基于轻量网络的白细胞快速检测算法

doi:10.3969/j.issn.0258-8021.2025.01.007

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (15394 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract Due to the large variety and morphological differences of white blood cells, and overlap, adhesion, cell boundary blurring and color change in blood microscopy, the traditional system based on image detection has difficulty in feature extraction, poor detection accuracy and insufficient stability. To address these problems, a white blood cell rapid detection algorithm based on lightweight network structure was proposed. Firstly, the algorithm used MobileNetv3 as the feature extraction network, and proposed a dual-channel pyramid feature fusion structure TCPF-Net to complete the feature fusion for its insufficient feature extraction ability. The algorithm improved the feature extraction ability of white blood cell images with blur, color change and different shapes. After that, the algorithm abandoned the large target detection head of the detection network and only retained the small and medium target detection head for the special aspect ratio and scale characteristics of white blood cells, which improved the detection speed of the algorithm for the white blood cells. Finally, the algorithm used the intersection over union parameter when the complete anchor frame overlaped with the target to complete the optimization of the regression loss function of the detection network position, and improved the detection ability of the algorithm for overlapping and adherent cells. The experiment was conducted using 40x microscopic images of human blood stained with the Romanowsky staining method. With the validation of 8,848 white blood cell images, the meanaverage precision (mAP) of the lightweight network algorithm for white blood cell detection reached 98.8%, representing 1.1% improvement compared to the original network. Simultaneously, theframes per second (FPS) reached 54.19, indicating a 32% increase compared to the original network, achieving the rapid and precise detection of white blood cells.

Key words： white blood cell detection deep learning dual channel feature fusion lightweight network

Received: 13 April 2023

PACS:

R318

Corresponding Authors: *E-mail: kentchen@hnust.edu.cn

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Chen Liang
	Guo Huihui
	Yin Tao

Cite this article:

Chen Liang,Guo Huihui,Yin Tao. Fast White Blood Cell Detection Algorithm Based on Lightweight Network[J]. Chinese Journal of Biomedical Engineering, 2025, 44(1): 66-76.

URL:

http://cjbme.csbme.org/EN/10.3969/j.issn.0258-8021.2025.01.007 OR http://cjbme.csbme.org/EN/Y2025/V44/I1/66

[1] Mojtaba J, Safoora K, Hassan M, et al. Microfluidic platform with integrated electrical actuator to enrich and locating atypical/cancer cells from liquid cytology samples[J]. Sensors & Actuators: B. Chemical, 2019, 297.
[2] 陈畅,程少杰,李卫滨等.基于卷积神经网络的外周血白细胞分类[J].中国生物医学工程学报,2018,37(1):17-24.
[3] Fanous M, He S, Sengupta S, et al. White blood cell detection, classification and analysis using phase imaging with computational specificity (PICS)[J]. Scientific Reports, 2022, 12(1): 20043.
[4] 宋杰, 肖亮, 练智超. 级联稀疏卷积与决策树集成的病理图像细胞核分割方法[J]. 自动化学报, 2021, 47: 378-390.
[5] Nisha R, Bryan D, Mohammed E, et al.Isolation and two-step classification of normal white blood cells in peripheral blood smears[J].Journal of pathology informatics,2012,3:56-66.
[6] Arslan S, Ozyurek E, Gunduz D.A Color and shape based algorithm for segmentation of white blood cells in peripheral blood and bone marrow images[J].Cytometry PartA,2014,85(6):480-490.
[7] Abdurrazzaq A. Junoh AK, Yahya, Z, et al. New white blood cell detection technique by using singular value decomposition concept white blood cell detection technique[J]. Multimedia Tools and Applications, 2021:80(3): 4627-4638.
[8] Liu Yan, Chen Yong, Han Bo, et al. Fully automatic Breast ultrasound image segmentation based on fuzzy cellular automata framework[J]. Biomedical Signal Processing and Control, 2018, 40: 433-442.
[9] Mohammad M, Mohammad T.Machine learning approach of automatic identification and counting of blood cells[J]. Healthcare Technology Letters,2019,6(4): 103-108.
[10] Sarang S, Sheifali G, Deepali G, et al. Deep learning model for the automatic classification of white blood cells[J].Computational Intelligence and Neuroscience, 2022, 1:7384131.
[11] Roy R, Ameer P. Segmentation of leukocyte by semantic segmentation model: a deep learning approach[J]. Biomedical Signal Processing and Control, 2021, 65: 102385.
[12] Tiwari P, Qian J, Li Q, et al. Detection of sub type blood cells using deep learning[J]. Cognitive Systems Research,2018,52(12):1036-1044.
[13] Zheng Xin, Tang Pan, Ai Liefu, et al. White blood cell detection using saliency detection and CenterNet: a two‐stage approach[J]. Journal of Biophotonics, 2022: e202200174.
[14] Huang Hui, Feng Xian, Jiang Jionghui, et al.Mask RCNN algorithm for nuclei detection on breast cancer histopathological images[J].IntJ Imaging Syst.Technol,2022, 32: 209.
[15] Jane H, Anne C. Applying faster R-CNN for object detection on malaria images[C]//2017 IEEE Conference on Computer Vision and Pattem Recognition Workshops(CVPRW). Honolulu: IEEE, 2017:112.
[16] Jia Dongyao, Zhou Jialin. Zhang Chuanwang. Detection of cervical cells based on improved SSD network.Multimed[J]. Tools Appl. 2022, 81:13371.
[17] Zhang Xiaoqing, Zhao Shuguang. G.Blood cell image classification based on image segmentation preprocessing and CapsNet network model[J].Journal of Medical Imaging and Health Informatics,2019,9(1):159-166.
[18] Shakarami A, Menhaj M ,Mahdavi-Hormat A ,et al.A fast and yet efficient YOLOv3 for blood cell detection[J].Biomedical Signal Processing and Control,2021, 66: 102495.
[19] Chen Liang,Yang Yuyi, Wang Zhenheng, et al. Underwater target detection lightweight algorithm based on multi-scale feature fusion. [J]. Mar Sci Eng, 2023, 11: 320.
[20] Saito H, Aoki T, Aoyama K, et al. Automatie detection and classification of protruding lesions in wireless capsule endoscopy images based on a deep convolutional neural network [J]. Gastrintest Endosc,2020,92(1): 144-151.
[21] Geng Lei, Yang Lianmeng, Xiao Zhitao, et al. White blood cell detection and segmentation combined with the channel space[J]. Journal of Computer Aided Design and Graphics, 2021,33(9):1418-1427.
[22] Diwan T, Anirudh G, Tembhurne J. Object detection using YOLO: Challenges, architectural successors, datasets and applications[J]. multimedia Tools and Applications, 2023, 82(6): 9243-9275.
[23] Wang CY, Bochkovskiy A, Liao HYM. YOLOv7: trainable bagof-freebies sets new state-of-the-art for real-time objeet detectors[C]//2023 EEE/CVF Conference on Computer Vision andPaltern Recognition(CVPR). Vancouver:IEEE, 2023:7464-7475.
[24] 冷冰,冷敏,常智敏等.基于Transformer结构的深度学习模型用于外周血白细胞检测[J].仪器仪表学报,2023,44(5):113-120.
[25] Tusneem A,Mohd S,Mohd H, et al. Classification of atypical white blood cells in acute myeloid leukemia using a two-stage hybrid model based on deep convolutional autoencoder and deep convolutional neural network[J]. Diagnostics, 2023, 13: 196.
[26] 刘秀娜,于海涛.血液分析仪检验用于白血病诊断的临床价值分析[J].中国现代药物应用,2023,17(19):55-59.
[27] 张春梅,宋杰,王金祥.老年COPD伴肺部感染患者外周血细胞形态学变化及其对预后的预测价值[J].湖南师范大学学报(医学版),2024,21(2):51-55.
[28] 李瑞祥.血液分析仪白细胞分类计数结果与瑞氏染色镜检结果的比较[J].广西医学,2015,37(3):403-404.
[29] Samad M, Ponnuthurai D , Badrudin S , et al. Migration study of dielectrophoretically manipulated red blood cells in tapered aluminium microelectrode array: a pilot study[J]. Micromachines, 2023, 14(8): 1625.
[30] 李延飞,陈众.全自动血细胞分析仪与血涂片细胞形态学对血常规检测的干预分析[J].中国医学工程,2024,32(6):19-22.
[31] Yentrapragada D. Deep features based convolutional neural network to detect and automatic classification of white blood cells[J]. Journal of Ambient Intelligence and Humanized Computing, 2023, 14(7): 9191-9205.
[32] Nasir N, Raji S, Mustafa F, et al. Electrical detection of blood cells in urine[J]. Heliyon, 2020, 6(1):e03102.