The differential count and analysis of blood cells in microscope images can provide useful information concerning the health of patients. There are three major blood cell types, namely, erythrocytes (RBCs), leukocytes (WBCs), and platelets. Automated blood cell analysers can provide RBCs, WBCs and platelets count but the presence of abnormal cells could affect the cells counting, that should be checked manually. This is why today the conventional practice for such procedure is executed manually by pathologists under light microscope. However, the manual visual inspection is tedious, time consuming, repetitive and it is strongly influenced by the operator's capabilities and tiredness. Therefore, a good clinical decision support system for cells counting and classification has always become a necessity. Few examples of automated systems that can analyse and classify blood cells have been reported in the literature. This research proposes a computer-aided systems that simulates a human visual inspection to automate the process of detection and identification of WBCs and RBCs from blood smear images. The proposed method has been tested on public datasets of blood cell images and demonstrates a reliable and effective system for differential counting, obtaining an average accuracy value of 99.2% for WBCs and 98% for RBCs, outperforming the state-of-the-art.

A computer-aided system for differential count from peripheral blood cell images

LODDO, ANDREA;PUTZU, LORENZO;DI RUBERTO, CECILIA;FENU, GIANNI
2017-01-01

Abstract

The differential count and analysis of blood cells in microscope images can provide useful information concerning the health of patients. There are three major blood cell types, namely, erythrocytes (RBCs), leukocytes (WBCs), and platelets. Automated blood cell analysers can provide RBCs, WBCs and platelets count but the presence of abnormal cells could affect the cells counting, that should be checked manually. This is why today the conventional practice for such procedure is executed manually by pathologists under light microscope. However, the manual visual inspection is tedious, time consuming, repetitive and it is strongly influenced by the operator's capabilities and tiredness. Therefore, a good clinical decision support system for cells counting and classification has always become a necessity. Few examples of automated systems that can analyse and classify blood cells have been reported in the literature. This research proposes a computer-aided systems that simulates a human visual inspection to automate the process of detection and identification of WBCs and RBCs from blood smear images. The proposed method has been tested on public datasets of blood cell images and demonstrates a reliable and effective system for differential counting, obtaining an average accuracy value of 99.2% for WBCs and 98% for RBCs, outperforming the state-of-the-art.
2017
978-150905698-9
File in questo prodotto:
File Dimensione Formato  
SITIS_2016_open.pdf

Solo gestori archivio

Tipologia: versione post-print
Dimensione 2.18 MB
Formato Adobe PDF
2.18 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11584/184115
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 20
  • ???jsp.display-item.citation.isi??? 13
social impact