Leukemic cells segmentation algorithm based on molecular spectral imaging technology

Qingli Li, Chunni Dai, Hongjing Liu, Jingao LiuProceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE 2009 · DOI

Abstract

A molecular spectral imaging system instead of common microscope was used to capture the spectral images of blood smears. Then an improved spectral angle mapper algorithm for automatic blood cells segmentation was presented. In this algorithm, the spectral vectors of blood cells were normalized first. Then the spectral angles of all bands and partial bands were calculated respectively. Finally, the blood cells were segmented according to the spectral angles combined with the threshold segmentation method. As a case study, the leukemia cells were selected as the target and segmented with the new algorithm. The results demonstrate that this algorithm can utilizes both spectral and spatial information of blood cells and segment the leukemia cells more accurately.
BibTeX
@inproceedings{li2009leukemic,
  author = {Qingli Li and Chunni Dai and Hongjing Liu and Jingao Liu},
  title = {{Leukemic cells segmentation algorithm based on molecular spectral imaging technology}},
  booktitle = {Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE},
  year = {2009},
  doi = {10.1117/12.830539},
}

Loading related content...

Figure