Foundation models (FMs) are transforming computational pathology by offering new ways to analyze histopathology images. However, FMs typically require weeks of training on large databases, making their creation a resource-intensive process. In this paper, we present a training for foundation models from whole slide images using supervised, end-to-end, multitask learning on slide-level labels. Notably, it is the first model to incorporate cancer subtyping, risk estimation, and genetic mutation prediction into one model. The presented model outperforms self-supervised models on seven benchmark tasks while the training only required 5% of the computational resources. The results not only show that supervised training can outperform self-supervision with less data, but also offer a solution to annotation problems, as patient-based labels are widely available through routine clinical processes. Furthermore, an attention module provides a layer of explainability across different tasks and serves as a tumor detector for unseen cancer types. To address the issue of closed-source datasets, the model was fully trained on openly available data. The code and model weights are made available under https://github.com/FraunhoferMEVIS/MedicalMultitaskModeling.

翻译：基础模型通过提供分析组织病理学图像的新方法，正在变革计算病理学领域。然而，基础模型通常需要在大型数据库上进行数周的训练，这使得其创建过程成为资源密集型任务。本文提出了一种利用切片级标签，通过有监督、端到端、多任务学习从全切片图像训练基础模型的方法。值得注意的是，这是首个将癌症亚型分型、风险估计和基因突变预测整合到一个模型中的方法。所提出的模型在七项基准任务上超越了自监督模型，而训练仅需消耗5%的计算资源。这些结果不仅表明有监督训练能够以更少的数据超越自监督学习，同时也为标注问题提供了解决方案，因为基于患者的标签可通过常规临床流程广泛获取。此外，一个注意力模块为不同任务提供了一层可解释性，并可作为未见癌症类型的肿瘤检测器。为了解决闭源数据集的问题，该模型完全在公开可用的数据上进行了训练。代码和模型权重已在 https://github.com/FraunhoferMEVIS/MedicalMultitaskModeling 发布。