AI-based biomarkers can infer molecular features directly from hematoxylin & eosin (H&E) slides, yet most pathology foundation models (PFMs) rely on global patch-level embeddings and overlook cell-level morphology. We present a PFM model, JWTH (Joint-Weighted Token Hierarchy), which integrates large-scale self-supervised pretraining with cell-centric post-tuning and attention pooling to fuse local and global tokens. Across four tasks involving four biomarkers and eight cohorts, JWTH achieves up to 8.3% higher balanced accuracy and 1.2% average improvement over prior PFMs, advancing interpretable and robust AI-based biomarker detection in digital pathology.

翻译：基于人工智能的生物标志物可直接从苏木精-伊红（H&E）染色切片推断分子特征，然而多数病理学基础模型依赖于全局图像块级嵌入，忽视了细胞级形态学信息。我们提出一种病理学基础模型JWTH（联合加权令牌层次结构），该模型通过大规模自监督预训练结合以细胞为中心的微调及注意力池化机制，实现了局部与全局令牌的融合。在涵盖四种生物标志物、八个队列的四项任务中，JWTH相较于现有病理学基础模型取得了最高8.3%的平衡准确率提升及平均1.2%的改进，推动了数字病理学中可解释且稳健的AI生物标志物检测技术的发展。