Retrospective T2 quantification from conventional weighted MRI of the prostate based on deep learning

Prostate cancer (PCa) is one of the most common types of cancer with a considerable morbidity and mortality. Multiparametric MRI as a noninvasive imaging tool in PCa diagnosis has limitations. Recent studies suggest that quantitative T2 information is helpful in PCa diagnosis and lesion characterization but is not generally available due to the need for additional scans. Here, we developed a DL-based method to estimate T2 maps retrospectively from clinically acquired T1- and T2-weighted images. The developed technique has the potential to improve PCa diagnosis and lesion characterization using quantitative T2 information estimated from conventional clinical scans.