Related Experiment Video
Updated: May 10, 2026
04:25
Manual Segmentation of the Human Choroid Plexus Using Brain MRI
Published on: December 15, 2023
Automatic segmentation of brain MR images using an adaptive balloon snake model with fuzzy classification
Hung-Ting Liu1, Tony W H Sheu, Herng-Hua Chang
1Computational Biomedical Engineering Laboratory (CBEL), Department of Engineering Science and Ocean Engineering, National Taiwan University, 1, Sec. 4, Roosevelt Road, Daan, 10617, Taipei, Taiwan.
Medical & Biological Engineering & Computing
|June 8, 2013
Summary
This study introduces an adaptive balloon snake (ABS) model for precise skull-stripping in brain MR images. The novel hybrid approach accurately segments brain boundaries, outperforming existing methods.
Area of Science:
- Medical Image Analysis
- Computational Neuroscience
- Biomedical Engineering
Background:
- Skull-stripping is a critical preprocessing step for magnetic resonance (MR) image analysis.
- Accurate brain extraction is essential for subsequent quantitative studies and diagnostics.
Purpose of the Study:
- To develop and evaluate a novel hybrid skull-stripping algorithm for brain MR images.
- To improve the accuracy and robustness of brain segmentation compared to existing methods.
Main Methods:
- A hybrid algorithm combining fuzzy possibilistic c-means (FPCM) clustering and an adaptive balloon snake (ABS) model.
- FPCM provides initial brain boundary delineation, followed by ABS contour evolution for refined segmentation.
- Slice-by-slice segmentation applied across the entire MR image volume.
Main Results:
- The proposed ABS algorithm demonstrated accurate brain segmentation on diverse MR datasets.
- Quantitative evaluation using four similarity metrics showed higher conformity scores compared to state-of-the-art methods.
- The method successfully captured clear and precise brain boundaries.
Conclusions:
- The adaptive balloon snake (ABS) model offers a promising and effective solution for skull-stripping in brain MR imaging.
- This technique holds potential for various applications in medical image analysis and research studies.
- The hybrid approach enhances segmentation accuracy and reliability.
