HERO: Histology Encoder for Robust Representation in Oncology

HERO：肿瘤学鲁棒表征组织学编码器

Abstract: 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.

摘要： 在大型病理图像语料库上训练的基础模型，目前已为计算病理学提供了强大且可迁移的表征。过去几年中，一系列此类模型相继发布，且每一个模型的训练切片数量都比前一个更多；在标准的分类和分割基准测试中，领先模型之间的差距已微乎其微。

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.

然而，在临床应用中，基础模型往往被应用于来自训练数据之外的医院、扫描仪和染色方案的图像。编码器通常会将这些采集因素与生物学信息一并嵌入，这可能会引入下游误差并阻碍其在临床的安全应用。因此，病理学基础模型在不牺牲表征质量的前提下，应具备对采集偏差的鲁棒性，但鲁棒性却很少成为模型对比的核心维度。

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.

在本报告中，我们介绍了 HERO（肿瘤学鲁棒表征组织学编码器）。这是一个 ViT-G/14 病理学基础模型，采用 DINO 和 iBOT 目标进行训练，并利用形态学平衡语料库（包含来自约 575,000 张临床全切片图像的 5 亿个图块）通过高分辨率 Gram 锚定技术进行了精炼。

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.

在评估的公共基准测试中，HERO 在应对中心、扫描仪和染色差异方面表现出比同类最先进基础模型更强的鲁棒性；在图块级分类、分割和基因表达预测任务中表现相当；在 39 项评估的切片级临床任务中平均排名第一；并且在等权重的框架级分析下，在六个基准测试框架中取得了最佳的平均排名。