A deep learning method for counting white blood cells in bone marrow images

Abstract Background Differentiating and counting various types of white blood cells (WBC) in bone marrow smears allows the detection of infection, anemia, and leukemia or analysis of a process of treatment. However, manually locating, identifying, and counting the different classes of WBC is time-co...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Da Wang, Maxwell Hwang, Wei-Cheng Jiang, Kefeng Ding, Hsiao Chien Chang, Kao-Shing Hwang
Formato:	article
Lenguaje:	EN
Publicado:	BMC 2021
Materias:	Medical image Leukemia Deep learning Object detection Classification Computer applications to medicine. Medical informatics R858-859.7 Biology (General) QH301-705.5
Acceso en línea:	https://doaj.org/article/de6a87efa12f47cbb4c7d1d6e335f8ff
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:de6a87efa12f47cbb4c7d1d6e335f8ff
record_format	dspace
spelling	oai:doaj.org-article:de6a87efa12f47cbb4c7d1d6e335f8ff2021-11-14T12:12:57ZA deep learning method for counting white blood cells in bone marrow images10.1186/s12859-021-04003-z1471-2105https://doaj.org/article/de6a87efa12f47cbb4c7d1d6e335f8ff2021-11-01T00:00:00Zhttps://doi.org/10.1186/s12859-021-04003-zhttps://doaj.org/toc/1471-2105Abstract Background Differentiating and counting various types of white blood cells (WBC) in bone marrow smears allows the detection of infection, anemia, and leukemia or analysis of a process of treatment. However, manually locating, identifying, and counting the different classes of WBC is time-consuming and fatiguing. Classification and counting accuracy depends on the capability and experience of operators. Results This paper uses a deep learning method to count cells in color bone marrow microscopic images automatically. The proposed method uses a Faster RCNN and a Feature Pyramid Network to construct a system that deals with various illumination levels and accounts for color components' stability. The dataset of The Second Affiliated Hospital of Zhejiang University is used to train and test. Conclusions The experiments test the effectiveness of the proposed white blood cell classification system using a total of 609 white blood cell images with a resolution of 2560 × 1920. The highest overall correct recognition rate could reach 98.8% accuracy. The experimental results show that the proposed system is comparable to some state-of-art systems. A user interface allows pathologists to operate the system easily.Da WangMaxwell HwangWei-Cheng JiangKefeng DingHsiao Chien ChangKao-Shing HwangBMCarticleMedical imageLeukemiaDeep learningObject detectionClassificationComputer applications to medicine. Medical informaticsR858-859.7Biology (General)QH301-705.5ENBMC Bioinformatics, Vol 22, Iss S5, Pp 1-14 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medical image Leukemia Deep learning Object detection Classification Computer applications to medicine. Medical informatics R858-859.7 Biology (General) QH301-705.5
spellingShingle	Medical image Leukemia Deep learning Object detection Classification Computer applications to medicine. Medical informatics R858-859.7 Biology (General) QH301-705.5 Da Wang Maxwell Hwang Wei-Cheng Jiang Kefeng Ding Hsiao Chien Chang Kao-Shing Hwang A deep learning method for counting white blood cells in bone marrow images
description	Abstract Background Differentiating and counting various types of white blood cells (WBC) in bone marrow smears allows the detection of infection, anemia, and leukemia or analysis of a process of treatment. However, manually locating, identifying, and counting the different classes of WBC is time-consuming and fatiguing. Classification and counting accuracy depends on the capability and experience of operators. Results This paper uses a deep learning method to count cells in color bone marrow microscopic images automatically. The proposed method uses a Faster RCNN and a Feature Pyramid Network to construct a system that deals with various illumination levels and accounts for color components' stability. The dataset of The Second Affiliated Hospital of Zhejiang University is used to train and test. Conclusions The experiments test the effectiveness of the proposed white blood cell classification system using a total of 609 white blood cell images with a resolution of 2560 × 1920. The highest overall correct recognition rate could reach 98.8% accuracy. The experimental results show that the proposed system is comparable to some state-of-art systems. A user interface allows pathologists to operate the system easily.
format	article
author	Da Wang Maxwell Hwang Wei-Cheng Jiang Kefeng Ding Hsiao Chien Chang Kao-Shing Hwang
author_facet	Da Wang Maxwell Hwang Wei-Cheng Jiang Kefeng Ding Hsiao Chien Chang Kao-Shing Hwang
author_sort	Da Wang
title	A deep learning method for counting white blood cells in bone marrow images
title_short	A deep learning method for counting white blood cells in bone marrow images
title_full	A deep learning method for counting white blood cells in bone marrow images
title_fullStr	A deep learning method for counting white blood cells in bone marrow images
title_full_unstemmed	A deep learning method for counting white blood cells in bone marrow images
title_sort	deep learning method for counting white blood cells in bone marrow images
publisher	BMC
publishDate	2021
url	https://doaj.org/article/de6a87efa12f47cbb4c7d1d6e335f8ff
work_keys_str_mv	AT dawang adeeplearningmethodforcountingwhitebloodcellsinbonemarrowimages AT maxwellhwang adeeplearningmethodforcountingwhitebloodcellsinbonemarrowimages AT weichengjiang adeeplearningmethodforcountingwhitebloodcellsinbonemarrowimages AT kefengding adeeplearningmethodforcountingwhitebloodcellsinbonemarrowimages AT hsiaochienchang adeeplearningmethodforcountingwhitebloodcellsinbonemarrowimages AT kaoshinghwang adeeplearningmethodforcountingwhitebloodcellsinbonemarrowimages AT dawang deeplearningmethodforcountingwhitebloodcellsinbonemarrowimages AT maxwellhwang deeplearningmethodforcountingwhitebloodcellsinbonemarrowimages AT weichengjiang deeplearningmethodforcountingwhitebloodcellsinbonemarrowimages AT kefengding deeplearningmethodforcountingwhitebloodcellsinbonemarrowimages AT hsiaochienchang deeplearningmethodforcountingwhitebloodcellsinbonemarrowimages AT kaoshinghwang deeplearningmethodforcountingwhitebloodcellsinbonemarrowimages
_version_	1718429376854360064

A deep learning method for counting white blood cells in bone marrow images

Ejemplares similares