CARE：面向全切片图像分析的分子引导自适应区域建模基础模型
CARE: A Molecular-Guided Foundation Model with Adaptive Region Modeling for Whole Slide Image Analysis
把 WSI 从固定 patch 网格改为由分子信号引导的自适应不规则区域建模，并用区域级特征聚合出切片级表示；做病理或大尺寸图像分析时，这种「自适应区域 + 跨模态对齐」的预训练范式可直接迁移到其他超高分辨率图像任务。
原文依据 a cross-modal alignment stage that leverages RNA and protein profiles to refine the construction and representation of adaptive regions
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论基础模型在计算病理学领域已取得成功，在多种组织病理学任务上展现出泛化能力。然而，现有模型依赖并非为组织形态量身设计的自然图像骨干网络，因而忽视了感兴趣区域（ROI）的异质性与非均匀组织方式。其结果是，这些模型无法捕捉超越图像块层面的连贯组织结构，限制了可解释性与临床相关性。为应对这些挑战，本文提出跨模态自适应区域编码器（CARE），这是一个将全切片图像（WSI）划分为若干形态学相关区域的病理基础模型。具体而言，CARE 采用两阶段预训练策略：（1）自监督单模态预训练阶段，在无需分割标注的情况下从 34,277 张全切片图像中学习形态学表征；（2）跨模态对齐阶段，利用 RNA 与蛋白质谱来精化自适应区域的构建与表征。这种分子引导使 CARE 能够识别具有生物学意义的模式，并生成不规则但连贯的组织区域，从中选取代表性区域作为 ROI。CARE 支持广泛的病理相关任务，既可使用 ROI 特征，也可使用聚合自适应区域得到的切片级特征。CARE 仅使用主流基础模型通常所用预训练数据的十分之一，便在 33 个下游基准上取得更优的平均性能，涵盖形态学分类、分子预测与生存分析，并在总体上优于其他基础模型基线。
英文原文摘要 1648 字符
Foundation models have achieved success in computational pathology, demonstrating generalization across histopathology tasks. However, existing models overlook the heterogeneous and non-uniform organization of regions of interest (ROIs) because they rely on natural image backbones not tailored for tissue morphology. Consequently, they fail to capture the coherent tissue architecture beyond patches, limiting interpretability and clinical relevance. To address these challenges, we present Cross-modal Adaptive Region Encoder (CARE), a foundation model for pathology that partitions WSIs into several morphologically relevant regions. Specifically, CARE employs a two-stage pretraining strategy: (1) a self-supervised unimodal pretraining stage that learns morphological representations from 34,277 whole-slide images (WSIs) without segmentation annotations, and (2) a cross-modal alignment stage that leverages RNA and protein profiles to refine the construction and representation of adaptive regions. This molecular guidance enables CARE to identify biologically relevant patterns and generate irregular yet coherent tissue regions, selecting the representative area as ROI. CARE supports a broad range of pathology-related tasks, using either the ROI feature or the slide-level feature obtained by aggregating adaptive regions. Based on only one-tenth of the pretraining data typically used by mainstream foundation models, CARE achieves superior average performance across 33 downstream benchmarks, including morphological classification, molecular prediction, and survival analysis, and outperforms other foundation model baselines overall.