Sarah Hooper is a research scientist at the National Institutes of Health working at the intersection of deep learning and medical imaging. Her research focuses on developing AI systems that improve the quality, efficiency, and accessibility of healthcare.
During her Ph.D. in electrical engineering at Stanford University, Hooper developed label-efficient deep learning methods for medical image analysis. Her work focused on reducing the time, data, and specialized expertise required to interpret medical images, with the goal of expanding access to advanced imaging in high-volume and resource-limited healthcare settings.
More broadly, Hooper has worked across the medical imaging pipeline, from image acquisition and reconstruction to downstream image analysis and clinical workflow integration. At the NIH’s NHLBI Office of AI Research, she now develops deep learning tools and imaging platforms for biomedical and clinical research applications.
Hooper’s interest in healthcare technology began at Rice University, where she studied electrical engineering and global health technologies. She developed low-cost medical devices for neonatal care and worked in Malawi on technologies designed for resource-constrained healthcare environments. She later became interested in applying deep learning to healthcare through work on seizure prediction for epilepsy. Together, these experiences shaped her interest in developing deep learning methods to improve access to high-quality healthcare.
Outside of research, Sarah enjoys volunteering at a local animal shelter, gardening, and traveling
