Towards Explainable Graph Representations in Digital Pathology
This work addresses the need for explainable AI in digital pathology to facilitate clinical adoption, though it is incremental as it builds on existing graph techniques.
The paper tackles the problem of explainability in digital pathology by introducing a post-hoc explainer that generates compact per-instance explanations for graph-based representations, focusing on cells and cellular interactions in breast cancer subtyping, with qualitative and quantitative analyses showing its efficacy.
Explainability of machine learning (ML) techniques in digital pathology (DP) is of great significance to facilitate their wide adoption in clinics. Recently, graph techniques encoding relevant biological entities have been employed to represent and assess DP images. Such paradigm shift from pixel-wise to entity-wise analysis provides more control over concept representation. In this paper, we introduce a post-hoc explainer to derive compact per-instance explanations emphasizing diagnostically important entities in the graph. Although we focus our analyses to cells and cellular interactions in breast cancer subtyping, the proposed explainer is generic enough to be extended to other topological representations in DP. Qualitative and quantitative analyses demonstrate the efficacy of the explainer in generating comprehensive and compact explanations.