Related Experiment Video
Updated: Dec 18, 2025
08:40
Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging
Published on: April 8, 2016
13.3K
A semiautomatic approach for prostate segmentation in MR images using local texture classification and statistical
Maysam Shahedi1, Martin Halicek1,2, Qinmei Li1,3
1Department of Bioengineering, The University of Texas at Dallas, Richardson, TX.
Summary
This study introduces a fast, accurate 3D prostate segmentation method using shape and texture analysis on MR images. The semiautomated technique achieves accuracy comparable to expert variability, improving image-guided treatment planning.
Area of Science:
- Medical Imaging
- Computer-Aided Diagnosis
- Biomedical Engineering
Background:
- Manual prostate segmentation in MRI is time-consuming and prone to inter-observer variability.
- Accurate segmentation is crucial for image-guided procedures like biopsy and focal therapy.
Purpose of the Study:
- To develop a semiautomated 3D prostate segmentation technique for T2-weighted MR images.
- To improve accuracy and efficiency in prostate segmentation for clinical applications.
Main Methods:
- Proposed a semiautomated 3D segmentation technique using shape and texture analysis.
- Employed statistical point distribution modeling for prostate shape variation.
- Utilized local texture differences between prostate and surrounding tissues.
Main Results:
- Achieved segmentation accuracy within inter-expert variability (MAD: 1.4 ± 0.4 mm, HDist: 8.5 ± 2.0 mm, DSC: 86 ± 3%).
- Demonstrated fast, accurate, and robust performance on a test set of 14 MR images.
- Results were comparable to the best reported methods in the literature.
Conclusions:
- The proposed algorithm offers a significant improvement over manual segmentation for 3D prostate MRI.
- This technique has the potential to enhance the precision and efficiency of prostate cancer treatment planning.
- The method's accuracy and robustness make it suitable for clinical integration.
