Automatic information extraction from gel electrophoresis images using GEIAS

  • Authors:

  • C. M. R. Caridade;A. R. S. Marcal;T. Mendonça;A. M. Pessoa;S. Pereira

  • Affiliations:

  • Instituto Superior de Engenharia de Coimbra, R. Pedro Nunes, Qt.Nora, Coimbra, Portugal;Dep. Matemática, Faculdade de Ciências, Univ. Porto, Porto, Portugal;Dep. Matemática, Faculdade de Ciências, Univ. Porto, Porto, Portugal;Dep. Biologia, Faculdade de Ciências, Univ. Porto, Porto, Portugal;Dep. Biologia, Faculdade de Ciências, Univ. Porto, Porto, Portugal

  • Venue:
  • ICIAR'10 Proceedings of the 7th international conference on Image Analysis and Recognition - Volume Part II
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper presents a method (GEIAS) for the automatic processing of digital images obtained from Gel Electrophoresis. The performance of GEIAS was tested using 12 images, obtained from 4 gels with 3 different exposures with a total of 1082 bands, comparing the results provided by GEIAS and 3 other software tools. The GEIAS is able to fully automatically detect DNA lanes while the other 3 software tools tested can only do this in a semi-automatic or manual way. For the correct location of DNA bands, GEIAS required a manual correction of the location in 10.0% of the bands, and the other software tools 13.0%, 15.0% and 25.4%. The average error in the estimation of molecular weight was tested using a total of 5443 bands in 12 image using 672 reference/observed lane pairs. The average error was found to be 9.2% for GEIAS and 11.2%, 14.4% and 13.1% for the other software tools tested.