Automatic cell segmentation in fluorescence images of conuent cell monolayers using multi-object geometric deformable model

Zhen Yang, John A. Bogovic, Aaron Carass, Mao Ye, Peter C. Searson, Jerry Ladd Prince

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

Abstract

With the rapid development of microscopy for cell imaging, there is a strong and growing demand for image analysis software to quantitatively study cell morphology. Automatic cell segmentation is an important step in image analysis. Despite substantial progress, there is still a need to improve the accuracy, efficiency, and adaptability to different cell morphologies. In this paper, we propose a fully automatic method for segmenting cells in uorescence images of conuent cell monolayers. This method addresses several challenges through a combination of ideas. 1) It realizes a fully automatic segmentation process by first detecting the cell nuclei as initial seeds and then using a multi-object geometric deformable model (MGDM) for final segmentation. 2) To deal with different defects in the uorescence images, the cell junctions are enhanced by applying an orderstatistic filter and principal curvature based image operator. 3) The final segmentation using MGDM promotes robust and accurate segmentation results, and guarantees no overlaps and gaps between neighboring cells. The automatic segmentation results are compared with manually delineated cells, and the average Dice coefficient over all distinguishable cells is 0:88.

Original languageEnglish (US)
Title of host publicationProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume8669
DOIs
StatePublished - 2013
EventMedical Imaging 2013: Image Processing - Lake Buena Vista, FL, United States
Duration: Feb 10 2013Feb 12 2013

Other

OtherMedical Imaging 2013: Image Processing
CountryUnited States
CityLake Buena Vista, FL
Period2/10/132/12/13

Fingerprint

Image analysis
Monolayers
Fluorescence
fluorescence
cells
Microscopic examination
Cells
Imaging techniques
Defects
image analysis
Intercellular Junctions
Cell Nucleus
Microscopy
Software
seeds
curvature
microscopy
computer programs
filters
operators

Keywords

  • Cell junction network
  • Cell nuclei
  • Cell segmentation
  • Immunouorescence microscopy
  • Multi-object geometric deformable model (MGDM)

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics
  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Radiology Nuclear Medicine and imaging

Cite this

Yang, Z., Bogovic, J. A., Carass, A., Ye, M., Searson, P. C., & Prince, J. L. (2013). Automatic cell segmentation in fluorescence images of conuent cell monolayers using multi-object geometric deformable model. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE (Vol. 8669). [866904] https://doi.org/10.1117/12.2006603

Automatic cell segmentation in fluorescence images of conuent cell monolayers using multi-object geometric deformable model. / Yang, Zhen; Bogovic, John A.; Carass, Aaron; Ye, Mao; Searson, Peter C.; Prince, Jerry Ladd.

Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 8669 2013. 866904.

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

Yang, Z, Bogovic, JA, Carass, A, Ye, M, Searson, PC & Prince, JL 2013, Automatic cell segmentation in fluorescence images of conuent cell monolayers using multi-object geometric deformable model. in Progress in Biomedical Optics and Imaging - Proceedings of SPIE. vol. 8669, 866904, Medical Imaging 2013: Image Processing, Lake Buena Vista, FL, United States, 2/10/13. https://doi.org/10.1117/12.2006603
Yang Z, Bogovic JA, Carass A, Ye M, Searson PC, Prince JL. Automatic cell segmentation in fluorescence images of conuent cell monolayers using multi-object geometric deformable model. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 8669. 2013. 866904 https://doi.org/10.1117/12.2006603
Yang, Zhen ; Bogovic, John A. ; Carass, Aaron ; Ye, Mao ; Searson, Peter C. ; Prince, Jerry Ladd. / Automatic cell segmentation in fluorescence images of conuent cell monolayers using multi-object geometric deformable model. Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 8669 2013.
@inproceedings{da7265fb8798420d851f301756e1d54b,
title = "Automatic cell segmentation in fluorescence images of conuent cell monolayers using multi-object geometric deformable model",
abstract = "With the rapid development of microscopy for cell imaging, there is a strong and growing demand for image analysis software to quantitatively study cell morphology. Automatic cell segmentation is an important step in image analysis. Despite substantial progress, there is still a need to improve the accuracy, efficiency, and adaptability to different cell morphologies. In this paper, we propose a fully automatic method for segmenting cells in uorescence images of conuent cell monolayers. This method addresses several challenges through a combination of ideas. 1) It realizes a fully automatic segmentation process by first detecting the cell nuclei as initial seeds and then using a multi-object geometric deformable model (MGDM) for final segmentation. 2) To deal with different defects in the uorescence images, the cell junctions are enhanced by applying an orderstatistic filter and principal curvature based image operator. 3) The final segmentation using MGDM promotes robust and accurate segmentation results, and guarantees no overlaps and gaps between neighboring cells. The automatic segmentation results are compared with manually delineated cells, and the average Dice coefficient over all distinguishable cells is 0:88.",
keywords = "Cell junction network, Cell nuclei, Cell segmentation, Immunouorescence microscopy, Multi-object geometric deformable model (MGDM)",
author = "Zhen Yang and Bogovic, {John A.} and Aaron Carass and Mao Ye and Searson, {Peter C.} and Prince, {Jerry Ladd}",
year = "2013",
doi = "10.1117/12.2006603",
language = "English (US)",
isbn = "9780819494436",
volume = "8669",
booktitle = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

}

TY - GEN

T1 - Automatic cell segmentation in fluorescence images of conuent cell monolayers using multi-object geometric deformable model

AU - Yang, Zhen

AU - Bogovic, John A.

AU - Carass, Aaron

AU - Ye, Mao

AU - Searson, Peter C.

AU - Prince, Jerry Ladd

PY - 2013

Y1 - 2013

N2 - With the rapid development of microscopy for cell imaging, there is a strong and growing demand for image analysis software to quantitatively study cell morphology. Automatic cell segmentation is an important step in image analysis. Despite substantial progress, there is still a need to improve the accuracy, efficiency, and adaptability to different cell morphologies. In this paper, we propose a fully automatic method for segmenting cells in uorescence images of conuent cell monolayers. This method addresses several challenges through a combination of ideas. 1) It realizes a fully automatic segmentation process by first detecting the cell nuclei as initial seeds and then using a multi-object geometric deformable model (MGDM) for final segmentation. 2) To deal with different defects in the uorescence images, the cell junctions are enhanced by applying an orderstatistic filter and principal curvature based image operator. 3) The final segmentation using MGDM promotes robust and accurate segmentation results, and guarantees no overlaps and gaps between neighboring cells. The automatic segmentation results are compared with manually delineated cells, and the average Dice coefficient over all distinguishable cells is 0:88.

AB - With the rapid development of microscopy for cell imaging, there is a strong and growing demand for image analysis software to quantitatively study cell morphology. Automatic cell segmentation is an important step in image analysis. Despite substantial progress, there is still a need to improve the accuracy, efficiency, and adaptability to different cell morphologies. In this paper, we propose a fully automatic method for segmenting cells in uorescence images of conuent cell monolayers. This method addresses several challenges through a combination of ideas. 1) It realizes a fully automatic segmentation process by first detecting the cell nuclei as initial seeds and then using a multi-object geometric deformable model (MGDM) for final segmentation. 2) To deal with different defects in the uorescence images, the cell junctions are enhanced by applying an orderstatistic filter and principal curvature based image operator. 3) The final segmentation using MGDM promotes robust and accurate segmentation results, and guarantees no overlaps and gaps between neighboring cells. The automatic segmentation results are compared with manually delineated cells, and the average Dice coefficient over all distinguishable cells is 0:88.

KW - Cell junction network

KW - Cell nuclei

KW - Cell segmentation

KW - Immunouorescence microscopy

KW - Multi-object geometric deformable model (MGDM)

UR - http://www.scopus.com/inward/record.url?scp=84878280611&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84878280611&partnerID=8YFLogxK

U2 - 10.1117/12.2006603

DO - 10.1117/12.2006603

M3 - Conference contribution

AN - SCOPUS:84878280611

SN - 9780819494436

VL - 8669

BT - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

ER -