Abstract
Multiple instance learning (MIL) is a promising approach for weakly supervised classification in pathology using whole slide images (WSIs). However, conventional MIL methods such as Attention-Based Deep Multiple Instance Learning (ABMIL) typically disregard spatial interactions among patches that are crucial to pathological diagnosis. Recent advancements, such as Transformer based MIL (TransMIL), have incorporated spatial context and inter-patch relationships. However, it remains unclear whether explicitly modeling patch relationships yields similar performance gains in ABMIL, which relies solely on Multi-Layer Perceptrons (MLPs). In contrast, TransMIL employs Transformer-based layers, introducing a fundamental architectural shift at the cost of substantially increased computational complexity. In this work, we enhance the ABMIL framework by integrating interaction-aware representations to address this question. Our proposed model, Global ABMIL (GABMIL), explicitly captures inter-instance dependencies while preserving computational efficiency. Experimental results on two publicly available datasets for tumor subtyping in breast and lung cancers demonstrate that GABMIL achieves up to a 7 percentage point improvement in AUPRC and a 5 percentage point increase in the Kappa score over ABMIL, with minimal or no additional computational overhead. These findings underscore the importance of incorporating patch interactions within MIL frameworks.
Abstract (translated)
多实例学习（Multiple Instance Learning，MIL）是使用全滑动图像（WSI）在病理学中进行弱监督分类的一种有前景的方法。然而，传统的MIL方法如基于注意力的深度多实例学习（ABMIL），通常会忽略对病理诊断至关重要的补丁间空间交互作用。最近的研究进展，例如基于Transformer的MIL (TransMIL)，已经整合了空间上下文和补丁间的相互关系。但是，目前还不清楚在仅依赖多层感知机（MLP）的ABMIL中显式建模这些补丁关系是否能带来类似的性能提升。相比之下，TransMIL采用基于Transformer的层结构，在计算复杂度显著增加的情况下引入了架构的根本变化。 在这项工作中，我们通过整合认知交互表示来增强ABMIL框架，以解答这个问题。我们的模型——全局ABMIL（GABMIL）明确地捕捉实例间的依赖关系，同时保持计算效率不变。在两个公开可用的数据集上进行的实验显示，这些数据集用于乳腺癌和肺癌肿瘤亚型分类，结果显示与ABMIL相比，GABMIL将AUPRC提高了最多7个百分点，并且Kappa分数提升了5个百分点，在几乎不增加或完全没有额外计算开销的情况下实现了这一目标。这些结果强调了在MIL框架中整合补丁交互的重要性。
URL
https://arxiv.org/abs/2504.17379
