Segmentation of confocal microscope images of cell nuclei in thick tissue sections

Carlos Ortiz De Solórzano, E. García Rodriguez, A. Jones, D. Pinkel, Joe Gray, D. Sudar, S. J. Lockett

Research output: Contribution to journalArticle

121 Citations (Scopus)

Abstract

Segmentation of intact cell nuclei from three-dimensional (3D) images of thick tissue sections is an important basic capability necessary for many biological research studies. However, segmentation is often difficult because of the tight clustering of nuclei in many specimen types. We present a 3D segmentation approach that combines the recognition capabilities of the human visual system with the efficiency of automatic image analysis algorithms. The approach first uses automatic algorithms to separate the 3D image into regions of fluorescence-stained nuclei and unstained background. This includes a novel step, based on the Hough transform and an automatic focusing algorithm to estimate the size of nuclei. Then, using an interactive display, each nuclear region is shown to the analyst, who classifies it as either an individual nucleus, a cluster of multiple nuclei, partial nucleus or debris. Next, automatic image analysis based on morphological reconstruction and the watershed algorithm divides clusters into smaller objects, which are reclassified by the analyst. Once no more clusters remain, the analyst indicates which partial nuclei should be joined to form complete nuclei. The approach was assessed by calculating the fraction of correctly segmented nuclei for a variety of tissue types: Caenorhabditis elegans embryos (839 correct out of a total of 848), normal human skin (343/362), benign human breast tissue (492/525) a human breast cancer cell line grown as a xenograft in mice (425/479) and invasive human breast carcinoma (260/335). Furthermore, due to the analyst's involvement in the segmentation process, it is always known which nuclei in a population are correctly segmented and which not, assuming that the analyst's visual judgement is correct.

Original languageEnglish (US)
Pages (from-to)212-226
Number of pages15
JournalJournal of Microscopy
Volume193
Issue number3
DOIs
StatePublished - 1999
Externally publishedYes

Fingerprint

Cell Nucleus
Microscopes
microscopes
Cells
Tissue
nuclei
Image analysis
Hough transforms
Breast Neoplasms
breast
Watersheds
Debris
Three-Dimensional Imaging
Caenorhabditis elegans
Skin
Heterografts
Fluorescence
Display devices
image analysis
Cluster Analysis

Keywords

  • Confocal microscopy
  • Image analysis
  • Image segmentation
  • Three-dimensional analysis

ASJC Scopus subject areas

  • Instrumentation

Cite this

Ortiz De Solórzano, C., García Rodriguez, E., Jones, A., Pinkel, D., Gray, J., Sudar, D., & Lockett, S. J. (1999). Segmentation of confocal microscope images of cell nuclei in thick tissue sections. Journal of Microscopy, 193(3), 212-226. https://doi.org/10.1046/j.1365-2818.1999.00463.x

Segmentation of confocal microscope images of cell nuclei in thick tissue sections. / Ortiz De Solórzano, Carlos; García Rodriguez, E.; Jones, A.; Pinkel, D.; Gray, Joe; Sudar, D.; Lockett, S. J.

In: Journal of Microscopy, Vol. 193, No. 3, 1999, p. 212-226.

Research output: Contribution to journalArticle

Ortiz De Solórzano, C, García Rodriguez, E, Jones, A, Pinkel, D, Gray, J, Sudar, D & Lockett, SJ 1999, 'Segmentation of confocal microscope images of cell nuclei in thick tissue sections', Journal of Microscopy, vol. 193, no. 3, pp. 212-226. https://doi.org/10.1046/j.1365-2818.1999.00463.x
Ortiz De Solórzano, Carlos ; García Rodriguez, E. ; Jones, A. ; Pinkel, D. ; Gray, Joe ; Sudar, D. ; Lockett, S. J. / Segmentation of confocal microscope images of cell nuclei in thick tissue sections. In: Journal of Microscopy. 1999 ; Vol. 193, No. 3. pp. 212-226.
@article{8acb679f8fc643d1bb516f2e8f8bfcaf,
title = "Segmentation of confocal microscope images of cell nuclei in thick tissue sections",
abstract = "Segmentation of intact cell nuclei from three-dimensional (3D) images of thick tissue sections is an important basic capability necessary for many biological research studies. However, segmentation is often difficult because of the tight clustering of nuclei in many specimen types. We present a 3D segmentation approach that combines the recognition capabilities of the human visual system with the efficiency of automatic image analysis algorithms. The approach first uses automatic algorithms to separate the 3D image into regions of fluorescence-stained nuclei and unstained background. This includes a novel step, based on the Hough transform and an automatic focusing algorithm to estimate the size of nuclei. Then, using an interactive display, each nuclear region is shown to the analyst, who classifies it as either an individual nucleus, a cluster of multiple nuclei, partial nucleus or debris. Next, automatic image analysis based on morphological reconstruction and the watershed algorithm divides clusters into smaller objects, which are reclassified by the analyst. Once no more clusters remain, the analyst indicates which partial nuclei should be joined to form complete nuclei. The approach was assessed by calculating the fraction of correctly segmented nuclei for a variety of tissue types: Caenorhabditis elegans embryos (839 correct out of a total of 848), normal human skin (343/362), benign human breast tissue (492/525) a human breast cancer cell line grown as a xenograft in mice (425/479) and invasive human breast carcinoma (260/335). Furthermore, due to the analyst's involvement in the segmentation process, it is always known which nuclei in a population are correctly segmented and which not, assuming that the analyst's visual judgement is correct.",
keywords = "Confocal microscopy, Image analysis, Image segmentation, Three-dimensional analysis",
author = "{Ortiz De Sol{\'o}rzano}, Carlos and {Garc{\'i}a Rodriguez}, E. and A. Jones and D. Pinkel and Joe Gray and D. Sudar and Lockett, {S. J.}",
year = "1999",
doi = "10.1046/j.1365-2818.1999.00463.x",
language = "English (US)",
volume = "193",
pages = "212--226",
journal = "Journal of Microscopy",
issn = "0022-2720",
publisher = "Wiley-Blackwell",
number = "3",

}

TY - JOUR

T1 - Segmentation of confocal microscope images of cell nuclei in thick tissue sections

AU - Ortiz De Solórzano, Carlos

AU - García Rodriguez, E.

AU - Jones, A.

AU - Pinkel, D.

AU - Gray, Joe

AU - Sudar, D.

AU - Lockett, S. J.

PY - 1999

Y1 - 1999

N2 - Segmentation of intact cell nuclei from three-dimensional (3D) images of thick tissue sections is an important basic capability necessary for many biological research studies. However, segmentation is often difficult because of the tight clustering of nuclei in many specimen types. We present a 3D segmentation approach that combines the recognition capabilities of the human visual system with the efficiency of automatic image analysis algorithms. The approach first uses automatic algorithms to separate the 3D image into regions of fluorescence-stained nuclei and unstained background. This includes a novel step, based on the Hough transform and an automatic focusing algorithm to estimate the size of nuclei. Then, using an interactive display, each nuclear region is shown to the analyst, who classifies it as either an individual nucleus, a cluster of multiple nuclei, partial nucleus or debris. Next, automatic image analysis based on morphological reconstruction and the watershed algorithm divides clusters into smaller objects, which are reclassified by the analyst. Once no more clusters remain, the analyst indicates which partial nuclei should be joined to form complete nuclei. The approach was assessed by calculating the fraction of correctly segmented nuclei for a variety of tissue types: Caenorhabditis elegans embryos (839 correct out of a total of 848), normal human skin (343/362), benign human breast tissue (492/525) a human breast cancer cell line grown as a xenograft in mice (425/479) and invasive human breast carcinoma (260/335). Furthermore, due to the analyst's involvement in the segmentation process, it is always known which nuclei in a population are correctly segmented and which not, assuming that the analyst's visual judgement is correct.

AB - Segmentation of intact cell nuclei from three-dimensional (3D) images of thick tissue sections is an important basic capability necessary for many biological research studies. However, segmentation is often difficult because of the tight clustering of nuclei in many specimen types. We present a 3D segmentation approach that combines the recognition capabilities of the human visual system with the efficiency of automatic image analysis algorithms. The approach first uses automatic algorithms to separate the 3D image into regions of fluorescence-stained nuclei and unstained background. This includes a novel step, based on the Hough transform and an automatic focusing algorithm to estimate the size of nuclei. Then, using an interactive display, each nuclear region is shown to the analyst, who classifies it as either an individual nucleus, a cluster of multiple nuclei, partial nucleus or debris. Next, automatic image analysis based on morphological reconstruction and the watershed algorithm divides clusters into smaller objects, which are reclassified by the analyst. Once no more clusters remain, the analyst indicates which partial nuclei should be joined to form complete nuclei. The approach was assessed by calculating the fraction of correctly segmented nuclei for a variety of tissue types: Caenorhabditis elegans embryos (839 correct out of a total of 848), normal human skin (343/362), benign human breast tissue (492/525) a human breast cancer cell line grown as a xenograft in mice (425/479) and invasive human breast carcinoma (260/335). Furthermore, due to the analyst's involvement in the segmentation process, it is always known which nuclei in a population are correctly segmented and which not, assuming that the analyst's visual judgement is correct.

KW - Confocal microscopy

KW - Image analysis

KW - Image segmentation

KW - Three-dimensional analysis

UR - http://www.scopus.com/inward/record.url?scp=0032966937&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032966937&partnerID=8YFLogxK

U2 - 10.1046/j.1365-2818.1999.00463.x

DO - 10.1046/j.1365-2818.1999.00463.x

M3 - Article

C2 - 10199001

AN - SCOPUS:0032966937

VL - 193

SP - 212

EP - 226

JO - Journal of Microscopy

JF - Journal of Microscopy

SN - 0022-2720

IS - 3

ER -