Titre :

Detection and segmentation of erythrocytes in multispectral label-free blood smear images for automatic cell counting

Auteur(s) :

Doumun, Mékapeu Solange [Auteur]
Institut National Polytechnique Félix Houphouët-Boigny [Yamoussoukro] [INP-HB]
Lille économie management - UMR 9221 [LEM]
Laboratoire Paul Painlevé - UMR 8524 [LPP]
Dabo-Niang, Sophie [Auteur]
MOdel for Data Analysis and Learning [MODAL]
Zoueu, Jérémie [Auteur]
Institut National Polytechnique Félix Houphouët-Boigny [Yamoussoukro] [INP-HB]

Titre de la revue :

Journal of Spectral Imaging

Éditeur :

IM Publications

Date de publication :

2020-09-09

Mot(s)-clé(s) en anglais :

multispectral imaging
segmentation
malaria
automatic diagnosis
image analysis

Discipline(s) HAL :

Mathématiques [math]/Statistiques [math.ST]

Résumé en anglais : [en]

In this work we propose an efficient approach to image segmentation for multispectral images of unstained blood films and automatic counting of erythrocytes. Our method takes advantage of Beer–Lambert’s law by using, first, ...
Lire la suite >In this work we propose an efficient approach to image segmentation for multispectral images of unstained blood films and automatic counting of erythrocytes. Our method takes advantage of Beer–Lambert’s law by using, first, a statistical standardisation equation applied to transmittance images, followed by the local adaptive threshold to detect the blood cells and hysteresis contour closing to obtain the complete blood cell boundaries, and finally the watershed algorithm is used. With this method, image pre-processing is not required, which leads to time savings. We obtained the following results that show that our technique is effective, efficient and fast: Precision of 98.47 % and Recall of 98.23 %, a degree of precision (F-Measurement) of 98.34 % and an Accuracy of 96.75 %.Lire moins >

Langue :

Anglais

Comité de lecture :

Oui

Audience :

Internationale

Vulgarisation :

Non

Collections :

• Lille Économie Management (LEM) - UMR 9221

Source :

Harvested from HAL