Whole slide image (WSI) classification is a critical task in computational pathology. However, the gigapixel-size of such images remains a major challenge for the current state of deep-learning. Current methods rely on multiple-instance learning (MIL) models with frozen feature extractors. Given the the high number of instances in each image, MIL methods have long assumed independence and permutation-invariance of patches, disregarding the tissue structure and correlation between patches. Recent works started studying this correlation between instances but the computational workload of such a high number of tokens remained a limiting factor. In particular, relative position of patches remains unaddressed. We propose to apply a straightforward encoding module, namely a RoFormer layer , relying on memory-efficient exact self-attention and relative positional encoding. This module can perform full self-attention with relative position encoding on patches of large and arbitrary shaped WSIs, solving the need for correlation between instances and spatial modeling of tissues. We demonstrate that our method outperforms state-of-the-art MIL models on three commonly used public datasets (TCGA-NSCLC, BRACS and Camelyon16)) on weakly supervised classification tasks. Code is available at https://github.com/Sanofi-Public/DDS-RoFormerMIL

翻译：全切片图像分类是计算病理学中的关键任务。然而，此类图像的高像素尺寸仍是当前深度学习面临的主要挑战。现有方法依赖具有冻结特征提取器的多实例学习模型。鉴于每张图像中实例数量庞大，多实例学习方法长期以来假设斑块具有独立性和排列不变性，忽略了组织结构及斑块间的相关性。近期研究开始探索实例间的相关性，但海量令牌带来的计算负载仍是限制因素，尤其斑块的相对位置问题尚未解决。本文提出一种简洁的编码模块——即基于内存高效精确自注意力与相对位置编码的RoFormer层，该模块可对大型任意形状全切片图像的斑块进行带相对位置编码的完整自注意力计算，从而满足实例相关性建模与组织空间建模的需求。实验表明，在三个常用公开数据集（TCGA-NSCLC、BRACS和Camelyon16）的弱监督分类任务中，本方法优于现有最优的多实例学习模型。代码已开源：https://github.com/Sanofi-Public/DDS-RoFormerMIL