Multivariate Curve Resolution for Magnetic Resonance Image Analysis: Applications in Prostate Cancer Biomarkers Development

Abstract One current trending topic in medical imaging is imaging biomarkers, which are being developed for early cancer detection in several organs such as lung, breast, liver, colon, prostate, or brain. These imaging biomarkers, which act as indicators of a normal biological process, a disease or a response to a therapeutic intervention, rely on (hard) physiological models; making the interpretation difficult in some cases. In this work, multivariate curve resolution (MCR) is applied on magnetic resonance images from perfusion (dynamic contrast enhanced-magnetic resonance) and diffusion (diffusion weighted-magnetic resonance) sequences, in the case of prostate cancer. MCR provides new imaging biomarkers, complementary to those obtained from theoretical models, to improve clinical diagnosis, as well as an evaluation tool for assessing the appropriateness of theoretical models.