Related Experiment Video
Updated: Jun 8, 2026
09:11
Use of MRI-ultrasound Fusion to Achieve Targeted Prostate Biopsy
Published on: April 9, 2019
Automatic prostate segmentation using fused ultrasound B-mode and elastography images
S Sara Mahdavi1, Mehdi Moradi, William J Morris
1Department of Electrical and Computer Engineering, University of British Columbia, Vancouver, Canada. saram@ece.ubc.ca
Medical Image Computing and Computer-Assisted Intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
|October 1, 2010
Summary
This study introduces an automatic 2D prostate segmentation algorithm using fused ultrasound and elastography images. Combining mechanical and acoustic data significantly improves segmentation accuracy for better prostate imaging.
Area of Science:
- Medical Imaging
- Biomedical Engineering
- Image Processing
Background:
- Prostate segmentation is crucial for diagnosis and treatment planning.
- Ultrasound (US) and elastography offer complementary information for tissue characterization.
- Accurate segmentation of prostate images remains a challenge, especially with automated methods.
Purpose of the Study:
- To develop and evaluate a fully automatic 2D prostate segmentation algorithm.
- To investigate the benefit of fusing ultrasound and elastography data for improved segmentation.
- To assess the performance of the proposed algorithm against manual segmentation.
Main Methods:
- A novel algorithm fusing B-mode ultrasound and elastography images was developed.
- Active Shape Models were deformed using gray level edge similarity and continuity from both image types.
- The algorithm was tested on 107 transverse prostate images.
Main Results:
- The fused image approach demonstrated improved segmentation compared to using ultrasound alone.
- The automatic segmentation achieved a mean absolute error of 2.6 +/- 0.9 mm.
- The algorithm exhibited a mean running time of 17.9 +/- 12.2 seconds.
Conclusions:
- Fusing ultrasound and elastography data enhances prostate segmentation accuracy.
- The proposed automatic method shows promise for clinical applications.
- This approach provides a foundation for developing advanced 3D segmentation techniques.
