Assessing Bias in Skin Lesion Classifiers With Contemporary Deep Learning and Post-Hoc Explainability Techniques
Adam Corbin, Oge Marques
Abstract
As Artificial Intelligence is increasingly utilized in dermatology, ensuring fairness in the development of Machine Learning models is crucial, particularly in skin lesion classification, where decisions can significantly impact people’s lives. This study investigates the presence of biases between different Fitzpatrick Skin Types in baseline pretrained models and evaluates various training techniques to mitigate these disparities. An unsupervised skin transformer is developed to adjust an image’s FST, and joint regularization and synthetic image blending methods are employed to address bias concerns. Additionally, eXplainable AI techniques, such as Grad-CAM, are utilized to identify any underlying reasons for bias in the models. The results indicate that joint regularization and synthetic blending methods enhance the area under the curve performance and fairness. Meanwhile, eXplainable AI was found to be a valuable tool for fine-tuning Deep Learning models and uncovering problems. These findings can aid in developing accurate and unbiased skin lesion classification models, promoting equitable healthcare, and improving patient outcomes.