University of Minnesota

Christopher A Warlick

Gregory John Metzger

Stephen C Schmechel

Joseph S Koopmeiners

Chaitanya Kalavagunta

A user-independent, quantitative, multiparametric MRI model is developed and validated on co-registered correlative histopathology, yielding improved performance for cancer detection over single parameter estimators. A computing device may be configured to receive a first parametric map that maps imaged tissue of a patient using values of a first parameter, and a second parametric map that maps the imaged tissue using values of a second parameter, wherein the parametric maps are generated from medical imaging data for the imaged tissue. The computing device may be further configured to apply a multiparametric model to the maps to generate at least one Composite Biomarker Score for the tissue, the model being a function of the first parameter and the second parameter. The function may be determined based on co-registered histopathology data. The computing device may be further configured to generate an indication of whether the tissue includes predicted cancer, and output the indication.

Growing community of inventors

Lake Elmo, MN, United States of America

Christopher A Warlick