基于大规模视觉Transformer的革兰染色血培养玻片自动分类新框架
本研究开发了一种基于Transformer的深度学习模型,用于革兰染色全切片图像(WSI)分类,无需人工标注即可扩展至大数据集。在475张来自Dartmouth-Hitchcock医疗中心的玻片数据集上,模型五折嵌套交叉验证的分类准确率为0.858(95%CI: 0.805, 0.905),AUC为0.952(95%CI: 0.922, 0.976)。在27张来自Stanford Health的外部数据集上无需微调,二分类准确率达0.926(95%CI: 0.885, 0.960),AUC为0.8651(95%CI: 0.6337, 0.9917)。
要点
- 模型可自动分类五种革兰染色WSI类别,无需人工标注。
- 内部数据集分类准确率0.858,AUC 0.952。
- 外部数据集二分类准确率0.926,显示泛化能力。
核心结论
- 基于Transformer的模型能高准确度分类革兰染色WSI,且无需人工标注,具有 scalable 和泛化潜力。
研究设计与样本
- 研究开发了基于Transformer的深度学习模型,使用Dartmouth-Hitchcock医疗中心的475张玻片数据集进行五折嵌套交叉验证,并在Stanford Health的27张外部数据集上测试泛化性。
主要发现
- 在475张玻片数据集上,模型分类五种革兰染色WSI类别的准确率为0.858(95%CI: 0.805, 0.905),AUC为0.952(95%CI: 0.922, 0.976)。
- 在27张外部数据集上,模型无需微调即达到二分类准确率0.926(95%CI: 0.885, 0.960),AUC为0.8651(95%CI: 0.6337, 0.9917),用于区分革兰阳性与革兰阴性细菌。
关键数值与推荐
- 分类准确率0.858(95%CI: 0.805, 0.905),AUC 0.952(95%CI: 0.922, 0.976),基于475张玻片五折嵌套交叉验证。
- 外部二分类准确率0.926(95%CI: 0.885, 0.960),AUC 0.8651(95%CI: 0.6337, 0.9917),基于27张玻片。
临床怎么用
- 该模型可辅助革兰染色玻片自动分类,提升分析速度与可靠性,但需进一步临床验证。
局限性
- 外部验证数据集仅27张玻片,样本量较小。
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
UNLABELLED: This study introduces a new framework for the artificial intelligence-based characterization of Gram-stained whole-slide images (WSIs). As a test for the diagnosis of bloodstream infections, Gram stains provide critical early data to inform patient treatment in conjunction with data from rapid molecular tests. In this work, we developed a novel transformer-based model for Gram-stained WSI classification, which is more scalable to large data sets than previous convolutional neural network-based methods as it does not require patch-level manual annotations. We also introduce a large Gram stain data set from Dartmouth-Hitchcock Medical Center (Lebanon, New Hampshire, USA) to evaluate our model, exploring the classification of five major categories of Gram-stained WSIs: gram-positive cocci in clusters, gram-positive cocci in pairs/chains, gram-positive rods, gram-negative rods, and slides with no bacteria. Our model achieves a classification accuracy of 0.858 (95% CI: 0.805, 0.905) and an area under the receiver operating characteristic curve (AUC) of 0.952 (95% CI: 0.922, 0.976) using fivefold nested cross-validation on our 475-slide data set, demonstrating the potential of large-scale transformer models for Gram stain classification. Results were measured against the final clinical laboratory Gram stain report after growth of organism in culture. We further demonstrate the generalizability of our trained model by applying it without additional fine-tuning on a second 27-slide external data set from Stanford Health (Palo Alto, California, USA) where it achieves a binary classification accuracy of 0.926 (95% CI: 0.885, 0.960) and an AUC of 0.8651 (95% CI: 0.6337, 0.9917) while distinguishing gram-positive from gram-negative bacteria. IMPORTANCE: This study introduces a scalable transformer-based deep learning model for automating Gram-stained whole-slide image classification. It surpasses previous methods by eliminating the need for manual annotations and demonstrates high accuracy and generalizability across multiple data sets, enhancing the speed and reliability of Gram stain analysis.
引用
- McMahon J, Tomita N, Tatishev ES, et al. A novel framework for the automated characterization of Gram-stained blood culture slides using a large-scale vision transformer. J Clin Microbiol. 2025. PMID: 39992156. doi:10.1128/jcm.01514-24
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。