• Increase font size
  • Default font size
  • Decrease font size

Microaneurysm Detector

E-mail Print PDF

MA_LaTIM package (Microaneurysm Detector – LaTIM)

Copyright (C) 2010 by Gwenole Quellec, Mathieu Lamard, Guy Cazuguel

Following the publication of the LaTIM's automatic method for detecting microaneurysms in eye fundus photographs [TMI2008], we have been receiving a lot of requests to provide a source code of the method. We finally decided to satisfy these requests by releasing this package:

MA_LaTIM.R0 [140Mb]

The package consists of a software developed at the LaTIM laboratory for automated microaneurysm detection in eye fundus photographs and of a set of 36 manually annotated eye fundus color photographs from Brest University Hospital.

The software was written in C++ and depends on a set of open-source libraries (VTK, Xerces-C++, CMake, Open MPI and ctmf). It has been tested on Ubuntu platforms only. However it relies on multiplatform libraries, so the user should not experience a too much painful software installation. The software is released in the hope that it will be useful, however no further maintenance of the code will be provided.

The released code implements the method described in [TMI2008]. With some additional improvements not implemented in this release, this detector was the winner of the first Retinopathy Online Challenge (http://roc.healthcare.uiowa.edu/) in 2009. The results of this challenge and the additional improvements of the detector were presented in another IEEE Transactions on Medical Imaging paper [TMI2010]. If you plan to use this software for research purposes, please include a reference to [TMI2008] and [TMI2010] in your publications.

[TMI2008] G. Quellec, M. Lamard, P.-M. Josselin, G. Cazuguel, B. Cochener, C. Roux
Optimal wavelet transform for the detection of microaneurysms in retina photographs
IEEE T Med Imaging (2008), 27(9):1230-1241
http://hal.archives-ouvertes.fr/hal-00326135/en/

[TMI2010] M. Niemeijer, B. van Ginneken, M.J. Cree, A. Mizutani, G. Quellec et al.
Retinopathy Online Challenge: automatic detection of microaneurysms in digital color fundus photographs
IEEE T Med Imaging (2010), 29(1):185-195
http://ieeexplore.ieee.org/search/wrapper.jsp?arnumber=5282586

The set of images included in this package was manually annotated by a single diabetic retinopathy expert from the LaTIM laboratory. This new set of images has not been used for previous publications.

Contact information:
This e-mail address is being protected from spambots. You need JavaScript enabled to view it
, This e-mail address is being protected from spambots. You need JavaScript enabled to view it , This e-mail address is being protected from spambots. You need JavaScript enabled to view it

Last Updated on Thursday, 04 February 2010 13:36