Optimal Detection and Decision-Support Diagnosis of Diabetic Retinopathy

"Medical Data Acquisition and Image Processing"


The ultimate goal of the Imageret project is to develop new imaging hardware and novel image processing methods to efficiently and reliably assist in medical decision making in diabetic retinopathy diagnosis.

The goal can be achieved by combining the knowledge from medical science, optics, and image processing and via the scientific research provide new results to be used in medics. Furthermore, by educating new young masters and doctors within the field of medical image processing and medical image acquisition the future requirements of the health care can be met.

Funding:Research co-operation
  1. Tekes
  2. Kuomed Oy
  3. Mawell Oy
  4. Perimetria Oy
  5. Santen Oy
  1. Department of Ophthalmology, University of Kuopio (Prof. Uusitalo)
  2. Color Research Laboratory, University of Joensuu (Prof. Parkkinen)
  3. Communications and Signal Processing (Medical Image Processing Group), Imperial College, London, UK (Prof. Petrou)
  4. Department of Computer Science, University of Bristol, UK (Dr. Mirmehdi)
  5. YTI Research Centre, Mikkeli Polytechnic (Research manager Rossi)


  1. DiaRetDB -
    Standard Diabetic Retinopathy Database
  2. FunIA -
    Fundus Image Analysis
  3. FunImaging -
    Development of Fundus Imaging
  4. DiagSupport -
    Support of Diagnosis and Decision Making
The following project preceded ImageRet:
  1. RETINA - Retinal Image Analysis


Project received significant funding from the FinnWell Technology Program coordinated by the Finnish Funding Agency for Technology and Innovation, Tekes, and from the industrial partners.

The results of ImageRet were presented in a public closing seminar on Wednesday, January 14, 2008 in Tampere. The presentations were given by prof. Heikki Kälviäinen/LUT, Prof. Hannu Uusitalo/KuY/TaY, MSc Tomi Kauppi/LUT, and MSc Pauli Fält/UJo.

The project officially ended February 28, 2009. The scientific results will be finished during the year 2009. During the project, a prototype of a new eye fundus camera was developed, several eye fundus image databases related to diabetic retinopathy were released, and automatic image analysis methods were developed. The technology and knowhow is being transferred to product development.

Contact information

Lappeenranta University of Technology
Heikki Kälviäinen WWW Professor
Lasse Lensu WWW Project manager, post-doc researcher
Joni Kämäräinen WWW Post-doc researcher
Tomi Kauppi WWW Post-graduate researcher
University of Kuopio
Hannu Uusitalo WWW Research director
Iiris Sorri WWW Professor
Valentina Kalesnykiene WWW Post-graduate researcher
University of Joensuu
Jussi Parkkinen WWW Professor
Markku Hauta-Kasari WWW Director
Jouni Hiltunen WWW Laboratory engineer
Pauli Fält WWW Post-graduate researcher


Source code / executables

  1. ImgAnnoTool - Image Annotation Tool (contact Lasse Lensu for more information)

Data sets

  1. DIARETDB0 - Standard Diabetic Retinopathy Database (depricated)
  2. DIARETDB1 - Standard Diabetic Retinopathy Database (depricated)
  3. DIARETDB1 V2.1 - Standard Diabetic Retinopathy Database

Links to other resources

General information
Current Perspectives of Diabetic RetinopathyVery good description of the problem we are dealing with (with images)
European Vision ResearchHealth science oriented portal for vision research in EU
The Association for Research in Vision and OphthalmologyHealth science oriented portal for vision research in USA and worldwide
Other research groups
Cercia Center, University of BirminghamTaken spectral fundus images (see facilities)
Kestrel CorporationInvestigates multi-spectral fundus imaging device
School of Computer Science, University of BirminghamImage analysis, retinopathy, spectral imaging
MessidorDiabetic retinopathy evaluation
Conferences and meetings
Engineering the Eye II: Imaging the RetinaRetinal function, retinal disease, and advances in optical imaging
Medical Image Data Types and XML
David Clunie's Medical Image Format SiteYou find everything you need to know
XML Validation FormCan be used to validate XML code
HL7Standardisation organisation for healthcare IT
Multiple expert annotation fusion
STAPLESimultaneous Truth and Performance Level Estimation
Medical imaging libs and software
VTKVisualization Toolkit
ITKITK Insight Toolkit
KitwareVarious usefull toolkit and libraries
TeemVarious tools to process medical image data (e.g. NRRD format)


Do not hesitate to to contact authors (e-mail, etc.) in order to retrieve copies or reprints of the following publications.