文献速递消化内镜消化道肿瘤与早癌

GastroNet-5M:用于消化内镜基础模型开发的多中心数据集

GastroNet-5M: A Multicenter Dataset for Developing Foundation Models in Gastrointestinal Endoscopy.
PubMed 文献 · Gastroenterology · 2025-07-30

本研究构建了GastroNet-5M数据集,包含2012至2020年荷兰8家医院的4,820,653张匿名消化内镜图像,约50万次操作。采用自监督学习开发基础模型,并在17项消化内镜AI应用中与公开内镜基础模型及先进非基础模型比较,结果显示GastroNet-5M预训练模型在多数分类和分割任务上准确率更优,所需应用特异性训练数据更少,对数据异质性更稳健。

要点

  • GastroNet-5M含约500万张内镜图像,来自8家荷兰医院。
  • 自监督预训练模型在17项内镜AI任务中多数准确率优于对照。
  • 预训练减少应用特异性数据需求并提升对设备异质性的稳健性。

核心结论

  • 使用GastroNet-5M预训练内镜深度学习系统可提高诊断准确率,减少对稀缺应用特异性图像和标注的需求,并增强对临床实践中数据异质性的稳健性。

研究设计与样本

  • GastroNet-5M由2012至2020年荷兰8家医院采集的匿名通用内镜图像构成,共4,820,653张图像,约50万次操作。
  • 采用自监督学习利用GastroNet-5M开发基础模型,用于后续下游内镜人工智能应用。
  • 在17项覆盖全消化道的內镜AI应用中,将GastroNet-5M基础模型与公开内镜基础模型及先进非基础模型进行比较。

主要发现

  • GastroNet-5M预训练模型在几乎所有分类和分割任务的准确率上优于所有其他模型。
  • GastroNet-5M预训练模型达到满意性能所需的应用特异性训练数据显著更少。
  • 当模型暴露于不同内镜制造商图像等数据异质性时,GastroNet-5M预训练模型表现更稳健。

临床怎么用

  • 可利用公开的GastroNet-5M数据集预训练内镜AI模型,以减少对应用特异性标注数据的依赖。
  • 在临床实践中,预训练模型可能对来自不同内镜设备的数据具有更好的泛化能力。

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)。

原文

BACKGROUND & AIMS: Training deep learning systems in endoscopy generally requires vast datasets of annotated images, which are often scarce and costly to obtain. Foundation models are pretrained on large, diverse datasets and can be applied across a wide range of tasks with minimal additional fine-tuning. For endoscopy, foundation models require datasets of general endoscopic images. Yet, datasets for developing such models remain limited. In this study, we present GastroNet-5M, a dataset comprising 4,820,653 endoscopic images of ∼500,000 procedures. METHODS: GastroNet-5M consists of anonymized general endoscopic images captured in 8 Dutch hospitals between 2012 and 2020. Using self-supervised learning, GastroNet-5M was used to develop a foundation model for subsequent downstream endoscopic artificial intelligence (AI) applications. We compared our GastroNet-5M foundation model with publicly available endoscopic foundation models and state-of-the-art nonfoundation models across 17 endoscopic AI applications throughout the gastrointestinal tract. Outcome measures were classification and segmentation accuracy, data efficiency, and robustness to data heterogeneity. RESULTS: GastroNet-5M-pretrained models outperformed all other models in accuracy for nearly all classification and segmentation tasks. Furthermore, GastroNet-5M-pretrained models required significantly less application-specific training data for satisfactory model performance and displayed more robust performance when models were exposed to data heterogeneity such as imagery from different endoscope manufacturers. CONCLUSIONS: This study presents GastroNet-5M, a dataset of ∼5 million endoscopic images. Pretraining endoscopic deep learning systems with GastroNet-5M improves diagnostic accuracy, reduces the need for scarce application-specific endoscopic imagery and annotations, and increases their robustness to the inevitable data heterogeneity in clinical practice. This may significantly accelerate development and implementation of endoscopic AI systems. GastroNet-5M is publicly available for scientific use.

来源:Gastroenterology,查看原文。版权归原作者所有。

引用

  1. Jong MR, Boers TGW, Fockens KN, et al. GastroNet-5M: A Multicenter Dataset for Developing Foundation Models in Gastrointestinal Endoscopy. Gastroenterology. 2025. PMID: 40749857. doi:10.1053/j.gastro.2025.07.030

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。