Toward automatic phenotyping of developing embryos from videos

Feng Ning, Damien Delhomme, Yann LeCun, Fabio Piano, Léon Bottou, Paolo Emilio Barbano

Research output: Contribution to journalArticle

Abstract

We describe a trainable system for analyzing videos of developing C. elegans embryos. The system automatically detects, segments, and locates cells and nuclei in microscopic images. The system was designed as the central component of a fully automated phenotyping system. The system contains three modules 1) a convolutional network trained to classify each pixel into five categories: cell wall, cytoplasm, nucleus membrane, nucleus, outside medium; 2) an energy-based model, which cleans up the output of the convolutional network by learning local consistency constraints that must be satisfied by label images; 3) a set of elastic models of the embryo at various stages of development that are matched to the label images.

Original languageEnglish (US)
Pages (from-to)1360-1371
Number of pages12
JournalIEEE Transactions on Image Processing
Volume14
Issue number9
DOIs
StatePublished - Sep 2005

Fingerprint

Embryo
Labels
Nucleus
Pixels
Cells
Membranes
Cell Wall
Membrane
Pixel
Classify
Module
Output
Cell
Energy
Model

Keywords

  • Convolutional network
  • Energy-based model
  • Image segmentation
  • Nonlinear filter

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Graphics and Computer-Aided Design
  • Software
  • Theoretical Computer Science
  • Computational Theory and Mathematics
  • Computer Vision and Pattern Recognition

Cite this

Toward automatic phenotyping of developing embryos from videos. / Ning, Feng; Delhomme, Damien; LeCun, Yann; Piano, Fabio; Bottou, Léon; Barbano, Paolo Emilio.

In: IEEE Transactions on Image Processing, Vol. 14, No. 9, 09.2005, p. 1360-1371.

Research output: Contribution to journalArticle

Ning, Feng ; Delhomme, Damien ; LeCun, Yann ; Piano, Fabio ; Bottou, Léon ; Barbano, Paolo Emilio. / Toward automatic phenotyping of developing embryos from videos. In: IEEE Transactions on Image Processing. 2005 ; Vol. 14, No. 9. pp. 1360-1371.
@article{4079a1960a4b477f8d368fa90e71af4c,
title = "Toward automatic phenotyping of developing embryos from videos",
abstract = "We describe a trainable system for analyzing videos of developing C. elegans embryos. The system automatically detects, segments, and locates cells and nuclei in microscopic images. The system was designed as the central component of a fully automated phenotyping system. The system contains three modules 1) a convolutional network trained to classify each pixel into five categories: cell wall, cytoplasm, nucleus membrane, nucleus, outside medium; 2) an energy-based model, which cleans up the output of the convolutional network by learning local consistency constraints that must be satisfied by label images; 3) a set of elastic models of the embryo at various stages of development that are matched to the label images.",
keywords = "Convolutional network, Energy-based model, Image segmentation, Nonlinear filter",
author = "Feng Ning and Damien Delhomme and Yann LeCun and Fabio Piano and L{\'e}on Bottou and Barbano, {Paolo Emilio}",
year = "2005",
month = "9",
doi = "10.1109/TIP.2005.852470",
language = "English (US)",
volume = "14",
pages = "1360--1371",
journal = "IEEE Transactions on Image Processing",
issn = "1057-7149",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "9",

}

TY - JOUR

T1 - Toward automatic phenotyping of developing embryos from videos

AU - Ning, Feng

AU - Delhomme, Damien

AU - LeCun, Yann

AU - Piano, Fabio

AU - Bottou, Léon

AU - Barbano, Paolo Emilio

PY - 2005/9

Y1 - 2005/9

N2 - We describe a trainable system for analyzing videos of developing C. elegans embryos. The system automatically detects, segments, and locates cells and nuclei in microscopic images. The system was designed as the central component of a fully automated phenotyping system. The system contains three modules 1) a convolutional network trained to classify each pixel into five categories: cell wall, cytoplasm, nucleus membrane, nucleus, outside medium; 2) an energy-based model, which cleans up the output of the convolutional network by learning local consistency constraints that must be satisfied by label images; 3) a set of elastic models of the embryo at various stages of development that are matched to the label images.

AB - We describe a trainable system for analyzing videos of developing C. elegans embryos. The system automatically detects, segments, and locates cells and nuclei in microscopic images. The system was designed as the central component of a fully automated phenotyping system. The system contains three modules 1) a convolutional network trained to classify each pixel into five categories: cell wall, cytoplasm, nucleus membrane, nucleus, outside medium; 2) an energy-based model, which cleans up the output of the convolutional network by learning local consistency constraints that must be satisfied by label images; 3) a set of elastic models of the embryo at various stages of development that are matched to the label images.

KW - Convolutional network

KW - Energy-based model

KW - Image segmentation

KW - Nonlinear filter

UR - http://www.scopus.com/inward/record.url?scp=26444512083&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=26444512083&partnerID=8YFLogxK

U2 - 10.1109/TIP.2005.852470

DO - 10.1109/TIP.2005.852470

M3 - Article

VL - 14

SP - 1360

EP - 1371

JO - IEEE Transactions on Image Processing

JF - IEEE Transactions on Image Processing

SN - 1057-7149

IS - 9

ER -