arXiv 2512.213312025-12-25cs.CV

TICON：用于病理学表示学习的滑片级上下文化器

TICON: A Slide-Level Tile Contextualizer for Histopathology Representation Learning

Stony Brook University（石溪大学）；MICS, CentraleSupélec, Université Paris-Saclay（MICS、CentraleSupélec、巴黎-萨克雷大学）；UNC Charlotte（北卡罗来纳大学夏洛特分校）；Argonne National Laboratory（阿贡国家实验室）；University of Chicago（芝加哥大学）；Archimedes/Athena RC；Independent Researcher（独立研究者）

Varun Belagali, Saarthak Kapse, Pierre Marza, Srijan Das, Zilinghan Li, Sofiène Boutaj, Pushpak Pati, Srikar Yellapragada, Tarak Nath Nandi, Ravi K Madduri, Joe… 展开作者

Varun Belagali, Saarthak Kapse, Pierre Marza, Srijan Das, Zilinghan Li, Sofiène Boutaj, Pushpak Pati, Srikar Yellapragada, Tarak Nath Nandi, Ravi K Madduri, Joel Saltz, Prateek Prasanna, Stergios Christodoulidis, Maria Vakalopoulou, Dimitris Samaras

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

TICON通过统一的Transformer模型提升病理学滑片和全滑片表示学习的性能，实现多个基准的新状态-of-the-art结果。

摘要：

在大规模全滑片图像（WSI）中，小滑片的解释往往需要更大的图像上下文。我们介绍了TICON，一种基于Transformer的滑片表示上下文化器，能够为计算病理学中的任何应用生成丰富、上下文化的嵌入。标准的基于滑片编码器的流程，提取脱离上下文的滑片嵌入，无法建模对局部和全局任务至关重要的丰富滑片级信息。此外，不同的滑片编码器在不同的下游任务中表现优异。因此，需要一个统一的模型来上下文化来自“任何”滑片级基础模型的嵌入。TICON通过一个共享的编码器来解决这一需求，该编码器通过掩码建模目标进行预训练，同时统一和上下文化来自不同滑片级病理基础模型的表示。我们的实验表明，TICON上下文化的嵌入在许多不同任务中显著提高了性能，建立了在滑片级基准（如HEST-Bench、THUNDER、CATCH）和滑片级基准（如Patho-Bench）上的新状态-of-the-art结果。最后，我们预训练了一个聚合器在TICON上，形成一个滑片级基础模型，仅使用11K WSIs，优于预训练使用多达350K WSIs的现有滑片级基础模型。

英文摘要：

The interpretation of small tiles in large whole slide images (WSI) often needs a larger image context. We introduce TICON, a transformer-based tile representation contextualizer that produces rich, contextualized embeddings for ''any'' application in computational pathology. Standard tile encoder-based pipelines, which extract embeddings of tiles stripped from their context, fail to model the rich slide-level information essential for both local and global tasks. Furthermore, different tile-encoders excel at different downstream tasks. Therefore, a unified model is needed to contextualize embeddings derived from ''any'' tile-level foundation model. TICON addresses this need with a single, shared encoder, pretrained using a masked modeling objective to simultaneously unify and contextualize representations from diverse tile-level pathology foundation models. Our experiments demonstrate that TICON-contextualized embeddings significantly improve performance across many different tasks, establishing new state-of-the-art results on tile-level benchmarks (i.e., HEST-Bench, THUNDER, CATCH) and slide-level benchmarks (i.e., Patho-Bench). Finally, we pretrain an aggregator on TICON to form a slide-level foundation model, using only 11K WSIs, outperforming SoTA slide-level foundation models pretrained with up to 350K WSIs.

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。