AI to increase statistical power in clinical neuroimaging

Many studies worldwide use neuroimaging to investigate whether there are abnormalities in the structure or function of the brain that underlie mental disorders. The sample sizes in these studies are limited because of the high cost of neuroimaging and difficulties in recruiting large numbers of patients if the disease is rare. This is a problem because clinical researchers need to investigate correlations between imaging metrics and a wide array of demographic and clinical variables, which traditionally requires large sample sizes to obtain good statistical power. This project will thus harness artificial intelligence (AI) to reduce the many variables under consideration in a real-world clinical neuroimaging study of bipolar disorder to just those that are most important. This will boost the statistical power of the study and inform future clinical neuroimaging studies of the best approach to analyze richly-characterized yet small datasets.

Faculty Supervisor:

Nicholas Bock

Student:

Partner:

Indian Institute of Technology Kanpur

Discipline:

Life Sciences

Sector:

Education

University:

McMaster University

Program: