Our work on medical imaging AI is increasingly contributing to health policy and AI regulation. We have contributed to several recommendations and guidelines on how to evaluate, test and audit AI systems. Our work focuses on monitoring and assessment of bias and fairness, aiming to assure safe and ethical deployment of AI in clinical practice.
Selected Publications
A causal perspective on dataset bias in machine learning for medical imaging, Nature Machine Intelligence, 2024
Generalisable deep learning method for mammographic density prediction across imaging techniques and self-reported race, Communications Medicine, 2024
Risk of Bias in Chest Radiography Deep Learning Foundation Models, Radiology: Artificial Intelligence, 2023
Automatic correction of performance drift under acquisition shift in medical image classification, Nature Communications, 2023
What’s fair is… fair? Presenting JustEFAB, an ethical framework for operationalizing medical ethics and social justice in the integration of clinical machine learning, ACM FAccT Conference, 2023
Potential sources of dataset bias complicate investigation of underdiagnosis by machine learning algorithms, Nature Medicine, 2022
Recommendations for the development and use of imaging test sets to investigate the test performance of artificial intelligence in health screening, The Lancet Digital Health, 2022
The medical algorithmic audit, The Lancet Digital Health, 2022
