Segmentation of 3D microscopy data with an energy based interaction model

Michele Ceccarelli, Vincenzo Paduano, Carlo Sansone

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

4 Citations (Scopus)

Abstract

Biological imaging has recently received a strong impulse by the development of fluorescent probes and new high-resolution microscopes. It is presently having a profound impact on the way research is being conducted in the life sciences. Biologists can now visualize subcellular components and processes in vivo, both structurally and functionally. Observations can be made in two or three dimensions, at different wavelengths (spectroscopy), possibly with time-lapse imaging to investigate cellular dynamics. The observation of many biological processes relies on the ability to identify and locate specific proteins within their cellular environment. High content screening is the combination of modern cell biology, with all its molecular tools, with automated high resolution microscopy and robotic handling. Image analysis is then used to measure changes in properties of the cells caused by external treatment such as chemical inhibitors or RNA interference. Therefore the methods for automatically determine and measure the number and shape of cells within a given multichannel image constitute a basic step in much of the applications of high throughput screening. Here the problem of a fully automatic segmentation of 3D high throughput images is approached. The adopted method is an extension to the three dimensional domain of a recently proposed energy based method. This is a two step process, first there is the detection of nuclei and then an energy based surface evolution approach tries to separate the surfaces of the various cells in the image. The adopted energy model is an adaptation of the repulsion competition approach, already proposed in a two-dimensional framework by Yan, Zhou and Shah Here we use a different nucleus identification method suited for three dimensional images and an efficient extension of the level set surface evolution algorithm. Experimental results on samples of the HeLa cell image database are reported.

Original languageEnglish
Title of host publication2009 IEEE International Workshop on Medical Measurements and Applications, MeMeA 2009
Pages223-228
Number of pages6
DOIs
Publication statusPublished - 23 Nov 2009
Externally publishedYes
Event2009 IEEE International Workshop on Medical Measurements and Applications, MeMeA 2009 - Cetraro, Italy
Duration: 29 May 200930 May 2009

Other

Other2009 IEEE International Workshop on Medical Measurements and Applications, MeMeA 2009
CountryItaly
CityCetraro
Period29/5/0930/5/09

Fingerprint

Microscopy
Microscopic examination
Screening
Throughput
Cytology
Imaging techniques
Time-Lapse Imaging
RNA
Biological Phenomena
Image analysis
Three-Dimensional Imaging
Biological Science Disciplines
Cell Shape
Robotics
Microscopes
RNA Interference
Fluorescent Dyes
HeLa Cells
Spectroscopy
Proteins

ASJC Scopus subject areas

  • Biomedical Engineering
  • Electrical and Electronic Engineering
  • Radiology Nuclear Medicine and imaging

Cite this

Ceccarelli, M., Paduano, V., & Sansone, C. (2009). Segmentation of 3D microscopy data with an energy based interaction model. In 2009 IEEE International Workshop on Medical Measurements and Applications, MeMeA 2009 (pp. 223-228). [5167989] https://doi.org/10.1109/MEMEA.2009.5167989

Segmentation of 3D microscopy data with an energy based interaction model. / Ceccarelli, Michele; Paduano, Vincenzo; Sansone, Carlo.

2009 IEEE International Workshop on Medical Measurements and Applications, MeMeA 2009. 2009. p. 223-228 5167989.

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

Ceccarelli, M, Paduano, V & Sansone, C 2009, Segmentation of 3D microscopy data with an energy based interaction model. in 2009 IEEE International Workshop on Medical Measurements and Applications, MeMeA 2009., 5167989, pp. 223-228, 2009 IEEE International Workshop on Medical Measurements and Applications, MeMeA 2009, Cetraro, Italy, 29/5/09. https://doi.org/10.1109/MEMEA.2009.5167989
Ceccarelli M, Paduano V, Sansone C. Segmentation of 3D microscopy data with an energy based interaction model. In 2009 IEEE International Workshop on Medical Measurements and Applications, MeMeA 2009. 2009. p. 223-228. 5167989 https://doi.org/10.1109/MEMEA.2009.5167989
Ceccarelli, Michele ; Paduano, Vincenzo ; Sansone, Carlo. / Segmentation of 3D microscopy data with an energy based interaction model. 2009 IEEE International Workshop on Medical Measurements and Applications, MeMeA 2009. 2009. pp. 223-228
@inproceedings{efe4f2ccffaf4f0f8f25bdc4061c9c70,
title = "Segmentation of 3D microscopy data with an energy based interaction model",
abstract = "Biological imaging has recently received a strong impulse by the development of fluorescent probes and new high-resolution microscopes. It is presently having a profound impact on the way research is being conducted in the life sciences. Biologists can now visualize subcellular components and processes in vivo, both structurally and functionally. Observations can be made in two or three dimensions, at different wavelengths (spectroscopy), possibly with time-lapse imaging to investigate cellular dynamics. The observation of many biological processes relies on the ability to identify and locate specific proteins within their cellular environment. High content screening is the combination of modern cell biology, with all its molecular tools, with automated high resolution microscopy and robotic handling. Image analysis is then used to measure changes in properties of the cells caused by external treatment such as chemical inhibitors or RNA interference. Therefore the methods for automatically determine and measure the number and shape of cells within a given multichannel image constitute a basic step in much of the applications of high throughput screening. Here the problem of a fully automatic segmentation of 3D high throughput images is approached. The adopted method is an extension to the three dimensional domain of a recently proposed energy based method. This is a two step process, first there is the detection of nuclei and then an energy based surface evolution approach tries to separate the surfaces of the various cells in the image. The adopted energy model is an adaptation of the repulsion competition approach, already proposed in a two-dimensional framework by Yan, Zhou and Shah Here we use a different nucleus identification method suited for three dimensional images and an efficient extension of the level set surface evolution algorithm. Experimental results on samples of the HeLa cell image database are reported.",
author = "Michele Ceccarelli and Vincenzo Paduano and Carlo Sansone",
year = "2009",
month = "11",
day = "23",
doi = "10.1109/MEMEA.2009.5167989",
language = "English",
isbn = "9781424435999",
pages = "223--228",
booktitle = "2009 IEEE International Workshop on Medical Measurements and Applications, MeMeA 2009",

}

TY - GEN

T1 - Segmentation of 3D microscopy data with an energy based interaction model

AU - Ceccarelli, Michele

AU - Paduano, Vincenzo

AU - Sansone, Carlo

PY - 2009/11/23

Y1 - 2009/11/23

N2 - Biological imaging has recently received a strong impulse by the development of fluorescent probes and new high-resolution microscopes. It is presently having a profound impact on the way research is being conducted in the life sciences. Biologists can now visualize subcellular components and processes in vivo, both structurally and functionally. Observations can be made in two or three dimensions, at different wavelengths (spectroscopy), possibly with time-lapse imaging to investigate cellular dynamics. The observation of many biological processes relies on the ability to identify and locate specific proteins within their cellular environment. High content screening is the combination of modern cell biology, with all its molecular tools, with automated high resolution microscopy and robotic handling. Image analysis is then used to measure changes in properties of the cells caused by external treatment such as chemical inhibitors or RNA interference. Therefore the methods for automatically determine and measure the number and shape of cells within a given multichannel image constitute a basic step in much of the applications of high throughput screening. Here the problem of a fully automatic segmentation of 3D high throughput images is approached. The adopted method is an extension to the three dimensional domain of a recently proposed energy based method. This is a two step process, first there is the detection of nuclei and then an energy based surface evolution approach tries to separate the surfaces of the various cells in the image. The adopted energy model is an adaptation of the repulsion competition approach, already proposed in a two-dimensional framework by Yan, Zhou and Shah Here we use a different nucleus identification method suited for three dimensional images and an efficient extension of the level set surface evolution algorithm. Experimental results on samples of the HeLa cell image database are reported.

AB - Biological imaging has recently received a strong impulse by the development of fluorescent probes and new high-resolution microscopes. It is presently having a profound impact on the way research is being conducted in the life sciences. Biologists can now visualize subcellular components and processes in vivo, both structurally and functionally. Observations can be made in two or three dimensions, at different wavelengths (spectroscopy), possibly with time-lapse imaging to investigate cellular dynamics. The observation of many biological processes relies on the ability to identify and locate specific proteins within their cellular environment. High content screening is the combination of modern cell biology, with all its molecular tools, with automated high resolution microscopy and robotic handling. Image analysis is then used to measure changes in properties of the cells caused by external treatment such as chemical inhibitors or RNA interference. Therefore the methods for automatically determine and measure the number and shape of cells within a given multichannel image constitute a basic step in much of the applications of high throughput screening. Here the problem of a fully automatic segmentation of 3D high throughput images is approached. The adopted method is an extension to the three dimensional domain of a recently proposed energy based method. This is a two step process, first there is the detection of nuclei and then an energy based surface evolution approach tries to separate the surfaces of the various cells in the image. The adopted energy model is an adaptation of the repulsion competition approach, already proposed in a two-dimensional framework by Yan, Zhou and Shah Here we use a different nucleus identification method suited for three dimensional images and an efficient extension of the level set surface evolution algorithm. Experimental results on samples of the HeLa cell image database are reported.

UR - http://www.scopus.com/inward/record.url?scp=70449638624&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70449638624&partnerID=8YFLogxK

U2 - 10.1109/MEMEA.2009.5167989

DO - 10.1109/MEMEA.2009.5167989

M3 - Conference contribution

SN - 9781424435999

SP - 223

EP - 228

BT - 2009 IEEE International Workshop on Medical Measurements and Applications, MeMeA 2009

ER -