Level set segmentation of bovine corpora lutea in ex situ ovarian ultrasound images
2008

Detecting Bovine Corpus Lutea Boundaries Using Ultrasound Images

Sample size: 8 publication 10 minutes Evidence: moderate

Author Information

Author(s): Rusnell Brennan J, Pierson Roger A, Singh Jaswant, Adams Gregg P, Eramian Mark G

Primary Institution: University of Saskatchewan

Hypothesis

Bovine CL boundaries could be located within 1–2 mm by a level set image segmentation methodology.

Conclusion

The technique is promising for accurately locating CL boundaries, although some deviations can occur.

Supporting Evidence

  • The mean absolute distance (MAD) was 0.87 mm, indicating good accuracy.
  • Mean sensitivity was 0.814, showing the method often under-segments CLs.
  • Mean specificity was 0.990, indicating high accuracy in identifying non-CL regions.

Takeaway

This study shows a way to find the edges of a part of a cow's ovary using special computer techniques on ultrasound pictures.

Methodology

The study used level set methods to segment CL boundaries from ultrasound images, comparing results to manually delineated ground truth.

Limitations

The method may under-segment CLs and is sensitive to image noise.

Participant Demographics

Images were obtained from the ovaries of heifers.

Digital Object Identifier (DOI)

10.1186/1477-7827-6-33

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication