Are Explanations Helpful? A Comparative Analysis of Explainability Methods in Skin Lesion Classifiers
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917416429158400 |
|---|---|
| author | Paccotacya-Yanque, Rosa Y. G. Bissoto, Alceu Avila, Sandra |
| author_facet | Paccotacya-Yanque, Rosa Y. G. Bissoto, Alceu Avila, Sandra |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_03166 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Are Explanations Helpful? A Comparative Analysis of Explainability Methods in Skin Lesion Classifiers Paccotacya-Yanque, Rosa Y. G. Bissoto, Alceu Avila, Sandra Computer Vision and Pattern Recognition 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. |
| title | Are Explanations Helpful? A Comparative Analysis of Explainability Methods in Skin Lesion Classifiers |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.03166 |