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

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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Objective: To automatically segment cell nuclei in histology images of bladder and skin tissue for karyometric analysis. Materials/Methods: The four main steps in the program were as follows: 1) median filtering and thresholding, 2) segmentation, 3) categorizing, and 4) cusp correction. This robust segmentation technique used properties of the image histogram to optimally select a threshold and create closed four-way chain code nuclei segmentations. Each cell nucleus segmentation was treated as an individual object with properties of segmentation quality. A segmentation was placed in one of the following three categories based on its properties: throw away, salvageable, or good. Erosion/dilation and rethresholding were performed on salvageable nuclei to correct cusps. Results: Ten bladder histology images were segmented both by hand and using this automatic segmention algorithm. The automatic segmentation resulted in a sensitivity of 76.4%. The average difference between hand and automatic segmentations over 42 nuclei, calculated for each of the 95 features used in karyometric analysis, ranged between 0 and 48.3%, with an average of 2.8%. The same procedure was performed on 10 skin histology images with a sensitivity of 83.0%. Average differences over 44 nuclei ranged between 0 and 200%, with an average of 10.0%. 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. Average differences between hand and automatic segmentations were smaller in bladder histology images because these images contained less contrast, and therefore the range of the karyometric feature values was smaller.

Original languageEnglish (US)
Title of host publicationOptics InfoBase Conference Papers
PublisherOptical Society of America
ISBN (Print)9780819467713
StatePublished - 2007
EventEuropean Conference on Biomedical Optics, ECBO 2007 - Munich, Germany
Duration: Jun 17 2007Jun 17 2007

Other

OtherEuropean Conference on Biomedical Optics, ECBO 2007
CountryGermany
CityMunich
Period6/17/076/17/07

Fingerprint

Histology
bladder
histology
Skin
Cells
Tissue
nuclei
cusps
Erosion
sensitivity
histograms
erosion
thresholds

Keywords

  • Bladder
  • Karyometry
  • Nuclei
  • Segmentation
  • Skin

ASJC Scopus subject areas

  • Instrumentation
  • Atomic and Molecular Physics, and Optics

Cite this

Korde, V. R., Bartels, H., Ranger-Moore, J., & Barton, J. K. (2007). Automatic segmentation of cell nuclei in bladder and skin tissue for karyometric analysis. In Optics InfoBase Conference Papers Optical Society of America.

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

Optics InfoBase Conference Papers. Optical Society of America, 2007.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Korde, VR, Bartels, H, Ranger-Moore, J & Barton, JK 2007, Automatic segmentation of cell nuclei in bladder and skin tissue for karyometric analysis. in Optics InfoBase Conference Papers. Optical Society of America, European Conference on Biomedical Optics, ECBO 2007, Munich, Germany, 6/17/07.
Korde VR, Bartels H, Ranger-Moore J, Barton JK. Automatic segmentation of cell nuclei in bladder and skin tissue for karyometric analysis. In Optics InfoBase Conference Papers. Optical Society of America. 2007
Korde, Vrushali R. ; Bartels, Hubert ; Ranger-Moore, James ; Barton, Jennifer K. / Automatic segmentation of cell nuclei in bladder and skin tissue for karyometric analysis. Optics InfoBase Conference Papers. Optical Society of America, 2007.
@inproceedings{27291deb610946369a18d0436be3f360,
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. Materials/Methods: The four main steps in the program were as follows: 1) median filtering and thresholding, 2) segmentation, 3) categorizing, and 4) cusp correction. This robust segmentation technique used properties of the image histogram to optimally select a threshold and create closed four-way chain code nuclei segmentations. Each cell nucleus segmentation was treated as an individual object with properties of segmentation quality. A segmentation was placed in one of the following three categories based on its properties: throw away, salvageable, or good. Erosion/dilation and rethresholding were performed on salvageable nuclei to correct cusps. Results: Ten bladder histology images were segmented both by hand and using this automatic segmention algorithm. The automatic segmentation resulted in a sensitivity of 76.4{\%}. The average difference between hand and automatic segmentations over 42 nuclei, calculated for each of the 95 features used in karyometric analysis, ranged between 0 and 48.3{\%}, with an average of 2.8{\%}. The same procedure was performed on 10 skin histology images with a sensitivity of 83.0{\%}. Average differences over 44 nuclei ranged between 0 and 200{\%}, with an average of 10.0{\%}. 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. Average differences between hand and automatic segmentations were smaller in bladder histology images because these images contained less contrast, and therefore the range of the karyometric feature values was smaller.",
keywords = "Bladder, Karyometry, Nuclei, Segmentation, Skin",
author = "Korde, {Vrushali R.} and Hubert Bartels and James Ranger-Moore and Barton, {Jennifer K}",
year = "2007",
language = "English (US)",
isbn = "9780819467713",
booktitle = "Optics InfoBase Conference Papers",
publisher = "Optical Society of America",

}

TY - GEN

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

AU - Korde, Vrushali R.

AU - Bartels, Hubert

AU - Ranger-Moore, James

AU - Barton, Jennifer K

PY - 2007

Y1 - 2007

N2 - Objective: To automatically segment cell nuclei in histology images of bladder and skin tissue for karyometric analysis. Materials/Methods: The four main steps in the program were as follows: 1) median filtering and thresholding, 2) segmentation, 3) categorizing, and 4) cusp correction. This robust segmentation technique used properties of the image histogram to optimally select a threshold and create closed four-way chain code nuclei segmentations. Each cell nucleus segmentation was treated as an individual object with properties of segmentation quality. A segmentation was placed in one of the following three categories based on its properties: throw away, salvageable, or good. Erosion/dilation and rethresholding were performed on salvageable nuclei to correct cusps. Results: Ten bladder histology images were segmented both by hand and using this automatic segmention algorithm. The automatic segmentation resulted in a sensitivity of 76.4%. The average difference between hand and automatic segmentations over 42 nuclei, calculated for each of the 95 features used in karyometric analysis, ranged between 0 and 48.3%, with an average of 2.8%. The same procedure was performed on 10 skin histology images with a sensitivity of 83.0%. Average differences over 44 nuclei ranged between 0 and 200%, with an average of 10.0%. 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. Average differences between hand and automatic segmentations were smaller in bladder histology images because these images contained less contrast, and therefore the range of the karyometric feature values was smaller.

AB - Objective: To automatically segment cell nuclei in histology images of bladder and skin tissue for karyometric analysis. Materials/Methods: The four main steps in the program were as follows: 1) median filtering and thresholding, 2) segmentation, 3) categorizing, and 4) cusp correction. This robust segmentation technique used properties of the image histogram to optimally select a threshold and create closed four-way chain code nuclei segmentations. Each cell nucleus segmentation was treated as an individual object with properties of segmentation quality. A segmentation was placed in one of the following three categories based on its properties: throw away, salvageable, or good. Erosion/dilation and rethresholding were performed on salvageable nuclei to correct cusps. Results: Ten bladder histology images were segmented both by hand and using this automatic segmention algorithm. The automatic segmentation resulted in a sensitivity of 76.4%. The average difference between hand and automatic segmentations over 42 nuclei, calculated for each of the 95 features used in karyometric analysis, ranged between 0 and 48.3%, with an average of 2.8%. The same procedure was performed on 10 skin histology images with a sensitivity of 83.0%. Average differences over 44 nuclei ranged between 0 and 200%, with an average of 10.0%. 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. Average differences between hand and automatic segmentations were smaller in bladder histology images because these images contained less contrast, and therefore the range of the karyometric feature values was smaller.

KW - Bladder

KW - Karyometry

KW - Nuclei

KW - Segmentation

KW - Skin

UR - http://www.scopus.com/inward/record.url?scp=84898833576&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84898833576&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84898833576

SN - 9780819467713

BT - Optics InfoBase Conference Papers

PB - Optical Society of America

ER -