Segmentation of image data from complex organotypic 3D models of cancer tissues with Markov random fields

Sean Robinson (Corresponding Author), Laurent Guyon, Jaakko Nevalainen, Mervi Toriseva, Malin Åkerfelt, Matthias Nees

Research output: Contribution to journalArticleScientificpeer-review

6 Citations (Scopus)

Abstract

Organotypic, three dimensional (3D) cell culture models of epithelial tumour types such as prostate cancer recapitulate key aspects of the architecture and histology of solid cancers. Morphometric analysis of multicellular 3D organoids is particularly important when additional components such as the extracellular matrix and tumour microenvironment are included in the model. The complexity of such models has so far limited their successful implementation. There is a great need for automatic, accurate and robust image segmentation tools to facilitate the analysis of such biologically relevant 3D cell culture models. We present a segmentation method based on Markov random fields (MRFs) and illustrate our method using 3D stack image data from an organotypic 3D model of prostate cancer cells co-cultured with cancer-associated fibroblasts (CAFs). The 3D segmentation output suggests that these cell types are in physical contact with each other within the model, which has important implications for tumour biology. Segmentation performance is quantified using ground truth labels and we show how each step of our method increases segmentation accuracy. We provide the ground truth labels along with the image data and code. Using independent image data we show that our segmentation method is also more generally applicable to other types of cellular microscopy and not only limited to fluorescence microscopy.
Original languageEnglish
Article numbere143798
JournalPLoS ONE
Volume10
Issue number12
DOIs
Publication statusPublished - 2015
MoE publication typeA1 Journal article-refereed

Fingerprint

Tissue
neoplasms
Tumors
Neoplasms
Prostatic Neoplasms
Cell Culture Techniques
Organoids
prostatic neoplasms
Cell culture
Tumor Microenvironment
Labels
cell culture
Fluorescence Microscopy
Extracellular Matrix
Microscopy
Cultured Cells
Histology
Fluorescence microscopy
Fibroblasts
fluorescence microscopy

Cite this

Robinson, S., Guyon, L., Nevalainen, J., Toriseva, M., Åkerfelt, M., & Nees, M. (2015). Segmentation of image data from complex organotypic 3D models of cancer tissues with Markov random fields. PLoS ONE, 10(12), [e143798]. https://doi.org/10.1371/journal.pone.0143798
Robinson, Sean ; Guyon, Laurent ; Nevalainen, Jaakko ; Toriseva, Mervi ; Åkerfelt, Malin ; Nees, Matthias. / Segmentation of image data from complex organotypic 3D models of cancer tissues with Markov random fields. In: PLoS ONE. 2015 ; Vol. 10, No. 12.
@article{18071a242909490d9da899c973625faa,
title = "Segmentation of image data from complex organotypic 3D models of cancer tissues with Markov random fields",
abstract = "Organotypic, three dimensional (3D) cell culture models of epithelial tumour types such as prostate cancer recapitulate key aspects of the architecture and histology of solid cancers. Morphometric analysis of multicellular 3D organoids is particularly important when additional components such as the extracellular matrix and tumour microenvironment are included in the model. The complexity of such models has so far limited their successful implementation. There is a great need for automatic, accurate and robust image segmentation tools to facilitate the analysis of such biologically relevant 3D cell culture models. We present a segmentation method based on Markov random fields (MRFs) and illustrate our method using 3D stack image data from an organotypic 3D model of prostate cancer cells co-cultured with cancer-associated fibroblasts (CAFs). The 3D segmentation output suggests that these cell types are in physical contact with each other within the model, which has important implications for tumour biology. Segmentation performance is quantified using ground truth labels and we show how each step of our method increases segmentation accuracy. We provide the ground truth labels along with the image data and code. Using independent image data we show that our segmentation method is also more generally applicable to other types of cellular microscopy and not only limited to fluorescence microscopy.",
author = "Sean Robinson and Laurent Guyon and Jaakko Nevalainen and Mervi Toriseva and Malin {\AA}kerfelt and Matthias Nees",
year = "2015",
doi = "10.1371/journal.pone.0143798",
language = "English",
volume = "10",
journal = "PLoS ONE",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "12",

}

Robinson, S, Guyon, L, Nevalainen, J, Toriseva, M, Åkerfelt, M & Nees, M 2015, 'Segmentation of image data from complex organotypic 3D models of cancer tissues with Markov random fields', PLoS ONE, vol. 10, no. 12, e143798. https://doi.org/10.1371/journal.pone.0143798

Segmentation of image data from complex organotypic 3D models of cancer tissues with Markov random fields. / Robinson, Sean (Corresponding Author); Guyon, Laurent; Nevalainen, Jaakko; Toriseva, Mervi; Åkerfelt, Malin; Nees, Matthias.

In: PLoS ONE, Vol. 10, No. 12, e143798, 2015.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Segmentation of image data from complex organotypic 3D models of cancer tissues with Markov random fields

AU - Robinson, Sean

AU - Guyon, Laurent

AU - Nevalainen, Jaakko

AU - Toriseva, Mervi

AU - Åkerfelt, Malin

AU - Nees, Matthias

PY - 2015

Y1 - 2015

N2 - Organotypic, three dimensional (3D) cell culture models of epithelial tumour types such as prostate cancer recapitulate key aspects of the architecture and histology of solid cancers. Morphometric analysis of multicellular 3D organoids is particularly important when additional components such as the extracellular matrix and tumour microenvironment are included in the model. The complexity of such models has so far limited their successful implementation. There is a great need for automatic, accurate and robust image segmentation tools to facilitate the analysis of such biologically relevant 3D cell culture models. We present a segmentation method based on Markov random fields (MRFs) and illustrate our method using 3D stack image data from an organotypic 3D model of prostate cancer cells co-cultured with cancer-associated fibroblasts (CAFs). The 3D segmentation output suggests that these cell types are in physical contact with each other within the model, which has important implications for tumour biology. Segmentation performance is quantified using ground truth labels and we show how each step of our method increases segmentation accuracy. We provide the ground truth labels along with the image data and code. Using independent image data we show that our segmentation method is also more generally applicable to other types of cellular microscopy and not only limited to fluorescence microscopy.

AB - Organotypic, three dimensional (3D) cell culture models of epithelial tumour types such as prostate cancer recapitulate key aspects of the architecture and histology of solid cancers. Morphometric analysis of multicellular 3D organoids is particularly important when additional components such as the extracellular matrix and tumour microenvironment are included in the model. The complexity of such models has so far limited their successful implementation. There is a great need for automatic, accurate and robust image segmentation tools to facilitate the analysis of such biologically relevant 3D cell culture models. We present a segmentation method based on Markov random fields (MRFs) and illustrate our method using 3D stack image data from an organotypic 3D model of prostate cancer cells co-cultured with cancer-associated fibroblasts (CAFs). The 3D segmentation output suggests that these cell types are in physical contact with each other within the model, which has important implications for tumour biology. Segmentation performance is quantified using ground truth labels and we show how each step of our method increases segmentation accuracy. We provide the ground truth labels along with the image data and code. Using independent image data we show that our segmentation method is also more generally applicable to other types of cellular microscopy and not only limited to fluorescence microscopy.

U2 - 10.1371/journal.pone.0143798

DO - 10.1371/journal.pone.0143798

M3 - Article

VL - 10

JO - PLoS ONE

JF - PLoS ONE

SN - 1932-6203

IS - 12

M1 - e143798

ER -