FunnyNodules: A Customizable Medical Dataset Tailored for Evaluating Explainable AI
Not on the map. Why?
Abstract (arXiv)
Densely annotated medical image datasets that capture not only diagnostic labels but also the underlying reasoning behind these diagnoses are scarce. Such reasoning-related annotations are essential for developing and evaluating explainable AI (xAI) models that reason similarly to radiologists: making correct predictions for the right reasons. To address this gap, we introduce FunnyNodules, a fully parameterized synthetic dataset designed for systematic analysis of attribute-based reasoning in medical AI models. The dataset generates abstract, lung nodule-like shapes with controllable visual attributes such as roundness, margin sharpness, and spiculation. The target class is derived from a predefined attribute combination, allowing full control over the decision rule that links attributes to the diagnostic class. We demonstrate how FunnyNodules can be used in model-agnostic evaluations to assess whether models learn correct attribute-target relations, to interpret over- or underperformance in attribute prediction, and to analyze attention alignment with attribute-specific regions of interest. The framework is fully customizable, supporting variations in dataset complexity, target definitions, class balance, and beyond. With complete ground truth information, FunnyNodules provides a versatile foundation for developing, benchmarking, and conducting in-depth analyses of explainable AI methods in medical image analysis.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 22 of its 36 references that are in the map. First posted on arXiv 19 Nov 2025.
Builds on
22 of 36 references.
References · 22
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2016Densely Connected Convolutional Networkscited by 6,720
- 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
- 2013Visualizing and Understanding Convolutional Networkscited by 2,290
- 2017A Survey on Deep Learning in Medical Image Analysiscited by 1,186
- 2020Concept Bottleneck Modelscited by 1,032
- 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 737
- 2020CheXbert: Combining Automatic Labelers and Expert Annotations for Accurate Radiology Report Labeling Using BERTcited by 337
- 2022From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AIcited by 302
- 2022Brain Imaging Generation with Latent Diffusion Modelscited by 268
- 2018GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classificationcited by 242
- 2019Interpretable Counterfactual Explanations Guided by Prototypescited by 223
10 more
- 2022Towards Human-centered Explainable AI: A Survey of User Studies for Model Explanationscited by 85
- 2020This Looks Like That, Because ... Explaining Prototypes for Interpretable Image Recognitioncited by 50
- 2023FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methodscited by 50
- 2023Synthetically Enhanced: Unveiling Synthetic Data's Potential in Medical Imaging Researchcited by 18
- 2024Explaining Explainability: Recommendations for Effective Use of Concept Activation Vectorscited by 13
- 2022CIRDataset: A large-scale Dataset for Clinically-Interpretable lung nodule Radiomics and malignancy predictioncited by 6
- 2023Interpretable Medical Image Classification using Prototype Learning and Privileged Informationcited by 6
- 2024Evaluating the Explainability of Attributes and Prototypes for a Medical Classification Modelcited by 4
- 2025Hierarchical Vision Transformer with Prototypes for Interpretable Medical Image Classificationcited by 2
- 2025Minimum Data, Maximum Impact: 20 annotated samples for explainable lung nodule classificationcited by 1
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.