Research performed in veterinary medicine impacts companion and agricultural animals, as well as human health through the use of pre-clinical models of disease. Pursuits in this field range from understanding the impact of pollutants on various aspects of physiology to the response of the body to infectious agents of disease.
UC Davis is unique in that it has both a School of Veterinary Medicine and a School of Medicine, poising CeDAR to tap experts at both schools, and analyze data sets from both fields, enhancing the potential impact and efficiency of developing tools and research methods to improve human and animal health.
Data Science Challenges in Large-Scale Light Microscopy Imaging with Applications to Neuroimmunology
Principal Investigator: Colin Reardon, assistant professor, Anatomy, Physiology and Cell Biology, School of Veterinary Medicine
Reardon and his team are developing data science methods and software that will impact the analysis, processing, and reconstruction of 3D light microscopy images arising in neuroimmunology. Their goal is to produce software capable of supporting the processing of large data sets (hundreds of gigabytes of data). The tools developed will have broad impact, benefiting not just neuroimmunology, but other fields where light microscopy is widely used.
This is an interdisciplinary collaboration, with school of veterinary medicine experts performing biological experiments, capturing images from slides, and generating data in the form of 3D images. Mathematicians will use the data to design novel image segmentation algorithms, improving on the existing arsenal of image processing tools.
AI in Clinical Decision Making for Veterinary Medicine
Principal Investigator: Allison Zwingenberger, professor, Surgical and Radiological Sciences, School of Veterinary Medicine
The application of Artificial Intelligence (AI) to clinical decision making in veterinary medicine is in its infancy. The School of Veterinary Medicine (SVM) at UC Davis is well positioned to become a leader in integrating artificial intelligence into clinical decision making. The SVM has a dedicated, well-connected multidisciplinary group of veterinarians and data scientists that are interested in promoting the use of big data and AI in veterinary medicine.
Zwingenberger and her team are creating a workflow to extract structured data and clinical information from unstructured text into a cross species common data model that will provide the means to unlock 20 years of clinical data and enable transformation to machine learning. This will facilitate studies in virtually every discipline of veterinary medicine and could extend to human medicine.