Research Infrastructure: MRI: Acquisition of the computational hardware to derive value from high-throughput whole-slide imaging

This project seeks to address the critical need for computational hardware capable of supporting artificial intelligence studies in pathology based on large-scale clinical data collection efforts currently underway at the Mayo Clinic in Rochester, MN. We are in the process of digitizing a vast clinical data repository to meet the clinical objectives of the Department of Laboratory Medicine and Pathology (DLMP), which carries enormous potential for innovative and unparalleled research in pathology. However, to fully leverage this treasure trove of data, significant investments in computation must be made. This project’s novelties are to develop a shared computational resource for pathology research based on the combined experience of the investigators in the Division of Computational Pathology and AI within DLMP and the ongoing data collection activities. Upon completion, this project will drive the advancement of knowledge throughout healthcare, leading to innovative breakthroughs that benefit both academia and the broader scientific community. Although our group contributes to the clinical application of AI in DLMP, the research itself cannot and should not be solely driven by the specific clinical needs of the department, and therefore we must augment existing strategies with the computational instrumentation needed to establish research capabilities around our rapidly growing data sets. The project involves utilizing an existing environment at Mayo to install GPU- and CPU-based computational servers dedicated to the proposed work and connected to the rapidly growing clinical data store. Local data storage for rapid computational processing is also part of the funded computational environment, and together will support data reuse, data exploration, and modern machine learning strategies to streamline data annotation and labeling. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.