Related Experiment Video
Updated: May 15, 2026
09:11
Use of MRI-ultrasound Fusion to Achieve Targeted Prostate Biopsy
Published on: April 9, 2019
Rotational-slice-Based prostate segmentation using level set with shape constraint for 3D end-firing TRUS guided
Wu Qiu1, Jing Yuan, Eranga Ukwatta
1Imaging Research Laboratories, Robarts Research Institute, 100 Perth, London, Ontario, Canada, N6A 5k8. WQiu@imaging.robarts.ca
Medical Image Computing and Computer-Assisted Intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
|January 5, 2013
Summary
This study presents a semi-automatic method for prostate segmentation in 3D ultrasound images, crucial for biopsy planning. The novel approach achieved high accuracy, with a 93.39% volume overlap ratio, improving prostate cancer treatment.
Area of Science:
- Medical Imaging
- Biomedical Engineering
- Computational Anatomy
Background:
- Accurate prostate segmentation in 3D ultrasound is vital for transrectal ultrasound (TRUS) guided prostate biopsy.
- Existing methods may lack precision or require extensive manual input.
Purpose of the Study:
- To develop and validate a semi-automatic prostate segmentation method for 3D TRUS images.
- To improve the accuracy and efficiency of prostate segmentation for biopsy planning.
Main Methods:
- Integration of a modified distance regularization level set formulation with shape constraints.
- Application to a rotational-slice-based 3D prostate segmentation technique.
- Quantitative validation using metrics like volume overlap ratio and mean absolute surface distance.
Main Results:
- Achieved a high volume overlap ratio of 93.39% +/- 1.26%.
- Demonstrated a mean absolute surface distance of 1.16 mm +/- 0.34 mm.
- Performance validated against expert delineations on twenty 3D patient prostate images.
Conclusions:
- The proposed semi-automatic method offers accurate and reliable prostate segmentation in 3D ultrasound.
- This technique can enhance the precision of TRUS-guided prostate biopsies.
- The integration of level sets and shape constraints shows significant potential for medical image segmentation.
