Quantifying Explainers of Graph Neural Networks in Computational Pathology
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.
Code (3)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
KS-GNNExplainer: Global Model Interpretation Through Instance Explanations On Histopathology images
Instance-level graph neural network explainers have proven beneficial for explaining such networks on histopathology images. However, there has been few methods that provide model explanations, which are common patterns …
Graph GenerationGraph Neural NetworkTowards the Explanation of Graph Neural Networks in Digital Pathology with Information Flows
As Graph Neural Networks (GNNs) are widely adopted in digital pathology, there is increasing attention to developing explanation models (explainers) of GNNs for improved transparency in clinical decisions. Existing expla…
PredictionEfficient Explanations from Empirical Explainers
Amid a discussion about Green AI in which we see explainability neglected, we explore the possibility to efficiently approximate computationally expensive explainers. To this end, we propose feature attribution modelling…
Graph Neural Network Causal Explanation via Neural Causal Models
Graph neural network (GNN) explainers identify the important subgraph that ensures the prediction for a given graph. Until now, almost all GNN explainers are based on association, which is prone to spurious correlations.…
Causal InferenceGraph Neural NetworkGraph Neural Network Explanations are Fragile
Explainable Graph Neural Network (GNN) has emerged recently to foster the trust of using GNNs. Existing GNN explainers are developed from various perspectives to enhance the explanation performance. We take the first ste…
Adversarial AttackGraph Neural Network