Cell Division Detection on the Arabidopsis Thaliana Root

  • Authors:
  • Monica Marcuzzo;Tiago Guichard;Pedro Quelhas;Ana Maria Mendonça;Aurélio Campilho

  • Affiliations:
  • INEB - Instituto de Engenharia Biomédica, Divisão de Sinal e Imagem, Campus FEUP,;Faculdade de Engenharia Departamento de Engenharia Electrotécnica e Computadores, Universidade do Porto,;INEB - Instituto de Engenharia Biomédica, Divisão de Sinal e Imagem, Campus FEUP, and Faculdade de Engenharia Departamento de Engenharia Electrotécnica e Computadores, Universidade ...;INEB - Instituto de Engenharia Biomédica, Divisão de Sinal e Imagem, Campus FEUP, and Faculdade de Engenharia Departamento de Engenharia Electrotécnica e Computadores, Universidade ...;INEB - Instituto de Engenharia Biomédica, Divisão de Sinal e Imagem, Campus FEUP, and Faculdade de Engenharia Departamento de Engenharia Electrotécnica e Computadores, Universidade ...

  • Venue:
  • IbPRIA '09 Proceedings of the 4th Iberian Conference on Pattern Recognition and Image Analysis
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

The study of individual plant cells and their growth structure is an important focus of research in plant genetics. To obtain development information at cellular level, researchers need to perform in vivo imaging of the specimen under study, through time-lapse confocal microscopy. Within this research field it is important to understand mechanisms like cell division and elongation of developing cells. We describe a tool to automatically search for cell division in the Arabidopsis thaliana using information of nuclei shape. The nuclei detection is based on a convergence index filter. Cell division detection is performed by an automatic classifier, trained through cross-validation. The results are further improved by a stability criterion based on the Mahalanobis distance of the shape of the nuclei through time. With this approach, we can achieve a correct detection rate of 94.7%.