EXAONE Path 2.0：具有端到端监督的病理学基础模型
EXAONE Path 2.0: Pathology Foundation Model with End-to-End Supervision
AI总结：
针对数字病理学中自监督学习方法数据效率低且易忽略复杂生物标志物特征的问题，提出在切片级监督下学习图像块表征的病理学基础模型EXAONE Path 2.0，仅用37k张WSIs即在10项预测任务中达到最优平均性能。
摘要：
在数字病理学中，全切片图像（WSIs）因其千兆像素规模而难以处理，因此大多数方法通过自监督学习（SSL）训练图像块编码器，然后通过多实例学习（MIL）或切片编码器聚合图像块级嵌入以用于下游任务。然而，图像块级SSL可能会忽略对生物标志物预测至关重要的复杂领域特定特征，例如突变状态和分子特征，因为SSL方法仅依赖于针对小图像块区域上自然图像域选择的基本数据增强。此外，SSL方法在数据效率上仍不及全监督方法，需要大量的计算资源和数据集才能实现有竞争力的性能。为了解决这些局限性，我们提出了EXAONE Path 2.0，这是一种在直接切片级监督下学习图像块级表征的病理学基础模型。仅使用37k张WSIs进行训练，EXAONE Path 2.0在10项生物标志物预测任务中取得了最先进的平均性能，展现出卓越的数据效率。
英文摘要：
In digital pathology, whole-slide images (WSIs) are often difficult to handle due to their gigapixel scale, so most approaches train patch encoders via self-supervised learning (SSL) and then aggregate the patch-level embeddings via multiple instance learning (MIL) or slide encoders for downstream tasks. However, patch-level SSL may overlook complex domain-specific features that are essential for biomarker prediction, such as mutation status and molecular characteristics, as SSL methods rely only on basic augmentations selected for natural image domains on small patch-level area. Moreover, SSL methods remain less data efficient than fully supervised approaches, requiring extensive computational resources and datasets to achieve competitive performance. To address these limitations, we present EXAONE Path 2.0, a pathology foundation model that learns patch-level representations under direct slide-level supervision. Using only 37k WSIs for training, EXAONE Path 2.0 achieves state-of-the-art average performance across 10 biomarker prediction tasks, demonstrating remarkable data efficiency.
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。
