It is a great pleasure to announce Timothy Odonga as speaker at our lab! Timothy will present his latest research on fairness of classifiers that was already featured on MICCAI and NeurIPS Fair ML for Health.
Abstract: Recent advances in computer vision have led to breakthroughs in the development of automated skin image analysis. However, no attempt has been made to evaluate the consistency in performance across populations with varying skin tones. In this paper, we present an approach to estimate skin tone in skin disease benchmark datasets and investigate whether model performance is dependent on this measure. Specifically, we use Individual Typology Angle (ITA) to approximate skin tone in dermatology datasets. We look at the distribution of ITA values to better understand skin color representation in two benchmark datasets: 1) the ISIC 2018 Challenge dataset, a collection of dermoscopic images of skin lesions for the detection of skin cancer, and 2) the SD-198 dataset, a collection of clinical images capturing a wide variety of skin diseases. To estimate ITA, we first develop segmentation models to isolate non diseased areas of skin. We find that the majority of the data in the two datasets have ITA values between 34.5 and 48, which are associated with lighter skin, and is consistent with under-representation of darker skinned populations in these datasets. We also find no measurable correlation between accuracy of machine learning models and ITA values, though more comprehensive data is needed for further validation.
Short Bio: Timothy holds a master’s degree in Electrical and Computer Engineering from Carnegie Mellon University, and two bachelor’s degrees in Physics and Electrical Engineering from Gordon College and the University of Southern California, respectively. He has experience working on research projects in machine learning at CMU and IBM Research. During his time at IBM Research, he was an IBM Great Minds scholar and an AI for Social Good fellow as he worked on a project on AI Fairness in dermatology. The research papers from this work were accepted and published in the MICCAI 2020 conference, and the NeurIPS Fair ML for Health Workshop in 2019. His research interests include machine learning for healthcare focusing on topics like fairness, explainability, and causality
Paper at MICCAI 2020: Fairness of Classifiers Across Skin Tones in Dermatology - https://link.springer.com/chapter/10.1007/978-3-030-59725-2_31
NeurIPS Fair ML for Health Workshop with Timothy's Paper - https://www.fairmlforhealth.com/accepted-papers
This video is released under CC BY 4.0. Please feel free to share and reuse.