Related Experiment Video
Updated: Jun 2, 2026
06:08
A Cognitive Fusion-guided Prostate Biopsy Using Multiparametric Magnetic Resonance Imaging and Transrectal Ultrasound
Published on: March 21, 2025
Biopsy needle detection in transrectal ultrasound
Alper Ayvaci1, Pingkun Yan, Sheng Xu
1University of California, Los Angeles, CA 90095, USA. ayvaci@cs.ucla.edu
Summary
This study presents an automated method to detect and segment biopsy needles in transrectal ultrasound (TRUS) videos. This technique enhances the precision of MRI/TRUS fusion guided prostate biopsies for improved clinical outcomes.
Area of Science:
- Medical Imaging
- Surgical Technology
- Computational Biology
Background:
- MRI/TRUS fusion guided prostate biopsy offers improved outcomes compared to TRUS alone.
- Accurate localization of the biopsy needle within the TRUS video is critical for precision during fusion guided procedures.
Purpose of the Study:
- To develop and validate an automated algorithm for detecting and segmenting biopsy needles in transrectal ultrasound (TRUS) videos.
- To enhance the accuracy and reliability of MRI/TRUS fusion guided prostate biopsies.
Main Methods:
- A novel algorithm combining ultrasound probe stability, TRUS video background modeling, and prior knowledge of needle orientation and position was developed.
- The algorithm was tested on over 25,000 frames from TRUS video sequences.
Main Results:
- The proposed algorithm successfully detected and segmented biopsy needle deployments with high accuracy.
- A low false-positive detection rate was achieved, indicating the robustness of the method.
Conclusions:
- Automated biopsy needle detection and segmentation in TRUS is feasible and accurate.
- This technology has the potential to improve the safety and efficacy of MRI/TRUS fusion guided prostate biopsies.
