0.98-0.99),前瞻性验证AUC 0.961(95%CI 0.94-0.98)、准确率0.89(95%CI 0.86-0.92)。结论认为该模型在儿科临床应用潜力巨大,将人工智能与儿科超声结合可提高IVH诊断的准确性和效率。

要点

  • 前瞻性双中心验证中模型AUC 0.961(95%CI 0.94-0.98)、准确率0.89(95%CI 0.86-0.92)。
  • 回顾性数据中模型AUC 0.99(95%CI 0.98-0.99)、精确率0.92(95%CI 0.89-0.95)。
  • 模型采用卷积块注意力模块机制,并以显著性图可视化影响检测的感兴趣区。

核心结论

  • 双中心前瞻性验证结果显示periventricular IVH net模型在儿科临床应用方面具有巨大潜力,人工智能与儿科超声结合可提高IVH诊断的准确性和效率,尤其在基层医院或社区医院。

研究设计与样本

  • 多中心观察性研究,纳入两家医院共1060例病例和健康对照;回顾性建模数据集773例(2020年1月至2023年7月),前瞻性双中心验证数据集287例(2023年8月至2024年1月),回顾性数据随机分为训练集和验证集后以前瞻性双中心数据独立验证。

诊断标准与关键数值

  • 回顾性数据:AUC 0.99(95%CI 0.98-0.99),精确率0.92(95%CI 0.89-0.95),召回率0.93(95%CI 0.89-0.95),F1分数0.93(95%CI 0.90-0.95);前瞻性双中心验证数据:AUC 0.961(95%CI 0.94-0.98),准确率0.89(95%CI 0.86-0.92)。

临床应用与阅片要点

  • 模型可用于颅脑超声图像中脑室周围IVH的检测和分级,并通过显著性图可视化影响检测的感兴趣区,t-SNE算法可视化模型检测参数的聚类。

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: Periventricular-intraventricular haemorrhage (IVH) is the most prevalent type of neonatal intracranial haemorrhage. It is especially threatening to preterm infants, in whom it is associated with significant morbidity and mortality. Cranial ultrasound has become an important means of screening periventricular IVH in infants. The integration of artificial intelligence with neonatal ultrasound is promising for enhancing diagnostic accuracy, reducing physician workload, and consequently improving periventricular IVH outcomes.

OBJECTIVES: The study investigated whether deep learning-based analysis of the cranial ultrasound images of infants could detect and grade periventricular IVH.

MATERIALS AND METHODS: This multicentre observational study included 1,060 cases and healthy controls from two hospitals. The retrospective modelling dataset encompassed 773 participants from January 2020 to July 2023, while the prospective two-centre validation dataset included 287 participants from August 2023 to January 2024. The periventricular IVH net model, a deep learning model incorporating the convolutional block attention module mechanism, was developed. The model's effectiveness was assessed by randomly dividing the retrospective data into training and validation sets, followed by independent validation with the prospective two-centre data. To evaluate the model, we measured its recall, precision, accuracy, F1-score, and area under the curve (AUC). The regions of interest (ROI) that influenced the detection by the deep learning model were visualised in significance maps, and the t-distributed stochastic neighbour embedding (t-SNE) algorithm was used to visualise the clustering of model detection parameters.

RESULTS: The final retrospective dataset included 773 participants (mean (standard deviation (SD)) gestational age, 32.7 (4.69) weeks; mean (SD) weight, 1,862.60 (855.49) g). For the retrospective data, the model's AUC was 0.99 (95% confidence interval (CI), 0.98-0.99), precision was 0.92 (0.89-0.95), recall was 0.93 (0.89-0.95), and F1-score was 0.93 (0.90-0.95). For the prospective two-centre validation data, the model's AUC was 0.961 (95% CI, 0.94-0.98) and accuracy was 0.89 (95% CI, 0.86-0.92).

CONCLUSION: The two-centre prospective validation results of the periventricular IVH net model demonstrated its tremendous potential for paediatric clinical applications. Combining artificial intelligence with paediatric ultrasound can enhance the accuracy and efficiency of periventricular IVH diagnosis, especially in primary hospitals or community hospitals.

来源:Pediatr Radiol,查看原文。版权归原作者所有。

引用

  1. Peng Y, Hu Z, Wen M, et al. Development and validation of a cranial ultrasound imaging-based deep learning model for periventricular-intraventricular haemorrhage detection and grading: a two-centre study. Pediatr Radiol. 2025. PMID: 40728538. doi:10.1007/s00247-025-06327-x

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。