Bone Marrow Cell Counting Method Based on Fourier Ptychographic Microscopy and Convolutional Neural Network

Xin Wang; Tingfa Xu; Jizhou Zhang; Shushan Wang; Yizhou Zhang; Yiwen Chen; Jinhua Zhang

doi:10.1007/978-981-15-8411-4_92

Bone Marrow Cell Counting Method Based on Fourier Ptychographic Microscopy and Convolutional Neural Network

Xin Wang, Tingfa Xu^*, Jizhou Zhang, Shushan Wang, Yizhou Zhang, Yiwen Chen, Jinhua Zhang

^*此作品的通讯作者

光电学院

Beijing Institute of Technology

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

摘要

In bone marrow examination, the number of bone marrow cells is an essential parameter to judge the degree of myeloproliferative. In this paper, we propose a new bone marrow cell counting method based on Fourier ptychographic microscopy and convolutional neural network. We use Fourier ptychographic microscopy technology to obtain the intensity and phase images of bone marrow cells at first. Then, we combine the intensity and the phase image correspondingly to obtain a dual-channel image. We use the convolutional neural network to extract the characteristics of bone marrow cells in the dual-channel image, which can generate a density map. The number of bone marrow cells is realized by integrating the density map. The experimental results show that both the mean absolute error (MAE = 0.66) and mean square error (MSE = 0.67) of our method are lower than those existing methods.

源语言	英语
主期刊名	Communications, Signal Processing, and Systems - Proceedings of the 9th International Conference on Communications, Signal Processing, and Systems
编辑	Qilian Liang, Wei Wang, Xin Liu, Zhenyu Na, Xiaoxia Li, Baoju Zhang
出版商	Springer Science and Business Media Deutschland GmbH
页	687-693
页数	7
ISBN（印刷版）	9789811584107
DOI	https://doi.org/10.1007/978-981-15-8411-4_92
出版状态	已出版 - 2021
活动	9th International Conference on Communications, Signal Processing, and Systems, CSPS 2020 - Changbaishan, 中国期限: 4 7月 2020 → 5 7月 2020

出版系列

姓名	Lecture Notes in Electrical Engineering
卷	654 LNEE
ISSN（印刷版）	1876-1100
ISSN（电子版）	1876-1119

会议

会议	9th International Conference on Communications, Signal Processing, and Systems, CSPS 2020
国家/地区	中国
市	Changbaishan
时期	4/07/20 → 5/07/20

访问文件

10.1007/978-981-15-8411-4_92

其它文件与链接

链接到 Scopus 的出版物

引用此

Wang, X., Xu, T., Zhang, J., Wang, S., Zhang, Y., Chen, Y., & Zhang, J. (2021). Bone Marrow Cell Counting Method Based on Fourier Ptychographic Microscopy and Convolutional Neural Network. 在 Q. Liang, W. Wang, X. Liu, Z. Na, X. Li, & B. Zhang (编辑), Communications, Signal Processing, and Systems - Proceedings of the 9th International Conference on Communications, Signal Processing, and Systems (页码 687-693). (Lecture Notes in Electrical Engineering; 卷 654 LNEE). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-15-8411-4_92

Wang, Xin ; Xu, Tingfa ; Zhang, Jizhou 等. / Bone Marrow Cell Counting Method Based on Fourier Ptychographic Microscopy and Convolutional Neural Network. Communications, Signal Processing, and Systems - Proceedings of the 9th International Conference on Communications, Signal Processing, and Systems. 编辑 / Qilian Liang ; Wei Wang ; Xin Liu ; Zhenyu Na ; Xiaoxia Li ; Baoju Zhang. Springer Science and Business Media Deutschland GmbH, 2021. 页码 687-693 (Lecture Notes in Electrical Engineering).

@inproceedings{82f762e0bbb54e95b365d900825d6110,

title = "Bone Marrow Cell Counting Method Based on Fourier Ptychographic Microscopy and Convolutional Neural Network",

abstract = "In bone marrow examination, the number of bone marrow cells is an essential parameter to judge the degree of myeloproliferative. In this paper, we propose a new bone marrow cell counting method based on Fourier ptychographic microscopy and convolutional neural network. We use Fourier ptychographic microscopy technology to obtain the intensity and phase images of bone marrow cells at first. Then, we combine the intensity and the phase image correspondingly to obtain a dual-channel image. We use the convolutional neural network to extract the characteristics of bone marrow cells in the dual-channel image, which can generate a density map. The number of bone marrow cells is realized by integrating the density map. The experimental results show that both the mean absolute error (MAE = 0.66) and mean square error (MSE = 0.67) of our method are lower than those existing methods.",

keywords = "Bone marrow cells, Convolutional neural network, Counting, Fourier ptychographic microscopy",

author = "Xin Wang and Tingfa Xu and Jizhou Zhang and Shushan Wang and Yizhou Zhang and Yiwen Chen and Jinhua Zhang",

note = "Publisher Copyright: {\textcopyright} 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.; 9th International Conference on Communications, Signal Processing, and Systems, CSPS 2020 ; Conference date: 04-07-2020 Through 05-07-2020",

year = "2021",

doi = "10.1007/978-981-15-8411-4_92",

language = "English",

isbn = "9789811584107",

series = "Lecture Notes in Electrical Engineering",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "687--693",

editor = "Qilian Liang and Wei Wang and Xin Liu and Zhenyu Na and Xiaoxia Li and Baoju Zhang",

booktitle = "Communications, Signal Processing, and Systems - Proceedings of the 9th International Conference on Communications, Signal Processing, and Systems",

address = "Germany",

}

Wang, X, Xu, T, Zhang, J, Wang, S, Zhang, Y, Chen, Y & Zhang, J 2021, Bone Marrow Cell Counting Method Based on Fourier Ptychographic Microscopy and Convolutional Neural Network. 在 Q Liang, W Wang, X Liu, Z Na, X Li & B Zhang (编辑), Communications, Signal Processing, and Systems - Proceedings of the 9th International Conference on Communications, Signal Processing, and Systems. Lecture Notes in Electrical Engineering, 卷 654 LNEE, Springer Science and Business Media Deutschland GmbH, 页码 687-693, 9th International Conference on Communications, Signal Processing, and Systems, CSPS 2020, Changbaishan, 中国, 4/07/20. https://doi.org/10.1007/978-981-15-8411-4_92

Bone Marrow Cell Counting Method Based on Fourier Ptychographic Microscopy and Convolutional Neural Network. / Wang, Xin; Xu, Tingfa; Zhang, Jizhou 等.
Communications, Signal Processing, and Systems - Proceedings of the 9th International Conference on Communications, Signal Processing, and Systems. 编辑 / Qilian Liang; Wei Wang; Xin Liu; Zhenyu Na; Xiaoxia Li; Baoju Zhang. Springer Science and Business Media Deutschland GmbH, 2021. 页码 687-693 (Lecture Notes in Electrical Engineering; 卷 654 LNEE).

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

TY - GEN

T1 - Bone Marrow Cell Counting Method Based on Fourier Ptychographic Microscopy and Convolutional Neural Network

AU - Wang, Xin

AU - Xu, Tingfa

AU - Zhang, Jizhou

AU - Wang, Shushan

AU - Zhang, Yizhou

AU - Chen, Yiwen

AU - Zhang, Jinhua

PY - 2021

Y1 - 2021

N2 - In bone marrow examination, the number of bone marrow cells is an essential parameter to judge the degree of myeloproliferative. In this paper, we propose a new bone marrow cell counting method based on Fourier ptychographic microscopy and convolutional neural network. We use Fourier ptychographic microscopy technology to obtain the intensity and phase images of bone marrow cells at first. Then, we combine the intensity and the phase image correspondingly to obtain a dual-channel image. We use the convolutional neural network to extract the characteristics of bone marrow cells in the dual-channel image, which can generate a density map. The number of bone marrow cells is realized by integrating the density map. The experimental results show that both the mean absolute error (MAE = 0.66) and mean square error (MSE = 0.67) of our method are lower than those existing methods.

AB - In bone marrow examination, the number of bone marrow cells is an essential parameter to judge the degree of myeloproliferative. In this paper, we propose a new bone marrow cell counting method based on Fourier ptychographic microscopy and convolutional neural network. We use Fourier ptychographic microscopy technology to obtain the intensity and phase images of bone marrow cells at first. Then, we combine the intensity and the phase image correspondingly to obtain a dual-channel image. We use the convolutional neural network to extract the characteristics of bone marrow cells in the dual-channel image, which can generate a density map. The number of bone marrow cells is realized by integrating the density map. The experimental results show that both the mean absolute error (MAE = 0.66) and mean square error (MSE = 0.67) of our method are lower than those existing methods.

KW - Bone marrow cells

KW - Convolutional neural network

KW - Counting

KW - Fourier ptychographic microscopy

UR - http://www.scopus.com/inward/record.url?scp=85111365979&partnerID=8YFLogxK

U2 - 10.1007/978-981-15-8411-4_92

DO - 10.1007/978-981-15-8411-4_92

M3 - Conference contribution

AN - SCOPUS:85111365979

SN - 9789811584107

T3 - Lecture Notes in Electrical Engineering

SP - 687

EP - 693

BT - Communications, Signal Processing, and Systems - Proceedings of the 9th International Conference on Communications, Signal Processing, and Systems

A2 - Liang, Qilian

A2 - Wang, Wei

A2 - Liu, Xin

A2 - Na, Zhenyu

A2 - Li, Xiaoxia

A2 - Zhang, Baoju

PB - Springer Science and Business Media Deutschland GmbH

T2 - 9th International Conference on Communications, Signal Processing, and Systems, CSPS 2020

Y2 - 4 July 2020 through 5 July 2020

ER -

Wang X, Xu T, Zhang J, Wang S, Zhang Y, Chen Y 等. Bone Marrow Cell Counting Method Based on Fourier Ptychographic Microscopy and Convolutional Neural Network. 在 Liang Q, Wang W, Liu X, Na Z, Li X, Zhang B, 编辑, Communications, Signal Processing, and Systems - Proceedings of the 9th International Conference on Communications, Signal Processing, and Systems. Springer Science and Business Media Deutschland GmbH. 2021. 页码 687-693. (Lecture Notes in Electrical Engineering). doi: 10.1007/978-981-15-8411-4_92

Bone Marrow Cell Counting Method Based on Fourier Ptychographic Microscopy and Convolutional Neural Network

摘要

出版系列

会议

访问文件

其它文件与链接

指纹

引用此