Development of a computer aided diagnosis model for prostate cancer classification on multi-parametric MRI

Introduction: Prostate cancer (PCa) is one of the most prevalent cancers among men. Diagnosis depends on a trans-rectal ultrasound (TRUS)-guided biopsy to estimate the stage and aggressiveness. The accuracy of this estimate is confounded by a high false negative rate due to a lack of consistent imaging characteristics that make the identification possible in a majority of cases and consequent use of a universal sextant needle targeting scheme for all patients. Multi-parametric magnetic resonance imaging (mpMRI) maps the prostate in 3D, but is relatively complex to interpret and suffers from inter-observer variability in lesion localization and scoring. Computer-aided diagnosis (CAD) systems have been developed as a solution as they have the power to perform deterministic quantitative image analysis. We measured the accuracy of such a system validated using accurately co-registered whole-mount digitized histology [1].