基础模型变压器的现实世界的基准测试和验证,用于从基因病理学上对子宫内膜癌的亚型鉴定
Vincent M Wagner1, Casey M Cosgrove2, Stephanie J Chen3
1University of Iowa, Department of Obstetrics and Gynecology, Division of Gynecologic Oncology, Iowa City, IA.
medRxiv : the preprint server for health sciences
|November 24, 2025
概括
开源基础模型从整个幻灯片图像 (WSIs) 中准确地分类子宫内膜癌 (EC) 的分子亚型. 这些模型在现实世界的验证中表现强,在精确瘤学中表现优于传统的CNN.
科学领域:
- 数字病理学数字病理学
- 计算瘤学是一种计算瘤学.
- 医学中的人工智能
背景情况:
- 子宫内膜癌 (EC) 的分子亚型是指导治疗的关键.
- 使用人工智能 (AI) 来精确地从整个幻灯片图像 (WSI) 中进行子类型化可以提高诊断效率.
- 在现实世界临床环境中评估人工智能模型的通用性至关重要.
研究的目的:
- 评估基于注意力的多个实例学习 (MIL) 的开源组织病理学基础模型的准确性,以从WSIs分类EC分子亚型.
- 在一个独立的,现实世界的队列中评估这些模型的性能维护.
主要方法:
- 使用了一个发现队列 (815名患者) 和一个独立的外部队列 (720名患者).
- 四个基础编码器和四个卷积神经网络 (CNN) 使用STAMP管道与TransMIL和CLAM MIL策略进行了基准测试.
- 模型通过交叉验证进行训练,并在外部队列上进行测试,以接收器运行特征曲线 (AUC) 下的宏观区域作为主要指标.
主要成果:
- 基础模型在交叉验证中显著优于CNN (宏观AUC0.799-0.860与0.715-0.829).
- 在交叉验证中,表现最好的基础模型 (Virchow2与CLAM) 在交叉验证中实现了0.860的宏观AUC.
- 在外部验证中,与CNN相比,基础模型表现更好 (宏观AUC为0.667-0.780),UNI2和CLAM实现了最高的外部宏观AUC (0.780).
结论:
- 与MIL相结合的开源基础模型可以准确地和一般地从WSIs直接对EC分子亚型进行分类.
- 这些人工智能模型在现实世界的验证中超越了传统的CNN,为可扩展和具有成本效益的精密瘤学工具提供了潜力.
- 这些发现支持使用这些模型来指导治疗决策和在EC中分类分子测试.
相关概念视频
Mouse Models of Cancer Study
Mice have long served as models for studying human biology and pathology because of their phylogenetic and physiological similarity with humans. They are also easy to maintain and breed in the laboratory, and hence, many inbred strains are now available for research. Studies on mice have contributed immeasurably to our understanding of cancer biology.
The development of transgenic, knockout, and knock-in mice has led to an exponential increase in their use as model organisms in research,...
The development of transgenic, knockout, and knock-in mice has led to an exponential increase in their use as model organisms in research,...
Mouse Models of Cancer Study
Mice have long served as models for studying human biology and pathology because of their phylogenetic and physiological similarity with humans. They are also easy to maintain and breed in the laboratory, and hence, many inbred strains are now available for research. Studies on mice have contributed immeasurably to our understanding of cancer biology.
The development of transgenic, knockout, and knock-in mice has led to an exponential increase in their use as model organisms in research,...
The development of transgenic, knockout, and knock-in mice has led to an exponential increase in their use as model organisms in research,...


