Counterfactual Intervention in Attention Multiple Instance Learning For Digital Pathology

Imane Chraki, Pierre Marza, Stergios Christodoulidis, Maria Vakalopoulou

Keywords: Multiple Instance Learning, Attention, Interpretability, Whole Slide Images, Digital Pathology, Causal Intervention

Abstract:

Attention-based Multiple Instance Learning (MIL) has become a prominent framework
for analysing whole-slide images (WSI). These models have been shown to achieve good
performance on classification tasks, while also offering an inherent proxy for interpretability
through attention weights. In this work, we first question the validity of using attention for
the interpretability of MIL models. Subsequently, we propose Counterfactual Intervention
in Attention for MIL (CIA-MIL), a causal extension of attention-based MIL that explic-
itly measures and optimizes the contribution of attention to slide-level predictions. Across
four histopathology classification benchmarks (BRCA, NSCLC, LUAD, Camelyon16) and
two feature encoders (Resnet50, UNI), we investigate how the interpretability of atten-
tion relates to the representation space, and the downstream performance. We then show
that CIA-MIL achieves performance comparable to strong MIL baselines while providing a
more causally meaningful attention vector. Qualitative perturbation experiments show that
dropping the top-attended patches leads to a larger confidence degradation in CIA-MIL
compared to baseline ABMIL, highlighting the potential of causal supervision for reliable
and interpretable WSI-based prediction.

Primary Subject Area: Application: Histopathology

Secondary Subject Area: Causality

Registration Requirement: Yes

Visa & Travel: Yes

Read CFP & Author Instructions: Yes

Originality Policy: Yes

Single-blind & Not Under Review Elsewhere: Yes

LLM Policy: Yes

Submission Number: 310