Multi Features Based Approach for White Blood Cells Segmentation and Classification in Peripheral Blood and Bone Marrow Images

Mohammed Lamine Benomar (1) , Amine M. Chikh (1) , Xavier Descombes (2) , Mourtada Benazzouz (1)

1 GBM - Laboratoire Génie BioMédical [Tlemcen]
2 MORPHEME - Morphologie et Images

This paper proposes a complete automated analysis system for white blood cells differential count in peripheral blood and bone marrow images in order to reduce the time and increase the accuracy of several blood disorders diagnosis. A new color transformation is proposed to highlight the white blood cells regions then a marker controlled watershed algorithm is used to segment the region we are interested in by introducing this transformation. The nucleus and cytoplasm are subsequently separated. In the identification step a set of color, texture and morphological features are extracted from both nucleus and cytoplasm regions. Next, the performances of the random forest classifier on a set of microscopic images are compared and evaluated. The provided results reveal high recognition accuracies for both segmentation and classification stage.

Mots clés: cells segmentation; peripheral blood images; morphological features; cells classification; texture features; white blood cells; color transformation; bone marrow images

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]; Intelligence artificielle [cs.AI]; Bio-informatique [q-bio.QM]; Imagerie médicale; Traitement du signal et de l'image [eess.SP]

Mohammed Lamine Benomar, Amine M. Chikh, Xavier Descombes, Mourtada Benazzouz. Multi Features Based Approach for White Blood Cells Segmentation and Classification in Peripheral Blood and Bone Marrow Images. 2019. ⟨hal-02279352v1⟩