An Efficient Multi-Level Convolutional Neural Network Approach for White Blood Cells Classification

Vista sencilla de ítem
dc.contributor.authorCheuque, C.
dc.contributor.authorQuerales, M.
dc.contributor.authorLeón, R.
dc.contributor.authorSalas, R.
dc.contributor.authorTorres, R.
dc.date.accessioned2022-08-05T13:59:56Z
dc.date.available2022-08-05T13:59:56Z
dc.date.issued2022-02
dc.descriptionIndexación: Scopus.es
dc.description.abstractThe evaluation of white blood cells is essential to assess the quality of the human immune system; however, the assessment of the blood smear depends on the pathologist’s expertise. Most machine learning tools make a one-level classification for white blood cell classification. This work presents a two-stage hybrid multi-level scheme that efficiently classifies four cell groups: lymphocytes and monocytes (mononuclear) and segmented neutrophils and eosinophils (polymorphonuclear). At the first level, a Faster R-CNN network is applied for the identification of the region of interest of white blood cells, together with the separation of mononuclear cells from polymorphonuclear cells. Once separated, two parallel convolutional neural networks with the MobileNet structure are used to recognize the subclasses in the second level. The results obtained using Monte Carlo cross-validation show that the proposed model has a performance metric of around 98.4% (accuracy, recall, precision, and F1-score). The proposed model represents a good alternative for computer-aided diagnosis (CAD) tools for supporting the pathologist in the clinical laboratory in assessing white blood cells from blood smear images.es
dc.description.urihttps://www.mdpi.com/2075-4418/12/2/248
dc.identifier.citationDiagnostics, Volume 12, Issue 2, February 2022, Article number 248es
dc.identifier.doi10.3390/diagnostics12020248
dc.identifier.issn2075-4418
dc.identifier.urihttps://repositorio.unab.cl/xmlui/handle/ria/23460
dc.language.isoenes
dc.publisherMDPIes
dc.rights.licenseAttribution 4.0 International (CC BY 4.0)
dc.rights.urihttps://www.mdpi.com/openaccess
dc.subjectDeep learninges
dc.subjectMulti-level classificationes
dc.subjectMultisource datasetses
dc.subjectWhite blood cells classificationes
dc.titleAn Efficient Multi-Level Convolutional Neural Network Approach for White Blood Cells Classificationes
dc.typeArtículoes
Archivos
Bloque original
Mostrando 1 - 1 de 1
Miniatura
Nombre:
Cheuque_An Efficient Multi-Level Convolutional Neural Network Approach for White Blood Cells Classification.pdf
Tamaño:
1.89 MB
Formato:
Adobe Portable Document Format
Descripción:
TEXTO COMPLETO EN INGLES
Descargar
Bloque de licencias
Mostrando 1 - 1 de 1
No hay miniatura disponible
Nombre:
license.txt
Tamaño:
1.71 KB
Formato:
Item-specific license agreed upon to submission
Descripción:
Descargar
Colecciones
FIng - Artículos de Revista