mlsanityData to 7 Oct 2026

Explainable Artificial Intelligence (XAI) in Computational Pathology: Definitions, Taxonomy, and Recommendations

arXiv 2608.28820 ↗First posted 28 Aug 2026cs.AI cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Computational pathology (CompPath) is transforming medicine by leveraging artificial intelligence (AI) algorithms to support diagnosis, prognosis, and treatment prediction from gigapixel whole-slide images. Clinical adoption is progressing, but is constrained by concerns about safety, accountability, and regulatory oversight in high-stakes clinical environments. Explainable AI (XAI) systems hold promise for building trust and enabling verification, yet the literature remains fragmented due to inconsistent terminology, overlapping methodological families, ad hoc validation, and current reviews. This review aims to formalize XAI methods in CompPath through the: i) introduction of a pathology-centric vocabulary comprising seven core terms; ii) development of a taxonomy across methodological families and three orthogonal axes (stage, type, scope); and iii) establishment of a task-driven framework that maps five clinical questions to recommended methods, method evaluation, and deployment context. Five key gaps between current XAI capabilities and clinical deployment are identified, and actionable steps are proposed to advance XAI for CompPath.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 86 of its 222 references that are in the map. First posted on arXiv 28 Aug 2026.

Builds on

86 of 222 references.

References · 86

  1. 2017Attention Is All You Needcited by 59,932
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  3. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  4. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  5. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  6. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  7. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  8. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,543
  9. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  10. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,400
  11. 2018Datasheets for Datasetscited by 1,371
  12. 2023Sparse Autoencoders Find Highly Interpretable Features in Language Modelscited by 1,359
38 more
  1. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,309
  2. 2018Sanity Checks for Saliency Mapscited by 1,149
  3. 2017SmoothGrad: removing noise by adding noisecited by 1,097
  4. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,086
  5. 2018Attention-based Deep Multiple Instance Learningcited by 1,077
  6. 2018Model Cards for Model Reportingcited by 1,068
  7. 2020Concept Bottleneck Modelscited by 1,022
  8. 2018A Survey Of Methods For Explaining Black Box Modelscited by 970
  9. 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 936
  10. 2019Attention is not Explanationcited by 916
  11. 2014Show and Tell: A Neural Image Caption Generatorcited by 877
  12. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 825
  13. 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 813
  14. 2020Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Imagescited by 738
  15. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 731
  16. 2019Attention is not not Explanationcited by 629
  17. 2020Transformer Interpretability Beyond Attention Visualizationcited by 620
  18. 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 611
  19. 2021TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classificationcited by 549
  20. 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
  21. 2018A Benchmark for Interpretability Methods in Deep Neural Networkscited by 467
  22. 2015Evaluating the visualization of what a Deep Neural Network has learnedcited by 416
  23. 2018HoVer-Net: Simultaneous Segmentation and Classification of Nuclei in Multi-Tissue Histology Imagescited by 387
  24. 2022Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learningcited by 357
  25. 2015Understanding Neural Networks Through Deep Visualizationcited by 332
  26. 2019Interpretable machine learning: definitions, methods, and applicationscited by 303
  27. 2022DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classificationcited by 254
  28. 2020Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Surveycited by 252
  29. 2017Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictionscited by 234
  30. 2023Learning to Exploit Temporal Structure for Biomedical Vision-Language Processingcited by 210
  31. 2018To Trust Or Not To Trust A Classifiercited by 205
  32. 2019Full-Gradient Representation for Neural Network Visualizationcited by 189
  33. 2026Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnetcited by 175
  34. 2022Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyondcited by 171
  35. 2021Explainable artificial intelligence (XAI) in deep learning-based medical image analysiscited by 147
  36. 2019Principles alone cannot guarantee ethical AIcited by 134
  37. 2021Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyondcited by 116
  38. 2020The role of explainability in creating trustworthy artificial intelligence for health care: a comprehensive survey of the terminology, design choices, and evaluation strategiescited by 91

50 most cited of 86 All 86 (JSON)

Built on by

Not cited yet.