In her TEDx talk From Pixels to Patients, Katy delves into the critical issue of how the quality and representation of data used to train AI systems are shaping the future of medical imaging and healthcare. By examining the role data plays in AI decision-making, she explores the potential biases, gaps, and opportunities for improvement that could directly impact patient outcomes. Drawing on her expertise, Katy highlights the importance of using diverse, high-quality datasets to ensure AI systems provide equitable and accurate healthcare solutions for all. Through her talk, she aims to spark a conversation on how we can better align technology with human health needs. Katy is an Associate Professor in Medical Imaging Physics, she has been at the University of Salford since 2007. She is the co-research lead for the Digital Skill and Medical Imaging research group, She is co-chair of the research ethics committee for the School of Health and Society. Her research interests are in medical image analysis and optimization, utilization of medical imaging technology to improve health outcomes, developing novel acquisition and analysis techniques of medical imaging data in a variety of clinical applications. Katy has been an associate editor for the British Journal of Radiology for 10 years; the BJR is the highest impact factor rated medical imaging journal in the UK, and represents the multidisciplinary imaging community. She is ordinary council member of the Manchester Medical Society Medical Imaging Section, and a member of the Greater Manchester Cancer Academy Expert Advisory Group. This talk was given at a TEDx event using the TED conference format but independently organized by a local community. Learn more at https://www.ted.com/tedx