Images, often stored in multidimensional arrays are fast becoming ubiquitous in medical and public health research. Analyzing populations of images is a statistical problem that raises a host of daunting challenges. The most severe challenge is that data sets incorporating images recorded for hundreds or thousands of subjects at multiple visits are massive. We introduce the population value decomposition (PVD), a general method for simultaneous dimensionality reduction of large populations of massive images. We show how PVD can seamlessly be incorporated into statistical modeling and lead to a new, transparent and fast inferential framework. Our methodology was motivated by and applied to the Sleep Heart Health Study, the largest community-based cohort study of sleep containing more than 85 billion observations on thousands of subjects at two visits.
Crainiceanu, Ciprian M.; Caffo, Brian S.; Luo, Sheng; and Zipunnikov, Vadim, "POPULATION VALUE DECOMPOSITION, A FRAMEWORK FOR THE ANALYSIS OF IMAGE POPULATIONS" (October 2010). Johns Hopkins University, Dept. of Biostatistics Working Papers. Working Paper 220.