Related Experiment Video
Updated: Jun 18, 2026
09:11
Use of MRI-ultrasound Fusion to Achieve Targeted Prostate Biopsy
Published on: April 9, 2019
Unsupervised segmentation of the prostate using MR images based on level set with a shape prior
Xin Liu1, D L Langer, M A Haider
1Medical Imaging Research Center, Illinois Institute of Technology, Chicago, IL, USA.
Summary
This study presents an automated prostate segmentation method using MRI. The technique accurately identifies prostate boundaries, aiding in cancer diagnosis and treatment planning.
Area of Science:
- Medical Imaging
- Oncology
- Computer Vision
Background:
- Prostate cancer is a leading cause of cancer death in men.
- Accurate prostate segmentation in MRI is crucial for diagnosis and treatment planning.
- Current methods often require manual input, limiting efficiency.
Purpose of the Study:
- To develop a fully automatic method for prostate segmentation using MRI.
- To improve the accuracy and efficiency of prostate localization for clinical applications.
Main Methods:
- A deformable ellipse model is used to approximate the prostate shape.
- Level set evolution is initiated and constrained by the ellipse model.
- Post-processing techniques refine the segmented prostate boundaries.
Main Results:
- The proposed method achieves accurate prostate segmentation on diffusion-weighted MRI (DWI).
- Segmentation results demonstrate comparable or superior performance to human readers.
- The automated approach facilitates tumor localization for biopsy and radiotherapy planning.
Conclusions:
- The developed automated segmentation method is effective for prostate MRI.
- This technique offers a promising tool for enhancing prostate cancer management.
- Further validation on diverse datasets will confirm its clinical utility.
