An automated and simple method for brain MR image extraction
2011

Automated Brain MR Image Extraction Method

Sample size: 10 publication Evidence: moderate

Author Information

Author(s): Zhang Haiyan, Liu Jiafeng, Zhu Zixin, Li Haiyun

Primary Institution: Capital Medical University

Hypothesis

Can an improved geometric active contour model provide an efficient and accurate method for brain extraction from MR images?

Conclusion

The proposed method can provide automated and accurate brain extraction results with high efficiency.

Supporting Evidence

  • The method was compared to manual segmentation results and two popular methods, showing improved efficiency.
  • It effectively addresses boundary leakage and intensity inhomogeneity issues in MR images.
  • The algorithm was implemented on a standard PC and tested on 10 normal T1 MR brain images.

Takeaway

This study created a computer program that can automatically find and separate the brain from other parts in MRI pictures, making it easier and faster to analyze brain images.

Methodology

The method uses an improved geometric active contour model to extract brain regions from MR images, applying a binary level set function and local region-based signed pressure force.

Limitations

The method was only tested on normal adult MRI brain data sets, and further testing is needed on larger and more diverse samples.

Participant Demographics

Normal adult MRI brain data sets were used.

Digital Object Identifier (DOI)

10.1186/1475-925X-10-81

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication