Multiresolution Analysis Using Wavelet, Ridgelet, and Curvelet Transforms for Medical Image Segmentation
2011

Improving Medical Image Segmentation with Curvelet Transform

publication Evidence: moderate

Author Information

Author(s): Shadi AlZubi, Islam Naveed, Abbod Maysam

Primary Institution: Brunel University

Hypothesis

Can multiresolution analysis using wavelet, ridgelet, and curvelet transforms improve the segmentation of medical images?

Conclusion

The study found that curvelet transform significantly enhances the classification of abnormal tissues in medical scans while reducing noise.

Supporting Evidence

  • Curvelet transform provides better segmentation results compared to wavelet and ridgelet transforms.
  • Curvelet transform effectively captures curved edges in medical images.
  • Segmentation using curvelet transform resulted in lower error percentages for small tumors.

Takeaway

This study shows that using special math tools called curvelets can help doctors see and understand medical images better, especially when looking for cancer.

Methodology

The study used multiresolution analysis techniques, applying wavelet, ridgelet, and curvelet transforms to segment medical images from CT scans.

Limitations

The ridgelet transform was less effective for medical images that do not contain strong linear features.

Digital Object Identifier (DOI)

10.1155/2011/136034

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication