Leukocyte segmentation and classification in blood-smear images

Herbert Ramoser; Vincent Laurain; Horst Bischof; Rupert Ecker

doi:10.1109/IEMBS.2005.1617200

Leukocyte segmentation and classification in blood-smear images

Conf Proc IEEE Eng Med Biol Soc. 2005:2005:3371-4. doi: 10.1109/IEMBS.2005.1617200.

Authors

Herbert Ramoser¹, Vincent Laurain, Horst Bischof, Rupert Ecker

Affiliation

¹ Advanced Computer Vision GmbH - ACV, Donau-City-Strasse 1, 1220 Wien, Austria, Email: [email protected].

PMID: 17280945
DOI: 10.1109/IEMBS.2005.1617200

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).