DaX: 跨尺度的通用病理学表示学习
DaX: Learning General Pathology Representations Across Scales
AI总结：
提出病理视觉基础模型DaX，通过改进DINOv3自监督学习，结合连续放大训练、跨尺度组织视图等设计，在44个公开数据集的161项临床任务上取得最佳平均性能。
摘要：
计算病理学需要能够跨不同临床终点迁移且对放大倍数、染色、扫描仪类型、切片制备和输入分辨率变化保持鲁棒的视觉表示。我们提出DaX，一个病理视觉基础模型，它将DINOv3风格的自监督学习适应到全切片组织病理学。DaX从自然图像DINOv3权重初始化，并融合了连续放大训练、跨尺度组织视图、方向无关和采集鲁棒的数据增强、多输入尺寸训练以及Gram锚定的密集一致性。这些设计旨在连接局部细胞形态与全局组织结构，同时稳定跨输入尺度的密集token级表示。我们进一步构建了一个WSI级基准，包含来自44个公共数据集的161项临床有意义任务，涵盖28,182名患者和34,394张切片，跨越四个临床领域和九个任务类别。所有模型在固定的患者级交叉验证协议下进行评估，并采用折叠级统计排名，从而实现可重复的比较，对分割依赖的变异性不敏感。在该基准上，DaX在任务中取得了最高的平均性能，并持续获得强大的任务级排名分数，其增益涵盖诊断病理学、生物标志物和分子谱分析、组织/标本背景以及风险、反应和预后。这些结果支持DaX作为计算病理学的可迁移视觉编码器，并为未来的病理基础模型提供了标准化的评估框架。项目页面：此https URL。
英文摘要：
Computational pathology requires visual representations that transfer across diverse clinical endpoints and remain robust to variation in magnification, staining, scanner type, slide preparation, and input resolution. We present DaX, a pathology vision foundation model that adapts DINOv3-style self-supervised learning to whole-slide histopathology. DaX is initialized from natural-image DINOv3 weights and incorporates continuous magnification training, cross-scale tissue views, orientation-agnostic and acquisition-robust augmentation, multi-input-size training, and Gram-anchored dense consistency. These designs aim to connect local cellular morphology with global tissue architecture while stabilizing dense token-level representations across input scales. We further construct a WSI-level benchmark comprising 161 clinically meaningful tasks from 44 public datasets, covering 28,182 patients and 34,394 slides across four clinical domains and nine task categories. All models are evaluated under a fixed patient-level cross-validation protocol with fold-level statistical ranking, enabling reproducible comparisons that are less sensitive to split-dependent variation. Across this benchmark, DaX achieves the highest mean performance across tasks and consistently strong task-level ranking scores, with gains spanning diagnostic pathology, biomarker and molecular profiling, tissue/specimen context, and risk, response, and prognosis. These results support DaX as a transferable visual encoder for computational pathology and provide a standardized evaluation framework for future pathology foundation models. Project page: https://alibaba-damo-academy.github.io/DaX/benchboard/.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
