Premium
Evaluation of nuclear chromatin using grayscale intensity and thresholded percentage area in liquid‐based cervical cytology
Author(s) -
Lee Hyekyung,
Han Myungein,
Yoo Taejo,
Jung Chanho,
Son HyunJin,
Cho Migyung
Publication year - 2018
Publication title -
diagnostic cytopathology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.417
H-Index - 65
eISSN - 1097-0339
pISSN - 8755-1039
DOI - 10.1002/dc.23906
Subject(s) - grayscale , thresholding , intensity (physics) , chromatin , nuclear medicine , medicine , standard deviation , artificial intelligence , mathematics , biology , statistics , optics , computer science , physics , pixel , dna , image (mathematics) , genetics
Objectives Development of computerized image analysis techniques has opened up the possibility for the quantitative analysis of nuclear chromatin in pathology. We hypothesized that the features extracted from digital images could be used to determine specific cytomorphological findings for nuclear chromatin that may be applicable for establishing a medical diagnosis. Methods Three parameters were evaluated from nuclear chromatin images obtained from the liquid‐based cervical cytology samples of patients with biopsy‐proven high‐grade squamous intraepithelial lesion (HGSIL), and compared between non‐neoplastic squamous epithelia and dysplastic epithelia groups: (1) standard deviation (SD) of the grayscale intensity; (2) difference between the maximum and minimum grayscale intensity (M‐M); and (3) thresholded area percentage. Each parameter was evaluated at the mean, mean‐1SD, and mean‐2SD thresholding intensity levels. Results Between the mean and mean‐1SD levels, the thresholded nuclear chromatin pattern was most similar to the chromatin granularity of the unthresholded grayscale images. The SD of the gray intensity and the thresholded area percentage differed significantly between the non‐neoplastic squamous epithelia and dysplastic epithelia of HGSIL images at all three thresholding intensity levels (mean, mean‐1SD, and mean‐2SD). However, the M‐M significantly differed between the two sample types for only two of the thresholding intensity levels (mean‐1SD and mean‐2SD). Conclusions The digital parameters SD and M‐M of the grayscale intensity, along with the thresholded area percentage could be useful in automated cytological evaluations. Further studies are needed to identify more valuable parameters for clinical application.