Homepage | Links | Contacts

Duration: 36 months
Starting date: September 2005
Status: Concluded
Project Contact:
José Manuel Fonseca

Project Team:
José Manuel Fonseca, André Damas Mora

Scientific Advisors:
Pedro Vieira (DF-FCT-UNL)

DRUSAS - Automatic Detection of Drusens in Fundus Images - Past Research Projects
Project Summary
Drusen is a retina abnormality considered a risk factor for age-related macular degeneration (ARMD) that is one of the leading causes of blindness. It is noticed in retina images as small sized yellow spots. To evaluate therapy effectiveness ophthalmologists usually do a visual inspection what is fastidious and not reproducible. Published data shows that the agreement between medical specialists in Drusen identification is only 67%.

The goal of this project is the development of a methodology for automatic unsupervised detection and modeling of Drusen spots using image processing techniques. The methodology will be validated with a software prototype that will certainly improve the detection and quantification of Drusen.

It is also a main objective for the project to do a clinical validation of it, to compare the results with the ones obtained by ophthalmologists.

Research Areas
  • Intelligent Medical Image Processing
  • Decision Support Tools
  • Uninova
  • Cefitec – Centro de Fisica e Investigação Tecnológica
  • Faculdade de Ciências Médicas da Universidade Nova de Lisboa
  • University of Aberdeen

  • A. Mora, P. Vieira, J. Fonseca, “MODELLING OF DRUSEN DEPOSITS BASED ON RETINA IMAGE TRIDIMENSIONAL INFORMATION”, CIMED 2005 – Second International Conference on Computacional Intelligence in Medicine and Healthcare, Costa da Caparica, Lisbon Portugal, 29th June to 1st July 2005.
  • Mora A., Fonseca J., Vieira P., “Drusen Deposits Modeling with Illumination Correction”, in Proc. Biomed-2005, Innsbruck, Austria, 16-18 February 2005.
  • A. Mora, P. Vieira, J. Fonseca, “DRUSEN DEPOSITS ON RETINA IMAGES: DETECTION AND MODELING”, 2nd International Conference on Advances in Medical Signal and Information Processing - MEDSIP 2004, Malta, 5-8 September 2004.
  • A. Mora, P. Vieira, J. Fonseca, “A Modeling Approach for Automatic Detection of Drusen Deposits on Retina Images”, 4th European Symposium on Biomedical Engineering, Patras Greece, 25-27 June 2004.

Apoio FCT – Fundação para a Ciência e a Tecnologia no âmbito da Unidade de Investigação CTS - Centro de Tecnologia e Sistemas, referência UID/EEA/00066/2013