Temporal Enhanced Ultrasound (TeUS), comprising a time series of ultrasound images, has been reported as an alternative non-invasive tissue characterization technique. TeUS utilizes an underlying machine learning framework to extract information from the backscattered ultrasound data obtained in a time span of few seconds without any imposed mechanical excitation. The time series of such data, analyzed by the TeUS framework, is tissue specific. In this project, we develop an accurate approach for detecting PCa from TeUS data collected during MRI-TRUS guided biopsy. We utilize deep recurrent neural networks to explicitly model the temporal information of TeUS. The clinical motivation of this work is to enable large-scale deployment of the TeUS technology on clinical ultrasound devices. The current approach will enable accurate, automatic, and real-time implementation of TeUS tissue characterization. This is a collaborative project with NIH, University of British Columbia, and Queen’s University.