Towards Facilitated Fairness Assessment of AI-based Skin Lesion Classifiers Through GenAI-based Image Synthesis
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915689184362496 |
|---|---|
| author | Watanabe, Ko Frolov, Stanislav Hassan, Aya Dembinsky, David Lucieri, Adriano Dengel, Andreas |
| author_facet | Watanabe, Ko Frolov, Stanislav Hassan, Aya Dembinsky, David Lucieri, Adriano Dengel, Andreas |
| contents | Recent advances in deep learning and on-device inference could transform routine screening for skin cancers. Along with the anticipated benefits of this technology, potential dangers arise from unforeseen and inherent biases. A significant obstacle is building evaluation datasets that accurately reflect key demographics, including sex, age, and race, as well as other underrepresented groups. To address this, we train a state-of-the-art generative model to generate synthetic data in a controllable manner to assess the fairness of publicly available skin cancer classifiers. To evaluate whether synthetic images can be used as a fairness testing dataset, we prepare a real-image dataset (MILK10K) as a benchmark and compare the True Positive Rate result of three models (DeepGuide, MelaNet, and SkinLesionDensnet). As a result, the classification tendencies observed in each model when tested on real and generated images showed similar patterns across different attribute data sets. We confirm that highly realistic synthetic images facilitate model fairness verification. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_17860 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Facilitated Fairness Assessment of AI-based Skin Lesion Classifiers Through GenAI-based Image Synthesis Watanabe, Ko Frolov, Stanislav Hassan, Aya Dembinsky, David Lucieri, Adriano Dengel, Andreas Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Recent advances in deep learning and on-device inference could transform routine screening for skin cancers. Along with the anticipated benefits of this technology, potential dangers arise from unforeseen and inherent biases. A significant obstacle is building evaluation datasets that accurately reflect key demographics, including sex, age, and race, as well as other underrepresented groups. To address this, we train a state-of-the-art generative model to generate synthetic data in a controllable manner to assess the fairness of publicly available skin cancer classifiers. To evaluate whether synthetic images can be used as a fairness testing dataset, we prepare a real-image dataset (MILK10K) as a benchmark and compare the True Positive Rate result of three models (DeepGuide, MelaNet, and SkinLesionDensnet). As a result, the classification tendencies observed in each model when tested on real and generated images showed similar patterns across different attribute data sets. We confirm that highly realistic synthetic images facilitate model fairness verification. |
| title | Towards Facilitated Fairness Assessment of AI-based Skin Lesion Classifiers Through GenAI-based Image Synthesis |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2507.17860 |