# Cellular-Communication-Level Interpretability for Pathology Foundation Models via Graph Distillation on Microenvironment

arXiv: https://arxiv.org/abs/2609.26073 · HTML: https://mlsanity.com/paper/2609.26073/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 30 references that are in the map.
- First posted on arXiv 2 Aug 2026.

## Builds on (most cited first, 13 of 13)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [How Attentive are Graph Attention Networks?](https://mlsanity.com/paper/2105.14491/) (2021)
- [Virchow2: Scaling Self-Supervised Mixed Magnification Models in Pathology](https://mlsanity.com/paper/2408.00738/) (2024)
- [BRACS: A Dataset for BReAst Carcinoma Subtyping in H&E Histology Images](https://mlsanity.com/paper/2111.04740/) (2021)
- [Artificial Intelligence for Digital and Computational Pathology](https://mlsanity.com/paper/2401.06148/) (2023)
- [Phikon-v2, A large and public feature extractor for biomarker prediction](https://mlsanity.com/paper/2409.09173/) (2024)
- [A Survey on Computational Pathology Foundation Models: Datasets, Adaptation Strategies, and Evaluation Tasks](https://mlsanity.com/paper/2501.15724/) (2025)
- [Rethinking Transformer for Long Contextual Histopathology Whole Slide Image Analysis](https://mlsanity.com/paper/2410.14195/) (2024)
- [Histo-Genomic Knowledge Distillation For Cancer Prognosis From Histopathology Whole Slide Images](https://mlsanity.com/paper/2403.10040/) (2024)
- [NuLite -- Lightweight and Fast Model for Nuclei Instance Segmentation and Classification](https://mlsanity.com/paper/2408.01797/) (2024)
- [Slide-based Graph Collaborative Training for Histopathology Whole Slide Image Analysis](https://mlsanity.com/paper/2410.10260/) (2024)

## Abstract (arXiv)

Pathology foundation models (PFMs) provide strong tile-level representations but remain difficult to interpret at the cellular and microenvironmental scales that underpin clinical reasoning. We introduce Graph-Interpreter (G-Interp), a graph-distillation framework that equips a frozen PFM teacher with a cellular-communication-level "plug-in" interpreter, without modifying the teacher. For each tile, we segment cells as graph nodes and construct a microenvironment graph based on spatial adjacency. Graph neural network (GNN) students distil the PFM embedding, whilst learning attention-based message passing that yields node- and edge-level importances. We interpret these importances as cell-cell communication evidence, providing fine-grained explanations of how PFMs encode microenvironmental context. To stabilise distillation when graph abstraction is imperfect, we employ a lightweight auxiliary student to supply complementary visual cues and condition graph message passing, while keeping the primary interpretability signal graph-derived. We evaluate explanation faithfulness by mapping graph-selected evidence back to the image using instance masks and measuring teacher sensitivity under targeted vs non-target occlusions. Across multiple histopathology tasks, G-Interp produces highly scalable, microenvironment-aware explanations, while maintaining competitive predictive performance.