Assessing the Generalizability of Deep Neural Networks-Based Models for Black Skin Lesions
-
1.
Universidade Estadual de Campinas (UNICAMP)
Description
Melanoma is the most severe type of skin cancer due to its ability to cause metastasis. It is more common in black people, often affecting acral regions: palms, soles, and nails. Deep neural networks have shown tremendous potential for improving clinical care and skin cancer diagnosis. Nevertheless, prevailing studies predominantly rely on datasets of white skin tones, neglecting to report diagnostic outcomes for diverse patient skin tones. In this work, we evaluate supervised and self-supervised models in skin lesion images extracted from acral regions commonly observed in black individuals. Also, we carefully curate a dataset containing skin lesions in acral regions and assess the datasets concerning the Fitzpatrick scale to verify performance on black skin. Our results expose the poor generalizability of these models, revealing their favorable performance for lesions on white skin. Neglecting to create diverse datasets, which necessitates the development of specialized models, is unacceptable. Deep neural networks have great potential to improve diagnosis, particularly for populations with limited access to dermatology. However, including black skin lesions is necessary to ensure these populations can access the benefits of inclusive technology.
Notes
Acknowledgments
- Levy Chaves is partially funded by Becas Santander/UNICAMP – HUB 2022, Google LARA 2021, in part by the Coordenação de Aperfeiçoamento de Pessoal de Nível Superior – Brasil (CAPES) – Finance Code 001.
- Sandra Avila is partially funded by CNPq 315231/2020-3, FAEPEX, FAPESP 2013/08293-7, 2020/09838-0, H.IAAC 01245.013778/2020-21, and Google Award for Inclusion Research Program 2022 ("Dark Skin Matters: Fair and Unbiased Skin Lesion Models").
Files
Restricted
The record is publicly accessible, but files are restricted to users with access.
Request access
If you would like to request access to these files, please fill out the form below.
You need to satisfy these conditions in order for this request to be accepted:
This dataset does not own the copyright of the image files. We can provide access under certain conditions and terms for researchers who wish to use the image files for non-commercial research and/or educational purposes.
Terms of access
The "Researcher" has requested permission to use the dataset. In exchange for such permission, Researcher hereby agrees to the following terms and conditions:
- Researcher shall use the dataset only for non-commercial research and educational purposes.
- Researcher accepts full responsibility for her/his/them use of the dataset and shall defend and indemnify the dataset team and the University of Campinas, including their employees, trustees, officers, and agents, against any claims arising from the Researcher's use of the dataset, including but not limited to Researcher's use of any copies of copyrighted image files that she/he/they may create from the dataset.
- Researcher will not under any circumstances attempt to determine the identity of individuals in the dataset.
- Researcher may provide research associates and colleagues access to the dataset if they first agree to be bound by these terms and conditions.
- The dataset team and the University of Campinas reserve the right to terminate the Researcher's access to the dataset anytime.
Access request
Please, fill this form with the following data:
- Name of the Institution you are working on.
- Briefly describe what the dataset will be used for.
The request must be done from an institutional/educational email account.
You are currently not logged in. Do you have an account? Log in here
Additional details
Identifiers
- arXiv
- arXiv:2310.00517
Dates
- Available
-
2023-11-27