Building trustworthy and transparent image-based medical artificial intelligence systems requires the ability to interrogate data and models at all stages of the development pipeline, from training models to post-deployment monitoring. Ideally, the data and associated AI systems could be described using terms already familiar to physicians, but this requires medical datasets densely annotated with semantically meaningful concepts.
Codella, N. C. F. et al. Skin lesion analysis toward melanoma detection: a challenge at the 2017 International Symposium on Biomedical Imaging , hosted by the International Skin Imaging Collaboration . InCodella, N. et al. Skin lesion analysis toward melanoma detection 2018: a challenge hosted by the International Skin Imaging Collaboration . Preprint at
Oakden-Rayner, L., Dunnmon, J., Carneiro, G. & Re, C. Hidden stratification causes clinically meaningful failures in machine learning for medical imaging. In 151–159 . Chung, Y., Kraska, T., Polyzotis, N., Tae, K. & Whang, S. Automated data slicing for model validation: a big data–AI integration approach. InDeGrave, A. J., Cai, Z. R., Janizek, J. D., Daneshjou, R. & Lee, S.-I. Auditing the inference processes of medical-image classifiers by leveraging generative AI and the expertise of physicians.Han, S. S. et al. The degradation of performance of a state-of-the-art skin image classifier when applied to patient-driven internet search.Yuksekgonul, M.