Radiological error is detrimental to both the health and wellbeing of patients. Despite the prevalence of radiological error in practice, the processes underlying such error are poorly understood, and current human and artificial intelligence (AI) training strategies are far from optimised. My proposed research project aims to gain a better understanding of the perceptual and cognitive mechanisms that contribute to radiological error with eye-tracking technology; develop human-intervention and AI training protocols to improve diagnostic accuracy; and develop a database of authentic medical images for use in training of radiologists.