# Quantifying Explainers of Graph Neural Networks in Computational Pathology

arXiv: https://arxiv.org/abs/2011.12646 · HTML: https://mlsanity.com/paper/2011.12646/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Nov 2020.

## Built on by (most cited first, 30 of 35)

- [BRACS: A Dataset for BReAst Carcinoma Subtyping in H&E Histology Images](https://mlsanity.com/paper/2111.04740/) (2021)
- [Whole Slide Images are 2D Point Clouds: Context-Aware Survival Prediction using Patch-based Graph Convolutional Networks](https://mlsanity.com/paper/2107.13048/) (2021)
- [Artificial Intelligence for Digital and Computational Pathology](https://mlsanity.com/paper/2401.06148/) (2023)
- [Lizard: A Large-Scale Dataset for Colonic Nuclear Instance Segmentation and Classification](https://mlsanity.com/paper/2108.11195/) (2021)
- [Trustworthy Graph Neural Networks: Aspects, Methods and Trends](https://mlsanity.com/paper/2205.07424/) (2022)
- [Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future](https://mlsanity.com/paper/2105.13137/) (2021)
- [Hierarchical Graph Representations in Digital Pathology](https://mlsanity.com/paper/2102.11057/) (2021)
- [CoNIC: Colon Nuclei Identification and Counting Challenge 2022](https://mlsanity.com/paper/2111.14485/) (2021)
- [A General-Purpose Self-Supervised Model for Computational Pathology](https://mlsanity.com/paper/2308.15474/) (2023)
- [A Survey on Graph-Based Deep Learning for Computational Histopathology](https://mlsanity.com/paper/2107.00272/) (2021)
- [A Survey on Explainability of Graph Neural Networks](https://mlsanity.com/paper/2306.01958/) (2023)
- [SI-MIL: Taming Deep MIL for Self-Interpretability in Gigapixel Histopathology](https://mlsanity.com/paper/2312.15010/) (2023)
- [Interpretable Prototype-based Graph Information Bottleneck](https://mlsanity.com/paper/2310.19906/) (2023)
- [Learning Whole-Slide Segmentation from Inexact and Incomplete Labels using Tissue Graphs](https://mlsanity.com/paper/2103.03129/) (2021)
- [HistoCartography: A Toolkit for Graph Analytics in Digital Pathology](https://mlsanity.com/paper/2107.10073/) (2021)
- [A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protection](https://mlsanity.com/paper/2205.10014/) (2022)
- [Generative Modelling of Structurally Constrained Graphs](https://mlsanity.com/paper/2406.17341/) (2024)
- [Structure Embedded Nucleus Classification for Histopathology Images](https://mlsanity.com/paper/2302.11416/) (2023)
- [Towards Explainable Motion Prediction using Heterogeneous Graph Representations](https://mlsanity.com/paper/2212.03806/) (2022)
- [Weakly Supervised Joint Whole-Slide Segmentation and Classification in Prostate Cancer](https://mlsanity.com/paper/2301.02933/) (2023)
- [GECKO: Gigapixel Vision-Concept Contrastive Pretraining in Histopathology](https://mlsanity.com/paper/2504.01009/) (2025)
- [Towards the Explanation of Graph Neural Networks in Digital Pathology with Information Flows](https://mlsanity.com/paper/2112.09895/) (2021)
- [Unsupervised Mutual Transformer Learning for Multi-Gigapixel Whole Slide Image Classification](https://mlsanity.com/paper/2305.02032/) (2023)
- [Tertiary Lymphoid Structures Generation through Graph-based Diffusion](https://mlsanity.com/paper/2310.06661/) (2023)
- [GNNFormer: A Graph-based Framework for Cytopathology Report Generation](https://mlsanity.com/paper/2303.09956/) (2023)
- [KS-GNNExplainer: Global Model Interpretation Through Instance Explanations On Histopathology images](https://mlsanity.com/paper/2304.08240/) (2023)
- [A Cognitive Explainer for Fetal ultrasound images classifier Based on Medical Concepts](https://mlsanity.com/paper/2201.07798/) (2022)
- [Scale dependant layer for self-supervised nuclei encoding](https://mlsanity.com/paper/2207.10950/) (2022)
- [Explainable and Position-Aware Learning in Digital Pathology](https://mlsanity.com/paper/2306.08198/) (2023)
- [Asymmetric Co-Training with Explainable Cell Graph Ensembling for Histopathological Image Classification](https://mlsanity.com/paper/2308.12737/) (2023)

## Abstract (arXiv)

Explainability of deep learning methods is imperative to facilitate their clinical adoption in digital pathology. However, popular deep learning methods and explainability techniques (explainers) based on pixel-wise processing disregard biological entities' notion, thus complicating comprehension by pathologists. In this work, we address this by adopting biological entity-based graph processing and graph explainers enabling explanations accessible to pathologists. In this context, a major challenge becomes to discern meaningful explainers, particularly in a standardized and quantifiable fashion. To this end, we propose herein a set of novel quantitative metrics based on statistics of class separability using pathologically measurable concepts to characterize graph explainers. We employ the proposed metrics to evaluate three types of graph explainers, namely the layer-wise relevance propagation, gradient-based saliency, and graph pruning approaches, to explain Cell-Graph representations for Breast Cancer Subtyping. The proposed metrics are also applicable in other domains by using domain-specific intuitive concepts. We validate the qualitative and quantitative findings on the BRACS dataset, a large cohort of breast cancer RoIs, by expert pathologists.