mlsanityData to 7 Oct 2026

XProtoNet: Diagnosis in Chest Radiography with Global and Local Explanations

arXiv 2103.10663 ↗First posted 19 Mar 2021cs.CVcited by 72

Not on the map. Why?

Abstract (arXiv)

Automated diagnosis using deep neural networks in chest radiography can help radiologists detect life-threatening diseases. However, existing methods only provide predictions without accurate explanations, undermining the trustworthiness of the diagnostic methods. Here, we present XProtoNet, a globally and locally interpretable diagnosis framework for chest radiography. XProtoNet learns representative patterns of each disease from X-ray images, which are prototypes, and makes a diagnosis on a given X-ray image based on the patterns. It predicts the area where a sign of the disease is likely to appear and compares the features in the predicted area with the prototypes. It can provide a global explanation, the prototype, and a local explanation, how the prototype contributes to the prediction of a single image. Despite the constraint for interpretability, XProtoNet achieves state-of-the-art classification performance on the public NIH chest X-ray dataset.

Key facts. Cited by 72 papers in the map (data through 7 Oct 2026). Builds on 25 of its 35 references that are in the map. First posted on arXiv 19 Mar 2021.

Builds on

25 of 35 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Densely Connected Convolutional Networkscited by 6,691
  3. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  4. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  5. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  6. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  7. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  8. 2019CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparisoncited by 1,410
  9. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,309
  10. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,201
  11. 2018Sanity Checks for Saliency Mapscited by 1,149
  12. 2017SmoothGrad: removing noise by adding noisecited by 1,097
13 more
  1. 2017ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseasescited by 969
  2. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 731
  3. 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
  4. 2017CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learningcited by 459
  5. 2020Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentationcited by 299
  6. 2017Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictionscited by 234
  7. 2019When Explanations Lie: Why Many Modified BP Attributions Failcited by 92
  8. 2017Learning how to explain neural networks: PatternNet and PatternAttributioncited by 84
  9. 2019Interpretable Image Recognition with Hierarchical Prototypescited by 64
  10. 2017Thoracic Disease Identification and Localization with Limited Supervisioncited by 55
  11. 2020Multi-label Thoracic Disease Image Classification with Cross-Attention Networkscited by 22
  12. 2019InfoMask: Masked Variational Latent Representation to Localize Chest Diseasecited by 15
  13. 2020Region Proposals for Saliency Map Refinement for Weakly-supervised Disease Localisation and Classificationcited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 14; 2023: 20; 2024: 16; 2025: 12; 2026: 3.

72 papers.

Sort:

  1. 2021Interpretable Image Classification with Differentiable Prototypes Assignmentcited by 97
  2. 2021Transparency of Deep Neural Networks for Medical Image Analysis: A Review of Interpretability Methodscited by 83
  3. 2022Delving into Masked Autoencoders for Multi-Label Thorax Disease Classificationcited by 65
  4. 2021This looks more like that: Enhancing Self-Explaining Models by Prototypical Relevance Propagationcited by 43
  5. 2023Learning Support and Trivial Prototypes for Interpretable Image Classificationcited by 38
  6. 2022ProtoVAE: A Trustworthy Self-Explainable Prototypical Variational Modelcited by 34
  7. 2023ProtoSeg: Interpretable Semantic Segmentation with Prototypical Partscited by 33
  8. 2021A Systematic Benchmarking Analysis of Transfer Learning for Medical Image Analysiscited by 31
  9. 2022Explainable Deep Learning Methods in Medical Image Classification: A Surveycited by 31
  10. 2022Explaining Chest X-ray Pathologies in Natural Languagecited by 27
  11. 2023Interpretability Benchmark for Evaluating Spatial Misalignment of Prototypical Parts Explanationscited by 27
  12. 2023ICICLE: Interpretable Class Incremental Continual Learningcited by 24
38 more
  1. 2021ProtoMIL: Multiple Instance Learning with Prototypical Parts for Whole-Slide Image Classificationcited by 22
  2. 2024EVA-X: A Foundation Model for General Chest X-ray Analysis with Self-supervised Learningcited by 22
  3. 2021Label-Assemble: Leveraging Multiple Datasets with Partial Labelscited by 20
  4. 2023Pixel-Grounded Prototypical Part Networkscited by 18
  5. 2024Self-eXplainable AI for Medical Image Analysis: A Survey and New Outlookscited by 18
  6. 2025A Comprehensive Survey on Self-Interpretable Neural Networkscited by 18
  7. 2024LucidPPN: Unambiguous Prototypical Parts Network for User-centric Interpretable Computer Visioncited by 15
  8. 2022Knowledge Distillation to Ensemble Global and Interpretable Prototype-Based Mammogram Classification Modelscited by 11
  9. 2023MProtoNet: A Case-Based Interpretable Model for Brain Tumor Classification with 3D Multi-parametric Magnetic Resonance Imagingcited by 11
  10. 2023Towards Medical Artificial General Intelligence via Knowledge-Enhanced Multimodal Pretrainingcited by 11
  11. 2023ProtoASNet: Dynamic Prototypes for Inherently Interpretable and Uncertainty-Aware Aortic Stenosis Classification in Echocardiographycited by 11
  12. 2022Probabilistic Integration of Object Level Annotations in Chest X-ray Classificationcited by 10
  13. 2023Keep the Faith: Faithful Explanations in Convolutional Neural Networks for Case-Based Reasoningcited by 10
  14. 2023A Framework for Interpretability in Machine Learning for Medical Imagingcited by 9
  15. 2023Concept Distillation: Leveraging Human-Centered Explanations for Model Improvementcited by 9
  16. 2022ProGReST: Prototypical Graph Regression Soft Trees for Molecular Property Predictioncited by 8
  17. 2024A survey on Concept-based Approaches For Model Improvementcited by 8
  18. 2023Don't PANIC: Prototypical Additive Neural Network for Interpretable Classification of Alzheimer's Diseasecited by 7
  19. 2023ProtoArgNet: Interpretable Image Classification with Super-Prototypes and Argumentation [Technical Report]cited by 7
  20. 2024This actually looks like that: Proto-BagNets for local and global interpretability-by-designcited by 7
  21. 2023Prototypical Self-Explainable Models Without Re-trainingcited by 6
  22. 2023ProtoExplorer: Interpretable Forensic Analysis of Deepfake Videos using Prototype Exploration and Refinementcited by 5
  23. 2024Learning Low-Rank Feature for Thorax Disease Classificationcited by 4
  24. 2024Cross- and Intra-image Prototypical Learning for Multi-label Disease Diagnosis and Interpretationcited by 4
  25. 2025ProtoECGNet: Case-Based Interpretable Deep Learning for Multi-Label ECG Classification with Contrastive Learningcited by 4
  26. 2023Interpretable Alzheimer's Disease Classification Via a Contrastive Diffusion Autoencodercited by 3
  27. 2023Robust Text Classification: Analyzing Prototype-Based Networkscited by 3
  28. 2024Prototype-based Interpretable Breast Cancer Prediction Models: Analysis and Challengescited by 3
  29. 2024Concept Complement Bottleneck Model for Interpretable Medical Image Diagnosiscited by 3
  30. 2025This looks like what? Challenges and Future Research Directions for Part-Prototype Modelscited by 3
  31. 2025SIDE: Sparse Information Disentanglement for Explainable Artificial Intelligencecited by 3
  32. 2024ProtoAL: Interpretable Deep Active Learning with prototypes for medical imagingcited by 2
  33. 2025DeepChest: Dynamic Gradient-Free Task Weighting for Effective Multi-Task Learning in Chest X-ray Classificationcited by 2
  34. 2025ProtoEFNet: Dynamic Prototype Learning for Inherently Interpretable Ejection Fraction Estimation in Echocardiographycited by 2
  35. 2021Ethical Implementation of Artificial Intelligence to Select Embryos in In Vitro Fertilizationcited by 1
  36. 2022Learning by Erasing: Conditional Entropy based Transferable Out-Of-Distribution Detectioncited by 1
  37. 2022XADLiME: eXplainable Alzheimer's Disease Likelihood Map Estimation via Clinically-guided Prototype Learningcited by 1
  38. 2023On Model Explanations with Transferable Neural Pathwayscited by 1

50 most cited of 72 All 72 (JSON)