Framework for White Blood Cell Segmentation Using Digital Image Processing
Author Information
Author(s): Sadeghian Farnoosh, Seman Zainina, Ramli Abdul Rahman, Abdul Kahar Badrul Hisham, Saripan M-Iqbal
Primary Institution: Universiti Putra Malaysia
Hypothesis
The study aims to segment white blood cells into their nucleus and cytoplasm using a proposed digital image processing framework.
Conclusion
The proposed framework achieved 92% accuracy for nucleus segmentation and 78% for cytoplasm segmentation.
Supporting Evidence
- The framework managed to obtain 92% accuracy for nucleus segmentation.
- The cytoplasm segmentation accuracy was found to be 78%.
- The method provides useful information about WBC maturation status.
Takeaway
This study created a method to help doctors see parts of white blood cells better, which can help them find diseases like leukemia.
Methodology
The study used digital image processing techniques to segment the nucleus and cytoplasm of white blood cells from microscopic images.
Limitations
The method was applied to sub-images, which may limit its effectiveness in fully automated segmentation.
Participant Demographics
The study focused on blood images from acute leukemia cases type L2.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website