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

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

doi:10.1117/12.728607

13 July 2007 Automatic segmentation of cell nuclei in bladder and skin tissue for karyometric analysis

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

Proceedings Volume 6633, Biophotonics 2007: Optics in Life Science; 66330V (2007) https://doi.org/10.1117/12.728607
Event: European Conferences on Biomedical Optics, 2007, Munich, Germany

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.

Citation Download Citation

Vrushali R. Korde, Hubert Bartels, James Ranger-Moore, and Jennifer Barton "Automatic segmentation of cell nuclei in bladder and skin tissue for karyometric analysis", Proc. SPIE 6633, Biophotonics 2007: Optics in Life Science, 66330V (13 July 2007); https://doi.org/10.1117/12.728607

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available