Quantifying Explainers of Graph Neural Networks in Computational Pathology

• URL: http://arxiv.org/abs/2011.12646v2
• Date: Fri, 14 May 2021 16:44:46 GMT
• Title: Quantifying Explainers of Graph Neural Networks in Computational Pathology
• Authors: Guillaume Jaume and Pushpak Pati and Behzad Bozorgtabar and Antonio Foncubierta-Rodr\'iguez and Florinda Feroce and Anna Maria Anniciello and Tilman Rau and Jean-Philippe Thiran and Maria Gabrani and Orcun Goksel
• Abstract summary: We propose a set of novel quantitative metrics based on statistics of class separability 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. We validate the qualitative and quantitative findings on the BRACS dataset, a large cohort of breast cancer RoIs, by expert pathologists.
• Score: 13.526389642048947
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Graph Relation Distillation for Efficient Biomedical Instance Segmentation [80.51124447333493]
  We propose a graph relation distillation approach for efficient biomedical instance segmentation. We introduce two graph distillation schemes deployed at both the intra-image level and the inter-image level. Experimental results on a number of biomedical datasets validate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2024-01-12T04:41:23Z)
• Tertiary Lymphoid Structures Generation through Graph-based Diffusion [54.37503714313661]
  In this work, we leverage state-of-the-art graph-based diffusion models to generate biologically meaningful cell-graphs. We show that the adopted graph diffusion model is able to accurately learn the distribution of cells in terms of their tertiary lymphoid structures (TLS) content.
  arXiv  Detail & Related papers  (2023-10-10T14:37:17Z)
• KS-GNNExplainer: Global Model Interpretation Through Instance Explanations On Histopathology images [0.0]
  We develop KS-GNNExplainer, the first instance-level graph neural network explainer. Our experiments on various datasets, and based on both quantitative and qualitative measures, demonstrate that the proposed explainer is capable of being a global pattern extractor.
  arXiv  Detail & Related papers  (2023-04-14T16:48:41Z)
• State of the Art and Potentialities of Graph-level Learning [54.68482109186052]
  Graph-level learning has been applied to many tasks including comparison, regression, classification, and more. Traditional approaches to learning a set of graphs rely on hand-crafted features, such as substructures. Deep learning has helped graph-level learning adapt to the growing scale of graphs by extracting features automatically and encoding graphs into low-dimensional representations.
  arXiv  Detail & Related papers  (2023-01-14T09:15:49Z)
• Automated Coronary Arteries Labeling Via Geometric Deep Learning [13.515293812745343]
  We propose an intuitive graph representation method, well suited to use with 3D coordinate data obtained from angiography scans. We subsequently seek to analyze subject-specific graphs using geometric deep learning. The proposed models leverage expert annotated labels from 141 patients to learn representations of each coronary segment, while capturing the effects of anatomical variability within the training data.
  arXiv  Detail & Related papers  (2022-12-01T09:31:08Z)
• Graph-in-Graph (GiG): Learning interpretable latent graphs in non-Euclidean domain for biological and healthcare applications [52.65389473899139]
  Graphs are a powerful tool for representing and analyzing unstructured, non-Euclidean data ubiquitous in the healthcare domain. Recent works have shown that considering relationships between input data samples have a positive regularizing effect for the downstream task. We propose Graph-in-Graph (GiG), a neural network architecture for protein classification and brain imaging applications.
  arXiv  Detail & Related papers  (2022-04-01T10:01:37Z)
• Discriminative Attribution from Counterfactuals [64.94009515033984]
  We present a method for neural network interpretability by combining feature attribution with counterfactual explanations. We show that this method can be used to quantitatively evaluate the performance of feature attribution methods in an objective manner.
  arXiv  Detail & Related papers  (2021-09-28T00:53:34Z)
• A Survey on Graph-Based Deep Learning for Computational Histopathology [36.58189530598098]
  We have witnessed a rapid expansion of the use of machine learning and deep learning for the analysis of digital pathology and biopsy image patches. Traditional learning over patch-wise features using convolutional neural networks limits the model when attempting to capture global contextual information. We provide a conceptual grounding of graph-based deep learning and discuss its current success for tumor localization and classification, tumor invasion and staging, image retrieval, and survival prediction.
  arXiv  Detail & Related papers  (2021-07-01T07:50:35Z)
• Integrating Logical Rules Into Neural Multi-Hop Reasoning for Drug Repurposing [23.783111050856245]
  We propose a novel method that combines these rules with a neural multi-hop reasoning approach that uses reinforcement learning. We apply our method to the biomedical knowledge graph Hetionet and show that our approach outperforms several baseline methods.
  arXiv  Detail & Related papers  (2020-07-10T10:32:08Z)
• Towards Explainable Graph Representations in Digital Pathology [9.369422379741982]
  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 digital pathology.
  arXiv  Detail & Related papers  (2020-07-01T08:05:26Z)
• Weakly supervised multiple instance learning histopathological tumor segmentation [51.085268272912415]
  We propose a weakly supervised framework for whole slide imaging segmentation. We exploit a multiple instance learning scheme for training models. The proposed framework has been evaluated on multi-locations and multi-centric public data from The Cancer Genome Atlas and the PatchCamelyon dataset.
  arXiv  Detail & Related papers  (2020-04-10T13:12:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.