• Laser & Optoelectronics Progress
  • Vol. 59, Issue 2, 0210002 (2022)
Jingcheng Wu1, Lulu Shi2, Yanan Du1, Luhong Wen1, and Zhenzhi Shi1、*
Author Affiliations
  • 1The Research Institute of Advanced Technologies, Ningbo University, Ningbo , Zhejiang 315211, China
  • 2China Innovation Instrument Co., Ltd., Ningbo , Zhejiang 315100, China
  • show less
    DOI: 10.3788/LOP202259.0210002 Cite this Article Set citation alerts
    Jingcheng Wu, Lulu Shi, Yanan Du, Luhong Wen, Zhenzhi Shi. Fast Segmentation Method of Cell Image Based on Dual-Gaussian Filtering[J]. Laser & Optoelectronics Progress, 2022, 59(2): 0210002 Copy Citation Text show less
    Feature analysis of phase contrast microscopy image. (a) Cell image; (b) gray value distribution at longitudinal lines; (c) gray value distribution at transverse line
    Fig. 1. Feature analysis of phase contrast microscopy image. (a) Cell image; (b) gray value distribution at longitudinal lines; (c) gray value distribution at transverse line
    Flow chart of the proposed method
    Fig. 2. Flow chart of the proposed method
    Dual-Gaussian filtering process. (a) Input image; (b) Gaussian filtering (large kernel); (c) Gaussian filtering (small kernel); (d) difference calculation
    Fig. 3. Dual-Gaussian filtering process. (a) Input image; (b) Gaussian filtering (large kernel); (c) Gaussian filtering (small kernel); (d) difference calculation
    Effect of different σ2 values ​​on the segmentation results
    Fig. 4. Effect of different σ2 values ​​on the segmentation results
    Relationship between σ2 value and standard deviation of fdg
    Fig. 5. Relationship between σ2 value and standard deviation of fdg
    Comparison diagrams before and after dual-Gaussian filtering. (a) Before processing; (b) grayscale mapping before processing; (c) after processing; (d) grayscale mapping after processing
    Fig. 6. Comparison diagrams before and after dual-Gaussian filtering. (a) Before processing; (b) grayscale mapping before processing; (c) after processing; (d) grayscale mapping after processing
    Binary segmentation image. (a) Threshold segmentation; (b) hole filling; (c) area constraint
    Fig. 7. Binary segmentation image. (a) Threshold segmentation; (b) hole filling; (c) area constraint
    Segmentation results of low-density cell images processed by different algorithms. (a) Cell image; (b) 2D-Otsu algorithm; (c) Jaccard algorithm; (d) Flight algorithm; (e) Vicar algorithm; (f) proposed algorithm
    Fig. 8. Segmentation results of low-density cell images processed by different algorithms. (a) Cell image; (b) 2D-Otsu algorithm; (c) Jaccard algorithm; (d) Flight algorithm; (e) Vicar algorithm; (f) proposed algorithm
    Segmentation results of medium-density cell images processed by different algorithms. (a) Cell image; (b) 2D-Otsu algorithm; (c) Jaccard algorithm; (d) Flight algorithm; (e) Vicar algorithm; (f) proposed algorithm
    Fig. 9. Segmentation results of medium-density cell images processed by different algorithms. (a) Cell image; (b) 2D-Otsu algorithm; (c) Jaccard algorithm; (d) Flight algorithm; (e) Vicar algorithm; (f) proposed algorithm
    Segmentation results of high-density cell images processed by different algorithms. (a) Cell image; (b) 2D-Otsu algorithm; (c) Jaccard algorithm; (d) Flight algorithm; (e) Vicar algorithm; (f) proposed algorithm
    Fig. 10. Segmentation results of high-density cell images processed by different algorithms. (a) Cell image; (b) 2D-Otsu algorithm; (c) Jaccard algorithm; (d) Flight algorithm; (e) Vicar algorithm; (f) proposed algorithm
    Comparison of segmentation results of different algorithms in complex situations
    Fig. 11. Comparison of segmentation results of different algorithms in complex situations
    AlgorithmPrecisionRecallF-scoreTime /s
    2D-Otsu0.08830.04620.06070.98
    Jaccard0.90300.84700.86062.66
    Flight0.91660.94020.92812.47
    Vicar0.97560.82460.89190.78
    Proposed algorithm0.97700.94570.96091.68
    Table 1. Comparison of segmentation results using different algorithms
    ExampleAlgorithmGTENNTPNFPNFNPrecisionRecallF-score
    Fig. 82D-Otsu10459554990.08470.04810.0614
    Jaccard1261002640.79370.96150.8696
    Flight112981460.8750.94230.9074
    Vicar105102320.97140.98080.9761
    Proposed algorithm10599650.94290.95190.9474
    Fig. 92D-Otsu271227122152590.05290.04430.0482
    Jaccard20819315780.92790.71220.8058
    Flight27925920120.92830.95570.9418
    Vicar2072016600.97100.74170.8410
    Proposed algorithm2652605110.98110.95940.9701
    Fig. 102D-Otsu577291122795650.04120.02080.0277
    Jaccard22822533490.98680.38990.5590
    Flight59956039140.93480.97050.9524
    Vicar38037282050.97890.64470.7774
    Proposed algorithm57456410130.98250.97750.9800
    Table 2. Comparison of cell segmentation results of sample images
    Jingcheng Wu, Lulu Shi, Yanan Du, Luhong Wen, Zhenzhi Shi. Fast Segmentation Method of Cell Image Based on Dual-Gaussian Filtering[J]. Laser & Optoelectronics Progress, 2022, 59(2): 0210002
    Download Citation