HERO：用于肿瘤学稳健表征的组织学编码器
HERO: Histology Encoder for Robust Representation in Oncology
浏览论文内容
中文总结 AI 辅助
HERO是一个基于ViT-G/14的病理学基础模型，通过DINO和iBOT训练及Gram锚定精炼，在5亿图块上实现稳健表征，在采集偏移下稳健性最强，平均排名第一。
中文摘要 AI 辅助
基于大规模病理图像语料库训练的基础模型，如今为计算病理学提供了强大且可迁移的表征。在过去几年中，一系列此类模型相继发布，每个模型训练的切片数量都比上一个更多；在标准分类和分割基准上，领先模型之间的差距已很小。然而，在临床应用中，基础模型被应用于来自其训练数据之外的医院、扫描仪和染色协议的图像。编码器通常将这些采集因素与生物信息一同嵌入，这可能引入下游错误并阻碍安全的临床采用。因此，病理学基础模型应能对采集偏移保持稳健，同时不牺牲表征质量，但稳健性很少成为模型比较的维度。在本报告中，我们介绍了HERO（用于肿瘤学稳健表征的组织学编码器），这是一个ViT-G/14病理学基础模型，使用DINO和iBOT目标进行训练，并通过高分辨率Gram锚定在形态学平衡的语料库上精炼，该语料库包含来自约575,000张临床全切片图像的5亿个图块。在评估的公共基准中，HERO在中心、扫描仪和染色变化方面表现出最强的稳健性，与所比较的最先进基础模型相比，在切片级分类、分割和基因表达预测上表现相当，在39项评估的切片级临床任务中平均排名第一，并且在等权重框架级分析中，在六个基准框架中具有最佳平均排名。
英文摘要
Foundation models trained on large pathology image corpora now provide strong, transferable representations for computational pathology. Over the past few years a series of such models has been released, each trained on more slides than the last; on standard classification and segmentation benchmarks, the leading models are now separated by small margins. In clinical use, however, the foundation model is applied to images from hospitals, scanners, and staining protocols outside its training data. Encoders generally embed these acquisition factors alongside biological information, which may introduce downstream errors and hinder safe clinical adoption. A pathology foundation model should therefore be robust to acquisition shift without giving up representation quality, yet robustness is seldom the axis along which models are compared. In this report, we introduce HERO (Histology Encoder for Robust Representation in Oncology), a ViT-G/14 pathology foundation model trained with the DINO and iBOT objectives and refined with high-resolution Gram anchoring on a morphology-balanced corpus of 500 million tiles from approximately 575,000 clinical whole-slide images. Across the evaluated public benchmarks, HERO shows the strongest robustness to center, scanner, and stain variation among the compared state-of-the-art foundation models, performs comparably on tile-level classification, segmentation, and gene-expression prediction, ranks first on average across 39 evaluated slide-level clinical tasks, and, under an equal-weighted framework-level analysis, has the best average rank across the six benchmark frameworks.
发表机构
- Caris Life Sciences（卡里斯生命科学公司）
机构由 AI 辅助整理，请以论文原文为准。
