Sparse Non-Negative Matrix Factorization for Preclinical Bioluminescent Imaging

Bioluminescent imaging is used in oncology to measure tumoral size and activity via spatio-temporal photon emission counting. Bioluminescent signal analysis often requires delineating regions of interest around each tumor by hand, which complicates quantification in the case of mice bearing multiple tumors. In this work, we propose to use Non-Negative Matrix Factorization with data-adaptive sparsity constraints to enable automated separation of signals emitted from multiple tumors in mice. Results are presented on a set of 18 long-exposure acquisitions.