Title :
Leukocyte segmentation and classification in blood-smear images
Author :
Ramoser, Herbert ; Laurain, Vincent ; Bischof, Horst ; Ecker, Rupert
Author_Institution :
Adv. Comput. Vision GmbH, Wien
Abstract :
The detection and classification of leukocytes in blood smear images is a routine task in medical diagnosis. In this paper we present a fully automated approach to leukocyte segmentation that is robust with respect to cell appearance and image quality. A set of features is used to describe cytoplasm and nucleus properties. Pairwise SVM classification is used to discriminate between different cell types. Evaluation on a set of 1166 images (13 classes) resulted in 95% correct segmentations and 75% to 99% correct classification (with reject option)
Keywords :
biomedical optical imaging; blood; cellular biophysics; image classification; image segmentation; medical image processing; support vector machines; blood-smear images; cell appearance; cytoplasm; image quality; leukocyte classification; leukocyte segmentation; medical diagnosis; nucleus; pairwise SVM classification; Cells (biology); Computer graphics; Computer vision; Image quality; Image segmentation; Robustness; Shape; Support vector machine classification; Support vector machines; White blood cells;
Conference_Titel :
Engineering in Medicine and Biology Society, 2005. IEEE-EMBS 2005. 27th Annual International Conference of the
Conference_Location :
Shanghai
Print_ISBN :
0-7803-8741-4
DOI :
10.1109/IEMBS.2005.1617200
