• Chinese Journal of Lasers
  • Vol. 49, Issue 5, 0507204 (2022)
Zhaohui Wang1, Huan Kang1, Duofang Chen1, Xinyi Xu1, Qi Zeng1, Jimin Liang2、**, and Xueli Chen1、*
Author Affiliations
  • 1Xi’an Key Laboratory of Intelligent Sensing and Regulation of Trans-Scale Life Information, School of Life Science and Technology, Xidian University, Xi’an 710126, Shaanxi, China
  • 2School of Electronic Engineering, Xidian University, Xi’an 710126, Shaanxi, China
  • show less
    DOI: 10.3788/CJL202249.0507204 Cite this Article Set citation alerts
    Zhaohui Wang, Huan Kang, Duofang Chen, Xinyi Xu, Qi Zeng, Jimin Liang, Xueli Chen. Lightweight Deep Learning Network Assisted Cell Classification Using Lensless Computational Microscopic Imaging Data[J]. Chinese Journal of Lasers, 2022, 49(5): 0507204 Copy Citation Text show less
    Lens-less computational microscopic imaging and classification system
    Fig. 1. Lens-less computational microscopic imaging and classification system
    Microscopic images of ECa109 cells under lensless computational microscopic imaging system and 4× objective lens. (a) Full field-of-view image of ECa109 cells acquired by lensless computational microscopic imaging system; (b) microscopic image of ECa109 cells in square outlined in Fig. 2(a) under 4× objective lens; (c) enlarged image of ECa109 cells in square outlined in Fig. 2(a) acquired by lensless computational microscopic imaging system
    Fig. 2. Microscopic images of ECa109 cells under lensless computational microscopic imaging system and 4× objective lens. (a) Full field-of-view image of ECa109 cells acquired by lensless computational microscopic imaging system; (b) microscopic image of ECa109 cells in square outlined in Fig. 2(a) under 4× objective lens; (c) enlarged image of ECa109 cells in square outlined in Fig. 2(a) acquired by lensless computational microscopic imaging system
    Images of different cells. (a) SUM cell; (b) MCF10A cell; (c) ECa109 cell; (d) CL-1 cell
    Fig. 3. Images of different cells. (a) SUM cell; (b) MCF10A cell; (c) ECa109 cell; (d) CL-1 cell
    Network structure of Depthwise-ResNeXt
    Fig. 4. Network structure of Depthwise-ResNeXt
    Fuzzy matrix of Depthwise-ResNeXt
    Fig. 5. Fuzzy matrix of Depthwise-ResNeXt
    Way to improveChannel numberTest accuracy
    Conv 1Layer 1Layer 2Layer 3Layer 4
    Depthwise convolution3232641282560.889
    Depthwise convolution64641282565120.928
    Depthwise convolution646412825600.905
    Depthwise convolution6412825651210240.926
    Table 1. Experimental results of networks with different sizes
    IndexChannel shuffleDepthwise convolutionAsymmetric convolutionDepthwise convolution & channel shuffleDepthwise convolution & asymmetric convolutionAllResNeXtM
    Accuracy0.9220.9280.9220.9130.9110.9080.921
    Calculated amount /1091.041.011.031.011.011.001.04
    Number of parameters /kB846806830806803803846
    Time /s1.17±5×10-41.12±4.2×10-41.18±1.4×10-41.13±2.2×1051.12±2.4×1051.15±2.2×10-41.16±6.4×10-5
    Table 2. Experimental results of different structured networks
    IndexShuffleNetMobileNetResNetDenseNetGoogleNetDepthwise-ResNeXt
    Accuracy0.8850.8700.9240.9310.9240.928
    Calculated amount/109253.406×10-31.94410.46010.2474.881.01
    Number of parameters /kB345.4602.228×10311.172×1036.952×1035.598×103806
    Run time /s1.25±26×10-41.33±4.8×10-41.19±1.6 ×10-51.88±9.4×10-41.33±2.1×10-41.12±4.2×10-4
    Table 3. Comparison of different network structures
    Zhaohui Wang, Huan Kang, Duofang Chen, Xinyi Xu, Qi Zeng, Jimin Liang, Xueli Chen. Lightweight Deep Learning Network Assisted Cell Classification Using Lensless Computational Microscopic Imaging Data[J]. Chinese Journal of Lasers, 2022, 49(5): 0507204
    Download Citation