Summer Institute in Neuroimaging and Data Science

Project Summary/Abstract The study of the human brain with neuroimaging technologies has entered an exciting era of Big Data. Many data collection projects, including NIH-funded initiatives such as the Human Connectome Project and the Ado- lescent Brain Cognitive Development Study, have made neuroimaging datasets of unprecedented quality freely available to researchers. Despite appearing only recently, these large datasets have already yielded important new insights about human brain structure and function, and the quantity of ongoing NIH-funded projects related to these datasets suggests that this yield has not yet peaked. However, neuroscience researchers face substan- tial challenges in capitalizing on these datasets. The incorporation of Big Data into research requires a set of technical and theoretical tools that are not emphasized in traditional training in neuroscience. These skills and ideas, collectively referred to as Data Science, include both technical expertise—e.g., computer science, soft- ware engineering, databases, machine learning, statistics, and data visualization—as well as a familiarity with the contemporary data ecosystem and best practices. The Summer Institute in Neuroimaging and Data Science features instruction by experts in data science methodology and by leading neuroimaging researchers who are applying data science to answer scientific questions about the human brain. In addition to lectures and tutorials on the theoretical background of data science methodology and its application to neuroimaging, the course fea- tures a week-long hackathon, in which learning is driven by student-led group-projects, with guidance from the course instructors and additional experts. Overall, the curriculum emphasizes experiential hands-on training and collaborative learning.