General Purpose Segmentation for Microorganisms in Microscopy Images

Sebastian H. Nesgaard Jensen, Thomas B. Moeslund, Christian Rankl

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

754 Downloads (Pure)

Abstract

In this paper, we propose an approach for achieving generalized segmentation of microorganisms in mi- croscopy images. It employs a pixel-wise classification strategy based on local features. Multilayer percep- trons are utilized for classification of the local features and is trained for each specific segmentation problem using supervised learning. This approach was tested on five different segmentation problems in bright field, differential interference contrast, fluorescence and laser confocal scanning microscopy. In all instance good results were achieved with the segmentation quality scoring a Dice coefficient of 0.831 or higher.
Original languageEnglish
Title of host publication9th International Conference on Computer Vision Theory and Applications
Number of pages6
PublisherInstitute for Systems and Technologies of Information, Control and Communication
Publication date2014
Publication statusPublished - 2014
EventInternational Conference on Computer Vision Theory and Applications - Lisbon, Denmark
Duration: 5 Jan 20148 Jan 2014

Conference

ConferenceInternational Conference on Computer Vision Theory and Applications
CountryDenmark
CityLisbon
Period05/01/201408/01/2014

Fingerprint

Microorganisms
Microscopic examination
Supervised learning
Multilayer neural networks
Pixels
Fluorescence
Scanning
Lasers

Cite this

Jensen, S. H. N., Moeslund, T. B., & Rankl, C. (2014). General Purpose Segmentation for Microorganisms in Microscopy Images. In 9th International Conference on Computer Vision Theory and Applications Institute for Systems and Technologies of Information, Control and Communication.
Jensen, Sebastian H. Nesgaard ; Moeslund, Thomas B. ; Rankl, Christian. / General Purpose Segmentation for Microorganisms in Microscopy Images. 9th International Conference on Computer Vision Theory and Applications . Institute for Systems and Technologies of Information, Control and Communication, 2014.
@inproceedings{685f2e87d0f34d47818144c46e0fc692,
title = "General Purpose Segmentation for Microorganisms in Microscopy Images",
abstract = "In this paper, we propose an approach for achieving generalized segmentation of microorganisms in mi- croscopy images. It employs a pixel-wise classification strategy based on local features. Multilayer percep- trons are utilized for classification of the local features and is trained for each specific segmentation problem using supervised learning. This approach was tested on five different segmentation problems in bright field, differential interference contrast, fluorescence and laser confocal scanning microscopy. In all instance good results were achieved with the segmentation quality scoring a Dice coefficient of 0.831 or higher.",
author = "Jensen, {Sebastian H. Nesgaard} and Moeslund, {Thomas B.} and Christian Rankl",
year = "2014",
language = "English",
booktitle = "9th International Conference on Computer Vision Theory and Applications",
publisher = "Institute for Systems and Technologies of Information, Control and Communication",

}

Jensen, SHN, Moeslund, TB & Rankl, C 2014, General Purpose Segmentation for Microorganisms in Microscopy Images. in 9th International Conference on Computer Vision Theory and Applications . Institute for Systems and Technologies of Information, Control and Communication, International Conference on Computer Vision Theory and Applications , Lisbon, Denmark, 05/01/2014.

General Purpose Segmentation for Microorganisms in Microscopy Images. / Jensen, Sebastian H. Nesgaard; Moeslund, Thomas B.; Rankl, Christian.

9th International Conference on Computer Vision Theory and Applications . Institute for Systems and Technologies of Information, Control and Communication, 2014.

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

TY - GEN

T1 - General Purpose Segmentation for Microorganisms in Microscopy Images

AU - Jensen, Sebastian H. Nesgaard

AU - Moeslund, Thomas B.

AU - Rankl, Christian

PY - 2014

Y1 - 2014

N2 - In this paper, we propose an approach for achieving generalized segmentation of microorganisms in mi- croscopy images. It employs a pixel-wise classification strategy based on local features. Multilayer percep- trons are utilized for classification of the local features and is trained for each specific segmentation problem using supervised learning. This approach was tested on five different segmentation problems in bright field, differential interference contrast, fluorescence and laser confocal scanning microscopy. In all instance good results were achieved with the segmentation quality scoring a Dice coefficient of 0.831 or higher.

AB - In this paper, we propose an approach for achieving generalized segmentation of microorganisms in mi- croscopy images. It employs a pixel-wise classification strategy based on local features. Multilayer percep- trons are utilized for classification of the local features and is trained for each specific segmentation problem using supervised learning. This approach was tested on five different segmentation problems in bright field, differential interference contrast, fluorescence and laser confocal scanning microscopy. In all instance good results were achieved with the segmentation quality scoring a Dice coefficient of 0.831 or higher.

M3 - Article in proceeding

BT - 9th International Conference on Computer Vision Theory and Applications

PB - Institute for Systems and Technologies of Information, Control and Communication

ER -

Jensen SHN, Moeslund TB, Rankl C. General Purpose Segmentation for Microorganisms in Microscopy Images. In 9th International Conference on Computer Vision Theory and Applications . Institute for Systems and Technologies of Information, Control and Communication. 2014