Skin Deep Unlearning: Artefact and Instrument Debiasing in the Context of Melanoma Classification

Peter Bevan, Amir Atapour-Abarghouei
Proceedings of the 39th International Conference on Machine Learning, PMLR 162:1874-1892, 2022.

Abstract

Convolutional Neural Networks have demonstrated dermatologist-level performance in the classification of melanoma from skin lesion images, but prediction irregularities due to biases seen within the training data are an issue that should be addressed before widespread deployment is possible. In this work, we robustly remove bias and spurious variation from an automated melanoma classification pipeline using two leading bias unlearning techniques. We show that the biases introduced by surgical markings and rulers presented in previous studies can be reasonably mitigated using these bias removal methods. We also demonstrate the generalisation benefits of unlearning spurious variation relating to the imaging instrument used to capture lesion images. Our experimental results provide evidence that the effects of each of the aforementioned biases are notably reduced, with different debiasing techniques excelling at different tasks.

Cite this Paper

BibTeX
@InProceedings{pmlr-v162-bevan22a, title = {Skin Deep Unlearning: Artefact and Instrument Debiasing in the Context of Melanoma Classification}, author = {Bevan, Peter and Atapour-Abarghouei, Amir}, booktitle = {Proceedings of the 39th International Conference on Machine Learning}, pages = {1874--1892}, year = {2022}, editor = {Chaudhuri, Kamalika and Jegelka, Stefanie and Song, Le and Szepesvari, Csaba and Niu, Gang and Sabato, Sivan}, volume = {162}, series = {Proceedings of Machine Learning Research}, month = {17--23 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v162/bevan22a/bevan22a.pdf}, url = {https://proceedings.mlr.press/v162/bevan22a.html}, abstract = {Convolutional Neural Networks have demonstrated dermatologist-level performance in the classification of melanoma from skin lesion images, but prediction irregularities due to biases seen within the training data are an issue that should be addressed before widespread deployment is possible. In this work, we robustly remove bias and spurious variation from an automated melanoma classification pipeline using two leading bias unlearning techniques. We show that the biases introduced by surgical markings and rulers presented in previous studies can be reasonably mitigated using these bias removal methods. We also demonstrate the generalisation benefits of unlearning spurious variation relating to the imaging instrument used to capture lesion images. Our experimental results provide evidence that the effects of each of the aforementioned biases are notably reduced, with different debiasing techniques excelling at different tasks.} }
Endnote
%0 Conference Paper %T Skin Deep Unlearning: Artefact and Instrument Debiasing in the Context of Melanoma Classification %A Peter Bevan %A Amir Atapour-Abarghouei %B Proceedings of the 39th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2022 %E Kamalika Chaudhuri %E Stefanie Jegelka %E Le Song %E Csaba Szepesvari %E Gang Niu %E Sivan Sabato %F pmlr-v162-bevan22a %I PMLR %P 1874--1892 %U https://proceedings.mlr.press/v162/bevan22a.html %V 162 %X Convolutional Neural Networks have demonstrated dermatologist-level performance in the classification of melanoma from skin lesion images, but prediction irregularities due to biases seen within the training data are an issue that should be addressed before widespread deployment is possible. In this work, we robustly remove bias and spurious variation from an automated melanoma classification pipeline using two leading bias unlearning techniques. We show that the biases introduced by surgical markings and rulers presented in previous studies can be reasonably mitigated using these bias removal methods. We also demonstrate the generalisation benefits of unlearning spurious variation relating to the imaging instrument used to capture lesion images. Our experimental results provide evidence that the effects of each of the aforementioned biases are notably reduced, with different debiasing techniques excelling at different tasks.
APA
Bevan, P. & Atapour-Abarghouei, A.. (2022). Skin Deep Unlearning: Artefact and Instrument Debiasing in the Context of Melanoma Classification. Proceedings of the 39th International Conference on Machine Learning, in Proceedings of Machine Learning Research 162:1874-1892 Available from https://proceedings.mlr.press/v162/bevan22a.html.

Related Material