Journal of Infrared and Millimeter Waves, Volume. 39, Issue 6, 749(2020)

Identification and measurement of cutaneous melanoma superficial spreading depth using microscopic hyperspectral imaging technology

Jian-Sheng WANG1,2, Qing-Li LI1,2,3、*, Mei ZHOU1,2, Li SUN1,2, Meng-Han HU1,2, Yue LYU1,2, and Jun-Hao CHU1,3
Author Affiliations
  • 1Shanghai Key Laboratory of Multidimensional Information Processing, East China Normal University, Shanghai200241, China
  • 2Engineering Center of SHMEC for Space Information and GNSS, Shanghai200241, China
  • 3Engineering Research Center of Nanophotonics & Advanced Instrument, Ministry of Education, East China Normal University, Shanghai200241, China
  • show less
    Figures & Tables(12)
    The main flowchart of the proposed methods
    (a) Normal skin tissue, (b) melanoma sample
    The main schematic and optical path diagram of microscopic hyperspectral imaging system
    (a) Spectrum of a sampling point, (b) the data cube of the cutaneous melanoma, and (c) the single band image
    (a) 100x microscopic image of melanoma sample, (c) 200x image, (b) and (d) Single-band images at 810 nm.
    (a) and (b) Single-band images after preprocessing. (c) and (d) Spectra at the same position before and after processing
    (a) The color microscope image, (b) the single-wavelength hyperspectral image, (c) the KMNF-based result at sixth waveband, (d) the morphological filtering result of skin granular layer, (e) the contour extraction based on level set segmentation, and (f) the finished segmentation result.
    Comparison of granular layer segmentation results of different methods
    (a) A microscope image of malignant melanocytes, (b) the single band image at 810 nm, (c) the SVM segmentation result, and (d) the CSS-LSSVM segmentation result.
    Measurement results of cutaneous melanoma superficial spreading depth.
    • Table 1. Comparison of malignant melanocytes segmentation results of different methods

      View table
      View in Article

      Table 1. Comparison of malignant melanocytes segmentation results of different methods

      Indexes /(%)MethodNo. of samples
      1234
      AccuracySVM68.6079.3477.2578.48
      CSS-LSSVM86.0287.4986.0286.85
      SensitivitySVM38.0560.0456.5058.32
      CSS-LSSVM77.9179.3376.7276.54
      SpecificitySVM99.1598.6498.0198.64
      CSS-LSSVM94.1395.6695.3397.15
    • Table 2. Correspondence between pixel size and real physical value of MHSI system

      View table
      View in Article

      Table 2. Correspondence between pixel size and real physical value of MHSI system

      Objective multipleScale distanceConversion coefficient(pixel/mm)
      0.01 mm0.02 mm0.05 mm0.1 mm0.2 mm
      4x9.5117.8544.7089.05177.11902
      10x23.3745.04110.432220.53442.572243
      20x46.0391.61222.09448.29891.024512
    Tools

    Get Citation

    Copy Citation Text

    Jian-Sheng WANG, Qing-Li LI, Mei ZHOU, Li SUN, Meng-Han HU, Yue LYU, Jun-Hao CHU. Identification and measurement of cutaneous melanoma superficial spreading depth using microscopic hyperspectral imaging technology[J]. Journal of Infrared and Millimeter Waves, 2020, 39(6): 749

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category: Infrared Spectroscopy and Spectral Analysis

    Received: Mar. 18, 2020

    Accepted: --

    Published Online: Jan. 20, 2021

    The Author Email: Qing-Li LI (qlli@cs.ecnu.edu.cn)

    DOI:10.11972/j.issn.1001-9014.2020.06.013

    Topics