Are Explanations Helpful? A Comparative Analysis of Explainability Methods in Skin Lesion Classifiers

Rosa Y. G. Paccotacya-Yanque, Alceu Bissoto, Sandra Avila
12/4/2024
cs.CV

No official code found. Best implementation: RosePY/XAI-for-Skin-Lesion (1 star, last commit 2025-12-04).

Abstract

Deep Learning has shown outstanding results in computer vision tasks; healthcare is no exception. However, there is no straightforward way to expose the decision-making process of DL models. Good accuracy is not enough for skin cancer predictions. Understanding the model's behavior is crucial for clinical application and reliable outcomes. In this work, we identify desiderata for explanations in skin-lesion models. We analyzed seven methods, four based on pixel-attribution (Grad-CAM, Score-CAM, LIME, SHAP) and three on high-level concepts (ACE, ICE, CME), for a deep neural network trained on the International Skin Imaging Collaboration Archive. Our findings indicate that while these techniques reveal biases, there is room for improving the comprehensiveness of explanations to achieve transparency in skin-lesion models.

View on arXivView PDF

Code Implementations(1)

RosePY/XAI-for-Skin-LesionCommunity100%

Repository for Are Explanations Helpful? A Comparative Analysis of Explainability Methods in Skin Lesion Classifiers paper

11Shell, PythonAug 1, 202410 months ago

Similar Papers

Enhancing Skin Disease Diagnosis: Interpretable Visual Concept Discovery with SAM

87% match2024

An Interpretable Deep Learning Approach for Skin Cancer Categorization

86% match1 repo112023

Using Computer Vision for Skin Disease Diagnosis in Bangladesh Enhancing Interpretability and Transparency in Deep Learning Models for Skin Cancer Classification

86% match2025

Revamping AI Models in Dermatology: Overcoming Critical Challenges for Enhanced Skin Lesion Diagnosis

86% match2023

Dermoscopic Dark Corner Artifacts Removal: Friend or Foe?

86% match1 repo12023

Evaluating Machine Learning-based Skin Cancer Diagnosis

86% match2024

Cite this paper

@article{paccotacyayanque2024explanations,
  title  = {Are Explanations Helpful? A Comparative Analysis of Explainability Methods in Skin Lesion Classifiers},
  author = {Rosa Y. G. Paccotacya-Yanque and Alceu Bissoto and Sandra Avila},
  year   = {2024},
  eprint = {2412.03166},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2412.03166v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2412.03166.svg)](https://codeofpaper.com/paper/2412.03166)

Discussion