Establishment and application of peripheral blood leukocyte classification model

YIN Xin; JIAO Juan; CHANG Zhihong; XIA Yinglong; LIU Jie; GUAN Kunping

doi:10.7619/jcmp.20223753

Journal of Clinical Medicine in Practice > 2023 > 27(3): 86-90. > DOI: 10.7619/jcmp.20223753

YIN Xin, JIAO Juan, CHANG Zhihong, XIA Yinglong, LIU Jie, GUAN Kunping. Establishment and application of peripheral blood leukocyte classification model[J]. Journal of Clinical Medicine in Practice, 2023, 27(3): 86-90. DOI: 10.7619/jcmp.20223753

Citation:

PDF (2273 KB)

Establishment and application of peripheral blood leukocyte classification model

1.
School of Public Health, Shanxi Medical University, Taiyuan, Shanxi, 030001
2.
Laboratory Department, the Seventh Medical Center of General Hospital of Chinese People's Liberation Army, Beijing, 100700
3.
Laboratory Department, the Second Hospital of Shanxi Medical University, Taiyuan, Shanxi, 030001

More Information

Received Date: December 14, 2022
Available Online: March 01, 2023

Graphical Abstract

Abstract

Abstract

Objective
To automatically classify peripheral blood leukocytes based on Swin Transformer model, and to compare the difference between Swin Transformer model and ResNet that is a classical convolutional neural network model.
Methods
The classical convolutional neural network model ResNet and the new Swin Transformer model were used as network prototypes for training. White blood cell images were collected using the Cella Vision DI60 automatic analyzer, and the category labels of cells were confirmed by two experienced inspectors. The exponential attenuation, a learning rate attenuation method, was used to make the model converge faster. Then, 2, 788 leukocyte images were tested.
Results
The average test accuracy of ResNet for five kinds of leukocyte images was 95.2%, while that of Swin Transformer was as high as 99.1%. Among them, the recognition accuracy of Swin Transformer model is 99.8% for neutrophils, 94.8% for eosinophils, 97.5% for basophils, 99.5% for lymphocytes and 93.8% for monocytes.
Conclusion
Swin Transformer model reduces the amount of calculation, and is more suitable for leukocyte classification and recognition. Compared with ResNet, this model has more advantage in accuracy.
- leukocyte classification,
- convolution neural network,
- Swin Transformer model,
- ResNet model,
- peripheral blood,
- deep learning

FullText(HTML)

References (14)

References

[1]	MASILAMANI V, DEVANESAN S, ALSALHI M S, et al. Fluorescence spectral detection of acute lymphoblastic leukemia (ALL) and acute myeloid leukemia (AML): a novel photodiagnosis strategy[J]. Photodiagnosis Photodyn Ther, 2020, 29: 101634. doi: 10.1016/j.pdpdt.2019.101634
[2]	WARNAT-HERRESTHAL S, PERRAKIS K, TASCHLER B, et al. Scalable prediction of acute myeloid leukemia using high-dimensional machine learning and blood transcriptomics[J]. iScience, 2020, 23(1): 100780. doi: 10.1016/j.isci.2019.100780
[3]	NIAZI M K K, PARWANI A V, GURCAN M N. Digital pathology and artificial intelligence[J]. Lancet Oncol, 2019, 20(5): e253-e261. doi: 10.1016/S1470-2045(19)30154-8
[4]	CHEN Y, FENG J, LIU J, et al. Detection and Classification of Lung Cancer Cells Using Swin Transformer[J]. J Cancer Ther, 2022, 13(7): 464-475. doi: 10.4236/jct.2022.137041
[5]	宋林科, 姜珏, 王娟, 等. 人工智能辅助评分系统联合超声弹性成像诊断甲状腺结节良恶性的价值[J]. 实用临床医药杂志, 2021, 25(4): 7-10. doi: 10.7619/jcmp.20201478
[6]	王晓元, 杜美玲, 张鹏祥, 等. 基于人工智能心电远程记录构建运动性心脏性猝死三级防治体系[J]. 实用临床医药杂志, 2021, 25(24): 65-68, 73. doi: 10.7619/jcmp.20214072
[7]	王春燕, 郭宗晓, 洪小丽, 等. 思维导图联合人工智能音箱对全髋关节置换术后延续护理的效果[J]. 实用临床医药杂志, 2021, 25(12): 102-105. doi: 10.7619/jcmp.20210763
[8]	李娟娟, 刘敏, 杨斌, 等. 人工智能辅助肺结节筛查及定性诊断的应用研究[J]. 实用临床医药杂志, 2022, 26(8): 8-12. doi: 10.7619/jcmp.20214698
[9]	赵晓阳, 许树林, 潘为领, 等. 公共人工智能平台在膝关节骨性关节炎分期中的应用[J]. 实用临床医药杂志, 2022, 26(8): 22-26. doi: 10.7619/jcmp.20212888
[10]	KARTHIKEYAN M P, VENKATESAN R. Interpolative Leishman-Stained transformation invariant deep pattern classification for white blood cells[J]. Soft Comput, 2020, 24(16): 12215-12225. doi: 10.1007/s00500-019-04662-4
[11]	HEGDE R B, PRASAD K, HEBBAR H, et al. Feature extraction using traditional image processing and convolutional neural network methods to classify white blood cells: a study[J]. Australas Phys Eng Sci Med, 2019, 42(2): 627-638. doi: 10.1007/s13246-019-00742-9
[12]	ACEVEDO A, ALFÉREZ S, MERINO A, et al. Recognition of peripheral blood cell images using convolutional neural networks[J]. Comput Methods Programs Biomed, 2019, 180: 105020.
[13]	MA L, SHUAI R J, RAN X M, et al. Combining DC-GAN with ResNet for blood cell image classification[J]. Med Biol Eng Comput, 2020, 58(6): 1251-1264.
[14]	HEGDE R B, PRASAD K, HEBBAR H, et al. Automated decision support system for detection of leukemia from peripheral blood smear images[J]. J Digit Imaging, 2020, 33(2): 361-374.

Cited By

Cited by

Periodical cited type(4)

1.	李丽芳，杨中男，刘力源，关郑军，徐艳，贺红丽，李燕萍. LncRNA LIPCAR在慢性心力衰竭患者外周血中的表达及临床意义. 宁夏医学杂志. 2024(09): 758-761 .
2.	朱占占，孙雯雯，张申伟. 二甲双胍联合达格列净治疗2型糖尿病合并射血分数中间值心力衰竭患者的效果. 河南医学研究. 2022(21): 3980-3983 .
3.	柳湘洁，刘晓霞. 沙库巴曲缬沙坦对射血分数中间值心力衰竭患者心功能及近期预后的影响. 临床和实验医学杂志. 2021(16): 1689-1692 .
4.	左路广，黄冠杰，詹明华，李宝亮，张斌. 慢性心力衰竭并发感染患者病原学及脑钠肽变化研究. 实用临床医药杂志. 2021(19): 49-52 . 本站查看

Other cited types(1)

Get Citation

PDF

XML

Article views (248) PDF downloads (21) Cited by(5)

Turn off MathJax

Article Contents

Abstract

References

Establishment and application of peripheral blood leukocyte classification model

Abstract

References

Cited by

Periodical cited type(4)

Other cited types(1)

Catalog

Export File

Citation

Format

Content