Related Experiment Video
Updated: Apr 23, 2026
09:31
Automated Quantification of Hematopoietic Cell – Stromal Cell Interactions in Histological Images of Undecalcified Bone
Published on: April 8, 2015
10.5K
White blood cell segmentation by color-space-based k-means clustering
Congcong Zhang1, Xiaoyan Xiao2, Xiaomei Li3
1School of Information Science and Engineering, Shandong University, Jinan 250100, China. zhangcongcong@mail.sdu.edu.cn.
Sensors (Basel, Switzerland)
|September 27, 2014
Summary
This study introduces a new method for segmenting white blood cells (WBCs) in blood smear images for cytometry. The novel approach achieves high accuracy in identifying both the nucleus and cytoplasm of WBCs.
Area of Science:
- Medical Imaging
- Computational Biology
- Hematology
Background:
- Accurate white blood cell (WBC) segmentation is crucial for cytometry.
- Challenges include diverse WBC morphology and complex backgrounds in blood smear images.
Purpose of the Study:
- To propose a novel method for nucleus and cytoplasm segmentation of WBCs.
- To improve the accuracy of WBC segmentation in microscopic blood smear images.
Main Methods:
- A color adjustment step was applied prior to segmentation.
- Segmentation was achieved by combining color space decomposition and k-means clustering.
- The method was evaluated on a database of 300 microscopic blood smear images.
Main Results:
- The proposed method achieved 95.7% overall accuracy for nucleus segmentation.
- The method achieved 91.3% overall accuracy for cytoplasm segmentation.
- Experimental results confirm effective and accurate WBC segmentation.
Conclusions:
- The novel segmentation method effectively segments WBCs with high accuracy.
- The approach addresses challenges posed by WBC morphological diversity and image background complexity.
- This technique shows promise for enhancing automated cytometry analysis.
