Automated optimisation of cell segmentation parameters in phase contrast using discrete mereotopology

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

Standard

Automated optimisation of cell segmentation parameters in phase contrast using discrete mereotopology. / Flight, Rachel; Landini, Gabriel; Styles, Iain; Shelton, Richard; Milward, Michael; Cooper, Paul.

Proceedings of Medical Image Understanding and Analysis 2015. British Machine Vision Association, 2015. p. 126-131.

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

Harvard

Flight, R, Landini, G, Styles, I, Shelton, R, Milward, M & Cooper, P 2015, Automated optimisation of cell segmentation parameters in phase contrast using discrete mereotopology. in Proceedings of Medical Image Understanding and Analysis 2015. British Machine Vision Association, pp. 126-131, Medical Image Understanding and Analysis Conference (MIUA), 2015, Lincoln, United Kingdom, 15/07/15.

APA

Flight, R., Landini, G., Styles, I., Shelton, R., Milward, M., & Cooper, P. (2015). Automated optimisation of cell segmentation parameters in phase contrast using discrete mereotopology. In Proceedings of Medical Image Understanding and Analysis 2015 (pp. 126-131). British Machine Vision Association.

Vancouver

Flight R, Landini G, Styles I, Shelton R, Milward M, Cooper P. Automated optimisation of cell segmentation parameters in phase contrast using discrete mereotopology. In Proceedings of Medical Image Understanding and Analysis 2015. British Machine Vision Association. 2015. p. 126-131

Author

Flight, Rachel ; Landini, Gabriel ; Styles, Iain ; Shelton, Richard ; Milward, Michael ; Cooper, Paul. / Automated optimisation of cell segmentation parameters in phase contrast using discrete mereotopology. Proceedings of Medical Image Understanding and Analysis 2015. British Machine Vision Association, 2015. pp. 126-131

Bibtex

@inproceedings{46e2dc9887c34397b585ae9b3205a72d,
title = "Automated optimisation of cell segmentation parameters in phase contrast using discrete mereotopology",
abstract = "It has been shown previously that the number of epithelial cells in a monolayer can be determined in vitro using phase contrast microscopy by subtracting images mean-filtered with two different kernel radii and then thresholding to segment cells. Careful selection of filter sizes was essential to ensure the number of segmented regions corresponded accurately with the number of cells in the image, however manual parameter selection and verification is time-consuming and prone to human error. We propose an intelligent imaging approach for evaluating the success of filter size combinations for cell detection using discrete mereotopology to compare segmentations with ground truth binary images of stained cell nuclei. Applying this approach to phase contrast images of H400 epithelial monolayers with varying levels of confluency, a region in the parameter space could be identified where more than 90% of cells were correctly detected.",
author = "Rachel Flight and Gabriel Landini and Iain Styles and Richard Shelton and Michael Milward and Paul Cooper",
year = "2015",
language = "English",
isbn = "1-901725-54-5",
pages = "126--131",
booktitle = "Proceedings of Medical Image Understanding and Analysis 2015",
publisher = "British Machine Vision Association",
note = "Medical Image Understanding and Analysis Conference (MIUA), 2015 ; Conference date: 15-07-2015 Through 17-07-2015",

}

RIS

TY - GEN

T1 - Automated optimisation of cell segmentation parameters in phase contrast using discrete mereotopology

AU - Flight, Rachel

AU - Landini, Gabriel

AU - Styles, Iain

AU - Shelton, Richard

AU - Milward, Michael

AU - Cooper, Paul

PY - 2015

Y1 - 2015

N2 - It has been shown previously that the number of epithelial cells in a monolayer can be determined in vitro using phase contrast microscopy by subtracting images mean-filtered with two different kernel radii and then thresholding to segment cells. Careful selection of filter sizes was essential to ensure the number of segmented regions corresponded accurately with the number of cells in the image, however manual parameter selection and verification is time-consuming and prone to human error. We propose an intelligent imaging approach for evaluating the success of filter size combinations for cell detection using discrete mereotopology to compare segmentations with ground truth binary images of stained cell nuclei. Applying this approach to phase contrast images of H400 epithelial monolayers with varying levels of confluency, a region in the parameter space could be identified where more than 90% of cells were correctly detected.

AB - It has been shown previously that the number of epithelial cells in a monolayer can be determined in vitro using phase contrast microscopy by subtracting images mean-filtered with two different kernel radii and then thresholding to segment cells. Careful selection of filter sizes was essential to ensure the number of segmented regions corresponded accurately with the number of cells in the image, however manual parameter selection and verification is time-consuming and prone to human error. We propose an intelligent imaging approach for evaluating the success of filter size combinations for cell detection using discrete mereotopology to compare segmentations with ground truth binary images of stained cell nuclei. Applying this approach to phase contrast images of H400 epithelial monolayers with varying levels of confluency, a region in the parameter space could be identified where more than 90% of cells were correctly detected.

M3 - Conference contribution

SN - 1-901725-54-5

SP - 126

EP - 131

BT - Proceedings of Medical Image Understanding and Analysis 2015

PB - British Machine Vision Association

T2 - Medical Image Understanding and Analysis Conference (MIUA), 2015

Y2 - 15 July 2015 through 17 July 2015

ER -