Sensors · 2014 · 141 citations · 20 references
MedicineBiomedical EngineeringPathologyBiomedical ImagingComputer VisionCytopathologyCytologyImage SegmentationMedical Image AnalysisMicroscopic Cell MorphologyAccuracyCell Nucleus DetectionCell SegmentationColor SegmentationK-means ClusteringSegmentationSegmentation By ColorWhite Blood Cell Morphology
White blood cell (WBC) segmentation, crucial for cytometry, is difficult due to the morphological diversity of WBCs and the complex, uncertain background of blood smear images. The study proposes a novel method for nucleus and cytoplasm segmentation of WBCs to aid cytometry. The method employs a color adjustment step, followed by color‑space decomposition and k‑means clustering, and its performance was evaluated on a database of 300 microscopic blood smear images. It achieved 95.7 % accuracy for nucleus segmentation and 91.3 % for cytoplasm segmentation, demonstrating effective high‑accuracy WBC segmentation.
White blood cell (WBC) segmentation, which is important for cytometry, is a challenging issue because of the morphological diversity of WBCs and the complex and uncertain background of blood smear images. This paper proposes a novel method for the nucleus and cytoplasm segmentation of WBCs for cytometry. A color adjustment step was also introduced before segmentation. Color space decomposition and k-means clustering were combined for segmentation. A database including 300 microscopic blood smear images were used to evaluate the performance of our method. The proposed segmentation method achieves 95.7% and 91.3% overall accuracy for nucleus segmentation and cytoplasm segmentation, respectively. Experimental results demonstrate that the proposed method can segment WBCs effectively with high accuracy.
20
Erik Reinhard, M. Adhikhmin, Bryan N S Gooch et al. · IEEE Computer Graphics and Applications · 2001 · 3K citations
Arts, Vision Science, Color Theory +10