mlsanityData to 14 Oct 2026

Interpreting and Correcting Medical Image Classification with PIP-Net

arXiv 2307.10404 ↗First posted 19 Jul 2023cs.CV cs.AI cs.LGcited by 11

Not on the map. Why?

Abstract (arXiv)

Part-prototype models are explainable-by-design image classifiers, and a promising alternative to black box AI. This paper explores the applicability and potential of interpretable machine learning, in particular PIP-Net, for automated diagnosis support on real-world medical imaging data. PIP-Net learns human-understandable prototypical image parts and we evaluate its accuracy and interpretability for fracture detection and skin cancer diagnosis. We find that PIP-Net's decision making process is in line with medical classification standards, while only provided with image-level class labels. Because of PIP-Net's unsupervised pretraining of prototypes, data quality problems such as undesired text in an X-ray or labelling errors can be easily identified. Additionally, we are the first to show that humans can manually correct the reasoning of PIP-Net by directly disabling undesired prototypes. We conclude that part-prototype models are promising for medical applications due to their interpretability and potential for advanced model debugging.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 21 of its 42 references that are in the map. First posted on arXiv 19 Jul 2023.

Builds on

21 of 42 references.

References · 21

  1. 2022A ConvNet for the 2020scited by 3,579
  2. 2020Shortcut Learning in Deep Neural Networkscited by 1,969
  3. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 737
  4. 2019Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)cited by 669
  5. 2022Last Layer Re-Training is Sufficient for Robustness to Spurious Correlationscited by 381
  6. 2019Unmasking Clever Hans Predictors and Assessing What Machines Really Learncited by 365
  7. 2017Right for the Right Reasons: Training Differentiable Models by Constraining their Explanationscited by 294
  8. 2021TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentationcited by 227
  9. 2017Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?cited by 221
  10. 2020Neural Prototype Trees for Interpretable Fine-grained Image Recognitioncited by 214
  11. 2019Interpretations are useful: penalizing explanations to align neural networks with prior knowledgecited by 145
  12. 2021What I Cannot Predict, I Do Not Understand: A Human-Centered Evaluation Framework for Explainability Methodscited by 98
9 more
  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. 2021IAIA-BL: A Case-based Interpretable Deep Learning Model for Classification of Mass Lesions in Digital Mammographycited by 72
  4. 2018Deep Learning Predicts Hip Fracture using Confounding Patient and Healthcare Variablescited by 50
  5. 2020How Useful Are the Machine-Generated Interpretations to General Users? A Human Evaluation on Guessing the Incorrectly Predicted Labelscited by 39
  6. 2021ProtoMIL: Multiple Instance Learning with Prototypical Parts for Whole-Slide Image Classificationcited by 22
  7. 2022Evaluating Explainable AI on a Multi-Modal Medical Imaging Task: Can Existing Algorithms Fulfill Clinical Requirements?cited by 20
  8. 2023Reveal to Revise: An Explainable AI Life Cycle for Iterative Bias Correction of Deep Modelscited by 17
  9. 2016An Overview of Melanoma Detection in Dermoscopy Images Using Image Processing and Machine Learningcited by 13

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 4; 2025: 5.

11 papers.

  1. 2024Towards Explainable Artificial Intelligence (XAI): A Data Mining Perspectivecited by 9
  2. 2023Dynamically Scaled Temperature in Self-Supervised Contrastive Learningcited by 4
  3. 2024PIPNet3D: Interpretable Detection of Alzheimer in MRI Scanscited by 3
  4. 2025This looks like what? Challenges and Future Research Directions for Part-Prototype Modelscited by 3
  5. 2025Birds look like cars: Adversarial analysis of intrinsically interpretable deep learningcited by 3
  6. 2024Patch-based Intuitive Multimodal Prototypes Network (PIMPNet) for Alzheimer's Disease classificationcited by 2
  7. 2024Revisiting FunnyBirds evaluation framework for prototypical parts networkscited by 2
  8. 2025Debugging Concept Bottleneck Models through Removal and Retrainingcited by 2
  9. 2023Representing visual classification as a linear combination of wordscited by 1
  10. 2025PiPViT: Patch-based Visual Interpretable Prototypes for Retinal Image Analysiscited by 0
  11. 2025Multimodal Feature Prototype Learning for Interpretable and Discriminative Cancer Survival Predictioncited by 0