Automatic segmentation of cell nuclei in bladder and skin tissue for karyometric analysis

Vrushali R. Korde, Hubert Bartels, Jennifer K Barton, James Ranger-Moore

Research output: Contribution to journalArticle

18 Citations (Scopus)

Abstract

OBJECTIVE: To automatically segment cell nuclei in histology images of bladder and skin tissue for karyometric analysis, STUDY DESIGN: The 4 main steps in the program were as follows: median filtering and thresholding, segmentation, categorizing and cusp correction. This robust segmentation technique used properties of the image histogram to optimally select a threshold and create closed 4-way chain code nuclear segmentations. Each cell nucleus segmentation was treated as an individual object of which the properties of segmentation quality were used for criteria to classify each nucleus as: throw away, salvageable or good. An erosion/dilation procedure and rethresholding were performed on salvageable nuclei to correct cusps. RESULTS: Ten bladder histology images were segmented both by hand and using this automatic segmentation algorithm. The automatic segmentation resulted in a sensitivity of 76.4%, defined as the percentage of hand - segmented nuclei that were automatically segmented with good quality. The median proportional difference between hand and automatic segmentations over 42 nuclei each with 95 features used in karyometric analysis was 1.6%. The same procedure was performed on 10 skin histology images with a sensitivity of 83.0% and median proportional difference of 2.6%. CONCLUSION: The close agreement in karyometric features with hand segmentation shows that automated segmentation can be used for analysis of bladder and skin histology images.

Original languageEnglish (US)
Pages (from-to)83-89
Number of pages7
JournalAnalytical and Quantitative Cytology and Histology
Volume31
Issue number2
StatePublished - Apr 2009

Fingerprint

Karyometry
Cell Nucleus
Histology
Urinary Bladder
Hand
Skin
Dilatation

Keywords

  • Bladder
  • Cell nucleus
  • Karyometry
  • Segmentation
  • Skin

ASJC Scopus subject areas

  • Anatomy
  • Histology

Cite this

Automatic segmentation of cell nuclei in bladder and skin tissue for karyometric analysis. / Korde, Vrushali R.; Bartels, Hubert; Barton, Jennifer K; Ranger-Moore, James.

In: Analytical and Quantitative Cytology and Histology, Vol. 31, No. 2, 04.2009, p. 83-89.

Research output: Contribution to journalArticle

@article{882066a188b749248aa4714a2d7dcb58,
title = "Automatic segmentation of cell nuclei in bladder and skin tissue for karyometric analysis",
abstract = "OBJECTIVE: To automatically segment cell nuclei in histology images of bladder and skin tissue for karyometric analysis, STUDY DESIGN: The 4 main steps in the program were as follows: median filtering and thresholding, segmentation, categorizing and cusp correction. This robust segmentation technique used properties of the image histogram to optimally select a threshold and create closed 4-way chain code nuclear segmentations. Each cell nucleus segmentation was treated as an individual object of which the properties of segmentation quality were used for criteria to classify each nucleus as: throw away, salvageable or good. An erosion/dilation procedure and rethresholding were performed on salvageable nuclei to correct cusps. RESULTS: Ten bladder histology images were segmented both by hand and using this automatic segmentation algorithm. The automatic segmentation resulted in a sensitivity of 76.4{\%}, defined as the percentage of hand - segmented nuclei that were automatically segmented with good quality. The median proportional difference between hand and automatic segmentations over 42 nuclei each with 95 features used in karyometric analysis was 1.6{\%}. The same procedure was performed on 10 skin histology images with a sensitivity of 83.0{\%} and median proportional difference of 2.6{\%}. CONCLUSION: The close agreement in karyometric features with hand segmentation shows that automated segmentation can be used for analysis of bladder and skin histology images.",
keywords = "Bladder, Cell nucleus, Karyometry, Segmentation, Skin",
author = "Korde, {Vrushali R.} and Hubert Bartels and Barton, {Jennifer K} and James Ranger-Moore",
year = "2009",
month = "4",
language = "English (US)",
volume = "31",
pages = "83--89",
journal = "Analytical and Quantitative Cytopathology and Histopathology",
issn = "0301-102X",
publisher = "John Rylands University Library",
number = "2",

}

TY - JOUR

T1 - Automatic segmentation of cell nuclei in bladder and skin tissue for karyometric analysis

AU - Korde, Vrushali R.

AU - Bartels, Hubert

AU - Barton, Jennifer K

AU - Ranger-Moore, James

PY - 2009/4

Y1 - 2009/4

N2 - OBJECTIVE: To automatically segment cell nuclei in histology images of bladder and skin tissue for karyometric analysis, STUDY DESIGN: The 4 main steps in the program were as follows: median filtering and thresholding, segmentation, categorizing and cusp correction. This robust segmentation technique used properties of the image histogram to optimally select a threshold and create closed 4-way chain code nuclear segmentations. Each cell nucleus segmentation was treated as an individual object of which the properties of segmentation quality were used for criteria to classify each nucleus as: throw away, salvageable or good. An erosion/dilation procedure and rethresholding were performed on salvageable nuclei to correct cusps. RESULTS: Ten bladder histology images were segmented both by hand and using this automatic segmentation algorithm. The automatic segmentation resulted in a sensitivity of 76.4%, defined as the percentage of hand - segmented nuclei that were automatically segmented with good quality. The median proportional difference between hand and automatic segmentations over 42 nuclei each with 95 features used in karyometric analysis was 1.6%. The same procedure was performed on 10 skin histology images with a sensitivity of 83.0% and median proportional difference of 2.6%. CONCLUSION: The close agreement in karyometric features with hand segmentation shows that automated segmentation can be used for analysis of bladder and skin histology images.

AB - OBJECTIVE: To automatically segment cell nuclei in histology images of bladder and skin tissue for karyometric analysis, STUDY DESIGN: The 4 main steps in the program were as follows: median filtering and thresholding, segmentation, categorizing and cusp correction. This robust segmentation technique used properties of the image histogram to optimally select a threshold and create closed 4-way chain code nuclear segmentations. Each cell nucleus segmentation was treated as an individual object of which the properties of segmentation quality were used for criteria to classify each nucleus as: throw away, salvageable or good. An erosion/dilation procedure and rethresholding were performed on salvageable nuclei to correct cusps. RESULTS: Ten bladder histology images were segmented both by hand and using this automatic segmentation algorithm. The automatic segmentation resulted in a sensitivity of 76.4%, defined as the percentage of hand - segmented nuclei that were automatically segmented with good quality. The median proportional difference between hand and automatic segmentations over 42 nuclei each with 95 features used in karyometric analysis was 1.6%. The same procedure was performed on 10 skin histology images with a sensitivity of 83.0% and median proportional difference of 2.6%. CONCLUSION: The close agreement in karyometric features with hand segmentation shows that automated segmentation can be used for analysis of bladder and skin histology images.

KW - Bladder

KW - Cell nucleus

KW - Karyometry

KW - Segmentation

KW - Skin

UR - http://www.scopus.com/inward/record.url?scp=64549123004&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=64549123004&partnerID=8YFLogxK

M3 - Article

C2 - 19402384

AN - SCOPUS:64549123004

VL - 31

SP - 83

EP - 89

JO - Analytical and Quantitative Cytopathology and Histopathology

JF - Analytical and Quantitative Cytopathology and Histopathology

SN - 0301-102X

IS - 2

ER -