Skip to main content

Research Repository

Advanced Search

Detecting Melanoma Fairly: Skin Tone Detection and Debiasing for Skin Lesion Classification

Bevan, Peter J.; Atapour-Abarghouei, Amir

Authors

Peter J. Bevan



Contributors

Konstantinos Kamnitsas
Editor

Lisa Koch
Editor

Mobarakol Islam
Editor

Ziyue Xu
Editor

Jorge Cardoso
Editor

Qi Doi
Editor

Nicola Rieke
Editor

Sotirios Tsaftaris
Editor

Abstract

Convolutional Neural Networks have demonstrated human-level performance in the classification of melanoma and other skin lesions, but evident performance disparities between differing skin tones should be addressed before widespread deployment. In this work, we propose an efficient yet effective algorithm for automatically labelling the skin tone of lesion images, and use this to annotate the benchmark ISIC dataset. We subsequently use these automated labels as the target for two leading bias ‘unlearning’ techniques towards mitigating skin tone bias. Our experimental results provide evidence that our skin tone detection algorithm outperforms existing solutions and that ‘unlearning’ skin tone may improve generalisation and can reduce the performance disparity between melanoma detection in lighter and darker skin tones.

Citation

Bevan, P. J., & Atapour-Abarghouei, A. (2022). Detecting Melanoma Fairly: Skin Tone Detection and Debiasing for Skin Lesion Classification. In K. Kamnitsas, L. Koch, M. Islam, Z. Xu, J. Cardoso, Q. Doi, …S. Tsaftaris (Eds.), DART 2022: Domain Adaptation and Representation Transfer (1-11). https://doi.org/10.1007/978-3-031-16852-9_1

Conference Name DART: MICCAI Workshop on Domain Adaptation and Representation Transfer
Acceptance Date Aug 15, 2022
Online Publication Date Sep 15, 2022
Publication Date 2022
Deposit Date Sep 20, 2022
Publicly Available Date Sep 16, 2023
Volume 13542
Pages 1-11
Series Title Lecture Notes in Computer Science
Series ISSN 0302-9743,1611-3349
Book Title DART 2022: Domain Adaptation and Representation Transfer
ISBN 9783031168512
DOI https://doi.org/10.1007/978-3-031-16852-9_1
Public URL https://durham-repository.worktribe.com/output/1135904

Files

Accepted Conference Proceeding (1.5 Mb)
PDF

Copyright Statement
This version of the contribution has been accepted for publication, after peer review (when applicable) but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: http://dx.doi.org/[insert DOI]. Use of this Accepted Version is subject to the publisher’s Accepted Manuscript terms of use https://www.springernature.com/gp/open-research/policies/accepted-manuscript-terms







You might also like



Downloadable Citations