Additive MIL: Intrinsic Interpretability for Pathology. (arXiv:2206.01794v1 [cs.CV])

Multiple Instance Learning (MIL) has been widely applied in pathology towards
solving critical problems such as automating cancer diagnosis and grading,
predicting patient prognosis, and therapy response. Deploying these models in a
clinical setting requires careful inspection of these black boxes during
development and deployment to identify failures and maintain physician trust.
In this work, we propose a simple formulation of MIL models, which enables
interpretability while maintaining similar predictive performance. Our Additive
MIL models enable spatial credit assignment such …

arxiv cv interpretability mil