Quantifying Explainers of Graph Neural Networks in Computational Pathology
Open accessThe DOI matches its Crossref record; 29 of the 29 references it cites were found in a registry or an index.
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. The code, data, and models can be accessed here1.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Veličković, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., & Bengio, Y. (2017) · arXiv · doi:10.48550/arxiv.1710.10903 · Cited by 12,107
Arrieta, A. B., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., García, S., Gil-López, S., Molina, D., Benjamins, R., et al. (2019) · arXiv · doi:10.48550/arxiv.1910.10045 · Cited by 11,321
Inductive Representation Learning on Large Graphs
Hamilton, W. L., Ying, R., & Leskovec, J. (2017) · arXiv · doi:10.48550/arxiv.1706.02216 · Cited by 10,639 · cited 1×
“We use GNNs [50, 13, 35, 24, 62, 66, 19], the conceptual analogous of 2D convolution for graph-structured data, to classify the CGs.”
MethodBarredo Arrieta, A., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., Garcia, S., Gil-Lopez, S., Molina, D., Benjamins, R., et al. (2020) · Information Fusion · doi:10.1016/j.inffus.2019.12.012 · Cited by 10,423
The graph neural network model
Scarselli, F., Gori, M., Tsoi, A. C., Hagenbuchner, M., & Monfardini, G. (2009) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2008.2005605 · Cited by 9,582 · cited 1×
“We use GNNs [50, 13, 35, 24, 62, 66, 19], the conceptual analogous of 2D convolution for graph-structured data, to classify the CGs.”
MethodHow Powerful are Graph Neural Networks?
Xu, K., Hu, W., Leskovec, J., & Jegelka, S. (2018) · arXiv · doi:10.48550/arxiv.1810.00826 · Cited by 6,078
Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
Simonyan, K., Vedaldi, A., & Zisserman, A. (2013) · arXiv · doi:10.48550/arxiv.1312.6034 · Cited by 5,370 · cited 1×
“Inspired by the explainability techniques (explainers) for DL model decisions on natural images [57, 68, 67, 6, 40, 52, 33, 72, 11, 32], several explainers have been implemented in digital pathology, such as feature attribution [10, 9, 23], concept attribution [21], and attention-based learning [38].”
MethodOn Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation
Bach, S., Binder, A., Montavon, G., Klauschen, F., Müller, K.-R., & Samek, W. (2015) · PLOS ONE · doi:10.1371/journal.pone.0130140 · Cited by 4,524 · cited 3×
“We use the proposed metrics to evaluate three types of graph-explainers, (1) graph pruning: GNNEXPLAINER [65, 29], (2) gradient-based saliency: GRAPHGRAD-CAM [52, 46], GRAPHGRAD-CAM++ [11], (3) layer-wise relevance propagation: GRAPHLRP [6, 40, 51], for explaining Cell-Graphs [22] in Breast Cancer Subtyping as shown i…”
Method
Cited by
Artificial intelligence for digital and computational pathology
Song, A. H., Jaume, G., Williamson, D. F. K., Lu, M. Y., Vaidya, A., Miller, T. R., & Mahmood, F. (2023) · Nature Reviews Bioengineering · doi:10.1038/s44222-023-00096-8 · Cited by 356
Self-citationGraph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future
Ahmedt-Aristizabal, D., Armin, M. A., Denman, S., Fookes, C., & Petersson, L. (2021) · Sensors · doi:10.3390/s21144758 · Cited by 272
Vision transformer-based weakly supervised histopathological image analysis of primary brain tumors
Li, Z., Cong, Y., Chen, X., Qi, J., Sun, J., Yan, T., Yang, H., Liu, J., Lu, E., Wang, L., et al. (2023) · iScience · doi:10.1016/j.isci.2022.105872 · Cited by 82
Weakly supervised joint whole-slide segmentation and classification in prostate cancer
Pati, P., Jaume, G., Ayadi, Z., Thandiackal, K., Bozorgtabar, B., Gabrani, M., & Goksel, O. (2023) · Medical Image Analysis · doi:10.1016/j.media.2023.102915 · Cited by 37
Self-citationIntegrating context for superior cancer prognosis
Jaume, G., Song, A. H., & Mahmood, F. (2022) · Nature Biomedical Engineering · doi:10.1038/s41551-022-00924-z · Cited by 8
Self-citation
Metadata
- Authors
- Jaume, G., Pati, P., Bozorgtabar, B., Foncubierta, A., Anniciello, A. M., Feroce, F., Rau, T., Thiran, J.-P., Gabrani, M., & Goksel, O.
- Venue
- 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2021-06
- Pages
- 8102-8112
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3110045238
- Cited by
- 73
- References
- 29
- FWCI
- 7.16
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.