Convolutional Neural Networks have demonstrated dermatologist-level performance in the classification of melanoma and other skin lesions, 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. Contributions of this work include the application of different debiasing techniques for artefact bias removal and the concept of instrument bias unlearning for domain generalisation in melanoma detection. 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.

翻译：在这项工作中,我们通过两种主要的偏向学技术,大力消除自动黑皮瘤分类管道中的偏差和虚假差异;我们通过这些消除偏向的方法,表明以往研究中外科标记和标尺带来的偏差可以合理地减轻;我们还展示了与用于捕获损耗图像的成像仪有关的非学习假变异的普及性益处;这项工作的贡献包括应用不同的偏向技术消除亚麻痹偏差,以及将仪器偏向学概念用于在黑皮瘤检测中的一般化;我们的实验结果证明,上述每一种偏差的影响都明显减少,不同的脱偏差技术在不同的任务中表现突出。