mlsanityData to 14 Oct 2026

Concept Inconsistency in Dermoscopic Concept Bottleneck Models: A Rough-Set Analysis of the Derm7pt Dataset

arXiv 2604.19323 ↗First posted 21 Apr 2026cs.LG cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Concept Bottleneck Models (CBMs) route predictions exclusively through a clinically grounded concept layer, binding interpretability to concept-label consistency. When a dataset contains concept-level inconsistencies, identical concept profiles mapped to conflicting diagnosis labels create an unresolvable bottleneck that imposes a hard ceiling on achievable accuracy. In this paper, we apply rough set theory to the Derm7pt dermoscopy benchmark and characterize the full extent and clinical structure of this inconsistency. Among 305 unique concept profiles formed by the 7 dermoscopic criteria of the 7-point melanoma checklist, 50 (16.4%) are inconsistent, spanning 306 images (30.3% of the dataset). This yields a theoretical accuracy ceiling of 92.1%, independent of backbone architecture or training strategy for CBMs that exclusively operate with hard concepts. In addition, we characterize the conflict-severity distribution, identify the clinical features most responsible for boundary ambiguity, and evaluate two filtering strategies with quantified effects on dataset composition and CBM interpretability. Symmetric removal of all boundary-region images yields Derm7pt+, a fully consistent benchmark subset of 705 images with perfect quality of classification and no hard accuracy ceiling. Building on this filtered dataset, we present a hard CBM evaluated across 19 backbone architectures from the EfficientNet, DenseNet, ResNet, and Wide ResNet families. Under symmetric filtering, explored for completeness, EfficientNet-B5 achieves the best label F1 score (0.85) and label accuracy (0.90) on the held-out test set, with a concept accuracy of 0.70. Under asymmetric filtering, EfficientNet-B7 leads across all four metrics, reaching a label F1 score of 0.82 and concept accuracy of 0.70. These results establish reproducible baselines for concept-consistent CBM evaluation on dermoscopic data.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 27 of its 51 references that are in the map. First posted on arXiv 21 Apr 2026.

Builds on

27 of 51 references.

References · 27

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  3. 2016Densely Connected Convolutional Networkscited by 6,720
  4. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  5. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  6. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  7. 2016Wide Residual Networkscited by 3,070
  8. 2020Concept Bottleneck Modelscited by 1,032
  9. 2022Post-hoc Concept Bottleneck Modelscited by 293
  10. 2023Label-Free Concept Bottleneck Modelscited by 285
  11. 2019BCN20000: Dermoscopic Lesions in the Wildcited by 225
  12. 2020Axiom-based Grad-CAM: Towards Accurate Visualization and Explanation of CNNscited by 151
15 more
  1. 2020A Patient-Centric Dataset of Images and Metadata for Identifying Melanomas Using Clinical Contextcited by 146
  2. 2021Promises and Pitfalls of Black-Box Concept Learning Modelscited by 131
  3. 2020Use HiResCAM instead of Grad-CAM for faithful explanations of convolutional neural networkscited by 79
  4. 2023A Closer Look at the Intervention Procedure of Concept Bottleneck Modelscited by 64
  5. 2021Logic Explained Networkscited by 45
  6. 2020On Interpretability of Deep Learning based Skin Lesion Classifiers using Concept Activation Vectorscited by 39
  7. 2023Human Uncertainty in Concept-Based AI Systemscited by 39
  8. 2023Coherent Concept-based Explanations in Medical Image and Its Application to Skin Lesion Diagnosiscited by 26
  9. 2022ExAID: A Multimodal Explanation Framework for Computer-Aided Diagnosis of Skin Lesionscited by 19
  10. 2024MICA: Towards Explainable Skin Lesion Diagnosis via Multi-Level Image-Concept Alignmentcited by 18
  11. 2024Concept Bottleneck Models Without Predefined Conceptscited by 17
  12. 2024Concept-Attention Whitening for Interpretable Skin Lesion Diagnosiscited by 11
  13. 2024DERM12345: A Large, Multisource Dermatoscopic Skin Lesion Dataset with 38 Subclassescited by 10
  14. 2025An Analysis of Concept Bottleneck Models: Measuring, Understanding, and Mitigating the Impact of Noisy Annotationscited by 5
  15. 2024Dermatologist-like explainable AI enhances melanoma diagnosis accuracy: eye-tracking studycited by 2

Built on by

Not cited yet.