Automatic identification and delineation of germ layer components in H&E stained images of teratomas derived from human and nonhuman primate embryonic stem cells

Ramamurthy Bhagavatula, Matthew Fickus, W. Kelly, Chenlei Guo, John A. Ozolek, Carlos A. Castro, Jelena Kovacevic

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

Abstract

We present a methodology for the automatic identification and delineation of germ-layer components in H&E stained images of teratomas derived from human and nonhuman primate embryonic stem cells. A knowledge and understanding of the biology of these cells may lead to advances in tissue regeneration and repair, the treatment of genetic and developmental syndromes, and drug testing and discovery. As a teratoma is a chaotic organization of tissues derived from the three primary embryonic germ layers, H&E teratoma images often present multiple tissues, each of having complex and unpredictable positions, shapes, and appearance with respect to each individual tissue as well as with respect to other tissues. While visual identification of these tissues is timeconsuming, it is surprisingly accurate, indicating that there exist enough visual cues to accomplish the task. We propose automatic identification and delineation of these tissues by mimicking these visual cues. We use pixel-based classification, resulting in an encouraging range of classification accuracies from 74.9% to 93.2% for 2- to 5-tissue classification experiments at different scales.

Original languageEnglish (US)
Title of host publication2010 7th IEEE International Symposium on Biomedical Imaging
Subtitle of host publicationFrom Nano to Macro, ISBI 2010 - Proceedings
Pages1041-1044
Number of pages4
DOIs
StatePublished - Aug 9 2010
Event7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010 - Rotterdam, Netherlands
Duration: Apr 14 2010Apr 17 2010

Other

Other7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010
CountryNetherlands
CityRotterdam
Period4/14/104/17/10

Fingerprint

Germ Layers
Teratoma
Embryonic Stem Cells
Stem cells
Primates
Tissue
Cues
Tissue regeneration
Drug Discovery
Repair
Cell Biology
Pixels
Regeneration
Testing

Keywords

  • Classification
  • Feature extraction
  • Image analysis
  • Stem cell biology

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Cite this

Bhagavatula, R., Fickus, M., Kelly, W., Guo, C., Ozolek, J. A., Castro, C. A., & Kovacevic, J. (2010). Automatic identification and delineation of germ layer components in H&E stained images of teratomas derived from human and nonhuman primate embryonic stem cells. In 2010 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010 - Proceedings (pp. 1041-1044). [5490168] https://doi.org/10.1109/ISBI.2010.5490168

Automatic identification and delineation of germ layer components in H&E stained images of teratomas derived from human and nonhuman primate embryonic stem cells. / Bhagavatula, Ramamurthy; Fickus, Matthew; Kelly, W.; Guo, Chenlei; Ozolek, John A.; Castro, Carlos A.; Kovacevic, Jelena.

2010 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010 - Proceedings. 2010. p. 1041-1044 5490168.

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

Bhagavatula, R, Fickus, M, Kelly, W, Guo, C, Ozolek, JA, Castro, CA & Kovacevic, J 2010, Automatic identification and delineation of germ layer components in H&E stained images of teratomas derived from human and nonhuman primate embryonic stem cells. in 2010 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010 - Proceedings., 5490168, pp. 1041-1044, 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010, Rotterdam, Netherlands, 4/14/10. https://doi.org/10.1109/ISBI.2010.5490168
Bhagavatula R, Fickus M, Kelly W, Guo C, Ozolek JA, Castro CA et al. Automatic identification and delineation of germ layer components in H&E stained images of teratomas derived from human and nonhuman primate embryonic stem cells. In 2010 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010 - Proceedings. 2010. p. 1041-1044. 5490168 https://doi.org/10.1109/ISBI.2010.5490168
Bhagavatula, Ramamurthy ; Fickus, Matthew ; Kelly, W. ; Guo, Chenlei ; Ozolek, John A. ; Castro, Carlos A. ; Kovacevic, Jelena. / Automatic identification and delineation of germ layer components in H&E stained images of teratomas derived from human and nonhuman primate embryonic stem cells. 2010 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010 - Proceedings. 2010. pp. 1041-1044
@inproceedings{9097e5046e3f4ca78c388781dc98e821,
title = "Automatic identification and delineation of germ layer components in H&E stained images of teratomas derived from human and nonhuman primate embryonic stem cells",
abstract = "We present a methodology for the automatic identification and delineation of germ-layer components in H&E stained images of teratomas derived from human and nonhuman primate embryonic stem cells. A knowledge and understanding of the biology of these cells may lead to advances in tissue regeneration and repair, the treatment of genetic and developmental syndromes, and drug testing and discovery. As a teratoma is a chaotic organization of tissues derived from the three primary embryonic germ layers, H&E teratoma images often present multiple tissues, each of having complex and unpredictable positions, shapes, and appearance with respect to each individual tissue as well as with respect to other tissues. While visual identification of these tissues is timeconsuming, it is surprisingly accurate, indicating that there exist enough visual cues to accomplish the task. We propose automatic identification and delineation of these tissues by mimicking these visual cues. We use pixel-based classification, resulting in an encouraging range of classification accuracies from 74.9{\%} to 93.2{\%} for 2- to 5-tissue classification experiments at different scales.",
keywords = "Classification, Feature extraction, Image analysis, Stem cell biology",
author = "Ramamurthy Bhagavatula and Matthew Fickus and W. Kelly and Chenlei Guo and Ozolek, {John A.} and Castro, {Carlos A.} and Jelena Kovacevic",
year = "2010",
month = "8",
day = "9",
doi = "10.1109/ISBI.2010.5490168",
language = "English (US)",
isbn = "9781424441266",
pages = "1041--1044",
booktitle = "2010 7th IEEE International Symposium on Biomedical Imaging",

}

TY - GEN

T1 - Automatic identification and delineation of germ layer components in H&E stained images of teratomas derived from human and nonhuman primate embryonic stem cells

AU - Bhagavatula, Ramamurthy

AU - Fickus, Matthew

AU - Kelly, W.

AU - Guo, Chenlei

AU - Ozolek, John A.

AU - Castro, Carlos A.

AU - Kovacevic, Jelena

PY - 2010/8/9

Y1 - 2010/8/9

N2 - We present a methodology for the automatic identification and delineation of germ-layer components in H&E stained images of teratomas derived from human and nonhuman primate embryonic stem cells. A knowledge and understanding of the biology of these cells may lead to advances in tissue regeneration and repair, the treatment of genetic and developmental syndromes, and drug testing and discovery. As a teratoma is a chaotic organization of tissues derived from the three primary embryonic germ layers, H&E teratoma images often present multiple tissues, each of having complex and unpredictable positions, shapes, and appearance with respect to each individual tissue as well as with respect to other tissues. While visual identification of these tissues is timeconsuming, it is surprisingly accurate, indicating that there exist enough visual cues to accomplish the task. We propose automatic identification and delineation of these tissues by mimicking these visual cues. We use pixel-based classification, resulting in an encouraging range of classification accuracies from 74.9% to 93.2% for 2- to 5-tissue classification experiments at different scales.

AB - We present a methodology for the automatic identification and delineation of germ-layer components in H&E stained images of teratomas derived from human and nonhuman primate embryonic stem cells. A knowledge and understanding of the biology of these cells may lead to advances in tissue regeneration and repair, the treatment of genetic and developmental syndromes, and drug testing and discovery. As a teratoma is a chaotic organization of tissues derived from the three primary embryonic germ layers, H&E teratoma images often present multiple tissues, each of having complex and unpredictable positions, shapes, and appearance with respect to each individual tissue as well as with respect to other tissues. While visual identification of these tissues is timeconsuming, it is surprisingly accurate, indicating that there exist enough visual cues to accomplish the task. We propose automatic identification and delineation of these tissues by mimicking these visual cues. We use pixel-based classification, resulting in an encouraging range of classification accuracies from 74.9% to 93.2% for 2- to 5-tissue classification experiments at different scales.

KW - Classification

KW - Feature extraction

KW - Image analysis

KW - Stem cell biology

UR - http://www.scopus.com/inward/record.url?scp=77955196330&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77955196330&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2010.5490168

DO - 10.1109/ISBI.2010.5490168

M3 - Conference contribution

SN - 9781424441266

SP - 1041

EP - 1044

BT - 2010 7th IEEE International Symposium on Biomedical Imaging

ER -