Biopsy needle detection in transrectal ultrasound

Abstract

Using the fusion of pre-operative MRI and real time intra-procedural transrectal ultrasound (TRUS) to guide prostate biopsy has been shown as a very promising approach to yield better clinical outcome than the routinely performed TRUS only guided biopsy. In several situations of the MRI/TRUS fusion guided biopsy, it is important to know the exact location of the deployed biopsy needle, which is imaged in the TRUS video. In this paper, we present a method to automatically detect and segment the biopsy needle in TRUS. To achieve this goal, we propose to combine information from multiple resources, including ultrasound probe stability, TRUS video background model, and the prior knowledge of needle orientation and position. The proposed algorithm was tested on TRUS video sequences which have in total more than 25,000 frames. The needle deployments were successfully detected and segmented in the sequences with high accuracy and low false-positive detection rate.