Semi-Automatic Integrated Segmentation Approaches and Contour Extraction Applied to Computed Tomography Scan Images
2008

Segmentation and Contour Extraction of CT Scan Images for Traumatic Brain Injuries

Sample size: 5 publication Evidence: moderate

Author Information

Author(s): B. Dhalila S. Y. Khoodoruth, Rughooputh Harry C. S., Lefer Wilfrid

Primary Institution: University of Pau and Pays de l'Adour

Hypothesis

We propose to segment two-dimensional CT scans of traumatic brain injuries using various methods.

Conclusion

The new computational pipeline technique effectively segments features in CT scans, demonstrating reliability for diagnostic or presurgery purposes.

Supporting Evidence

  • The proposed methods include bilateral filtering and diffusion properties for better contour extraction.
  • Segmentation is crucial for pre-surgery planning and diagnostic purposes.
  • Different segmentation approaches yield varying results based on the characteristics of the lesions.

Takeaway

This study shows how to use computer techniques to help doctors see and understand brain injuries better in CT scans.

Methodology

The study uses hybrid, feature extraction, level sets, region growing, and watershed methods for segmentation and contour extraction.

Limitations

The segmentation results may vary based on the constraints applied and the characteristics of the lesions.

Participant Demographics

CT scans obtained from 5 patients with various traumatic brain injuries.

Digital Object Identifier (DOI)

10.1155/2008/759354

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication