Screening of apoptotic genes by morphological analysis of high throughput fluorescence microscopy images

Yongsu Chae, Soo Jung Kim, Desok Kim

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

2 Citations (Scopus)

Abstract

Apoptosis is a programmed cell death required for development and maintenance of normal tissue. However, cancer cells often evade apoptosis by inactivating apoptotic genes. Thus, the discovery of apoptotic genes has become important in cancer research. We developed a morphological analysis to quantify apoptosis automatically. Cellular images were acquired by high throughput fluorescence microscopy and normalized. Nuclear and chromatin images were segmented by tophat operations and touching nuclei were further separated by erosion, labeling, and conditional dilation. Shape and intensity features were extracted from nuclear and chromatin images to produce discriminant functions by logistic regression. Nuclear objects were classified as isolated and touching with 91.7% accuracy. Apoptotic and mitotic nuclei were identified with 88.8% accuracy. Automatic apoptotic rates were highly correlated with manual rates (ρ = 0.91, p

Original languageEnglish (US)
Title of host publicationProceedings of the Frontiers in the Convergence of Bioscience and Information Technologies, FBIT 2007
Pages16-20
Number of pages5
DOIs
StatePublished - 2007
Externally publishedYes
EventFrontiers in the Convergence of Bioscience and Information Technologies, FBIT 2007 - Jeju Island, Korea, Republic of
Duration: Oct 11 2007Oct 13 2007

Other

OtherFrontiers in the Convergence of Bioscience and Information Technologies, FBIT 2007
CountryKorea, Republic of
CityJeju Island
Period10/11/0710/13/07

Fingerprint

Fluorescence microscopy
Cell death
Screening
Genes
Throughput
Labeling
Logistics
Erosion
Cells
Tissue

ASJC Scopus subject areas

  • Computer Science Applications
  • Information Systems

Cite this

Chae, Y., Kim, S. J., & Kim, D. (2007). Screening of apoptotic genes by morphological analysis of high throughput fluorescence microscopy images. In Proceedings of the Frontiers in the Convergence of Bioscience and Information Technologies, FBIT 2007 (pp. 16-20). [4524072] https://doi.org/10.1109/FBIT.2007.46

Screening of apoptotic genes by morphological analysis of high throughput fluorescence microscopy images. / Chae, Yongsu; Kim, Soo Jung; Kim, Desok.

Proceedings of the Frontiers in the Convergence of Bioscience and Information Technologies, FBIT 2007. 2007. p. 16-20 4524072.

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

Chae, Y, Kim, SJ & Kim, D 2007, Screening of apoptotic genes by morphological analysis of high throughput fluorescence microscopy images. in Proceedings of the Frontiers in the Convergence of Bioscience and Information Technologies, FBIT 2007., 4524072, pp. 16-20, Frontiers in the Convergence of Bioscience and Information Technologies, FBIT 2007, Jeju Island, Korea, Republic of, 10/11/07. https://doi.org/10.1109/FBIT.2007.46
Chae Y, Kim SJ, Kim D. Screening of apoptotic genes by morphological analysis of high throughput fluorescence microscopy images. In Proceedings of the Frontiers in the Convergence of Bioscience and Information Technologies, FBIT 2007. 2007. p. 16-20. 4524072 https://doi.org/10.1109/FBIT.2007.46
Chae, Yongsu ; Kim, Soo Jung ; Kim, Desok. / Screening of apoptotic genes by morphological analysis of high throughput fluorescence microscopy images. Proceedings of the Frontiers in the Convergence of Bioscience and Information Technologies, FBIT 2007. 2007. pp. 16-20
@inproceedings{fd1a93bb2a4a486d8e069407b0219fd8,
title = "Screening of apoptotic genes by morphological analysis of high throughput fluorescence microscopy images",
abstract = "Apoptosis is a programmed cell death required for development and maintenance of normal tissue. However, cancer cells often evade apoptosis by inactivating apoptotic genes. Thus, the discovery of apoptotic genes has become important in cancer research. We developed a morphological analysis to quantify apoptosis automatically. Cellular images were acquired by high throughput fluorescence microscopy and normalized. Nuclear and chromatin images were segmented by tophat operations and touching nuclei were further separated by erosion, labeling, and conditional dilation. Shape and intensity features were extracted from nuclear and chromatin images to produce discriminant functions by logistic regression. Nuclear objects were classified as isolated and touching with 91.7{\%} accuracy. Apoptotic and mitotic nuclei were identified with 88.8{\%} accuracy. Automatic apoptotic rates were highly correlated with manual rates (ρ = 0.91, p",
author = "Yongsu Chae and Kim, {Soo Jung} and Desok Kim",
year = "2007",
doi = "10.1109/FBIT.2007.46",
language = "English (US)",
isbn = "0769529992",
pages = "16--20",
booktitle = "Proceedings of the Frontiers in the Convergence of Bioscience and Information Technologies, FBIT 2007",

}

TY - GEN

T1 - Screening of apoptotic genes by morphological analysis of high throughput fluorescence microscopy images

AU - Chae, Yongsu

AU - Kim, Soo Jung

AU - Kim, Desok

PY - 2007

Y1 - 2007

N2 - Apoptosis is a programmed cell death required for development and maintenance of normal tissue. However, cancer cells often evade apoptosis by inactivating apoptotic genes. Thus, the discovery of apoptotic genes has become important in cancer research. We developed a morphological analysis to quantify apoptosis automatically. Cellular images were acquired by high throughput fluorescence microscopy and normalized. Nuclear and chromatin images were segmented by tophat operations and touching nuclei were further separated by erosion, labeling, and conditional dilation. Shape and intensity features were extracted from nuclear and chromatin images to produce discriminant functions by logistic regression. Nuclear objects were classified as isolated and touching with 91.7% accuracy. Apoptotic and mitotic nuclei were identified with 88.8% accuracy. Automatic apoptotic rates were highly correlated with manual rates (ρ = 0.91, p

AB - Apoptosis is a programmed cell death required for development and maintenance of normal tissue. However, cancer cells often evade apoptosis by inactivating apoptotic genes. Thus, the discovery of apoptotic genes has become important in cancer research. We developed a morphological analysis to quantify apoptosis automatically. Cellular images were acquired by high throughput fluorescence microscopy and normalized. Nuclear and chromatin images were segmented by tophat operations and touching nuclei were further separated by erosion, labeling, and conditional dilation. Shape and intensity features were extracted from nuclear and chromatin images to produce discriminant functions by logistic regression. Nuclear objects were classified as isolated and touching with 91.7% accuracy. Apoptotic and mitotic nuclei were identified with 88.8% accuracy. Automatic apoptotic rates were highly correlated with manual rates (ρ = 0.91, p

UR - http://www.scopus.com/inward/record.url?scp=49349094505&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=49349094505&partnerID=8YFLogxK

U2 - 10.1109/FBIT.2007.46

DO - 10.1109/FBIT.2007.46

M3 - Conference contribution

AN - SCOPUS:49349094505

SN - 0769529992

SN - 9780769529998

SP - 16

EP - 20

BT - Proceedings of the Frontiers in the Convergence of Bioscience and Information Technologies, FBIT 2007

ER -