Messidor

Project Description

MESSIDOR stands for Methods to Evaluate Segmentation and Indexing Techniques in the field of Retinal Ophthalmology (in French).
Within the scope of Diabetic Retinopathy, the primary purposes of the Messidor project is to compare and evaluate:

• Various segmentation algorithms developed for the detection of lesions present in color retinal images;
• Tools to index and manage image databases.

Project Funding

Messidor was a research program funded by the French Ministry of Research and Defense within a 2004 TECHNO-VISION program.

Different methods were evaluated

Download information

Introduction

The Messidor database has been established to facilitate studies on computer-assisted diagnoses of diabetic retinopathy. The research community is welcome to test its algorithms on this database. In this section, you will find instructions on how to download the database.

Using the database

Data included in this database can be used, free of charge, only for research and educational purposes. Copy, redistribution, and any unauthorized commercial use are prohibited. Any researcher reporting results that use this database must acknowledge the Messidor program by adding the following information:

Kindly provided by the Messidor program partners (see https://www.adcis.net/en/third-party/messidor/).

Users of the messidor database are encouraged to reference the following article:

Decencière et al.. Feedback on a publicly distributed database: the Messidor database.
Image Analysis & Stereology, v. 33, n. 3, p. 231-234, aug. 2014. ISSN 1854-5165.
Available at: http://www.ias-iss.org/ojs/IAS/article/view/1155 or
http://dx.doi.org/10.5566/ias.1155.

In addition, we appreciate to hear about any publication that is based on the Messidor database. Feedback on the database and this website is also welcome. The person to contact is Etienne Decencière Ferrandière or Bruno Laÿ.

Description

The 1200 eye fundus color numerical images of the posterior pole of the Messidor database were acquired by 3 ophthalmologic departments using a color video 3CCD camera mounted on a Topcon TRC NW6 non-mydriatic retinograph with a 45 degree field of view. Images were captured using 8 bits per color plane at 1440*960, 2240*1488 or 2304*1536 pixels.

800 images were acquired with pupil dilation (one drop of Tropicamide at 0.5%) and 400 without dilation.

The 1200 images are packaged in 3 sets, one per ophthalmologic department. Each set is divided into 4 zipped subsets containing each 100 images in TIFF format and an Excel file with medical diagnoses for each image.

Medical diagnoses

Two diagnoses have been provided by the medical experts for each image:

• Retinopathy grade
• Risk of macular edema

Retinopathy grade

• 0 (Normal): (μA = 0) AND (H = 0)
• 1: (0 < μA <= 5) AND (H = 0)
• 2: ((5 < μA < 15) OR (0 < H < 5)) AND (NV = 0)
• 3: (μA >= 15) OR (H >=5) OR (NV = 1)

• μA: number of microaneurysms
  H: number of hemorrhages
  NV = 1: neovascularization
  NV = 0: no neovascularization

Risk of macular edema

Hard exudates have been used to grade the risk of macular edema.

• 0 (No risk): No visible hard exudate
• 1: Shortest distance between macula and hard exudates > one papilla diameter
• 2: Shortest distance between macula and hard exudates <= one papilla diameter

All images contained in the database were used for making actual clinical diagnoses. To ensure the upmost protection of patient privacy, information that might allow to identify a patient has been discarded, and we have no actual knowledge that images could be used alone or in combination with others to identify any subject. To minimize any further risk of breach of privacy, the use of this database is restricted to individuals or organizations that obtained the database directly from this website.

Links

Other databases with retinal images are available on the following sites:

• Stare project: Retinal color images and results of automatic location of the optic nerve.
• Drive project: Retinal color images and results of automatic segmentation of blood vessels.

Errata

Note:

For the sake of consistency with research work based on the Messidor database before these mistakes were noticed, it was decided NOT to fix them in the downloadable Messidor database. The task of correcting them in the database before using it is users’ responsibility.

09 February 2018: Grading inconsistencies among image duplicates

Among the image duplicates in Base 33 (see 16 August 2017 erratum), 2 of them have inconsistent grades:

• 20051202_55562_0400_PP.tif and 20051202_54611_0400_PP.tif have different ‘Risk of macular edema’ grades (0 and 1 respectively)
• 20051202_55626_0400_PP.tif and 20051205_33025_0400_PP.tif have different Retinopathy grades (2 and 3 respectively)

We would like to thank Renoh Johnson Chalakkal (University of Auckland) and Jean-Claude Klein for pointing out and confirming these inconsistencies.

16 August 2017: Image duplicates in Base33

13 duplicate image pairs were discovered in this dataset. Here is the list of these pairs:

• 20051202_55582_0400_PP.tif – 20051202_54744_0400_PP.tif
• 20051202_41076_0400_PP.tif – 20051202_40508_0400_PP.tif
• 20051202_48287_0400_PP.tif – 20051202_41238_0400_PP.tif
• 20051202_48586_0400_PP.tif – 20051202_41260_0400_PP.tif
• 20051202_55457_0400_PP.tif – 20051202_54530_0400_PP.tif
• 20051202_55626_0400_PP.tif – 20051205_33025_0400_PP.tif
• 20051202_54783_0400_PP.tif – 20051202_55607_0400_PP.tif
• 20051202_48575_0400_PP.tif – 20051202_41034_0400_PP.tif
• 20051205_32966_0400_PP.tif – 20051205_35099_0400_PP.tif
• 20051202_55484_0400_PP.tif – 20051202_54555_0400_PP.tif
• 20051205_32981_0400_PP.tif – 20051205_35110_0400_PP.tif
• 20051202_55562_0400_PP.tif – 20051202_54611_0400_PP.tif
• 20051202_54547_0400_PP.tif – 20051202_55498_0400_PP.tif

We would like to thank Luca Giancardo, Mathieu Lamard and Jean-Claude Klein for pointing out and confirming this fix.

31 August 2016: Erratum in Base11 Excel file

• Image 20051020_63045_0100_PP.tif: Retinopathy grade should be 0 (instead of 3).

We would like to thank Visweswararao Durga, Ali Erginay and Jean-Claude Klein for pointing out and confirming this fix.

24 October 2016: Erratum in Base11 and Base 13 Excel files

• Image Base11/20051020_64007_0100_PP.tif: Retinopathy grade should be 3 (instead of 1).
• Image Base11/20051020_63936_0100_PP.tif: Retinopathy grade should be 1 (instead of 3).
• Image Base13/20060523_48477_0100_PP.tif: Retinopathy grade should be 3 (instead of 2).

We would like to thank Jocelyn Desbiens, Ali Erginay and Jean-Claude Klein for pointing out and confirming this fix.

Download

A form with personal information needs to be completed to download the databases.

Download form

If you encounter any trouble downloading the database please contact the administrator of the database.

Messidor Consortium

Evaluation System Architecture

Project Description

Issue and Context

Since the early 1980’s, many studies have been initiated worldwide to develop advanced systems for the automated detection and follow-up of Diabetic Retinopathy, the first cause of blindness in people between 25 and 65 years old. These systems, based on automatic image processing, mainly consist in tools for detecting and measuring common lesions (such as microaneurysms, exudates, hemorrhages) and in indexing and automated retrieval techniques applied to image databases.

In view of the numerous studies already available, the major issue is now to assess accurately and objectively the results that have been obtained so far. This problem is far from being solved due to the lack of a large and adequate database accessible to the scientific community. The size of the available databases described in literature is clinically inadequate to allow this kind of assessment.

Two methods, for which several algorithms have been developed by the partners of the Messidor project, have been more particularly studied:

1. The image Analysis-Quantization method which implements segmentation algorithms to detect and quantify elementary lesions like microaneurysms, first non equivocal sign of Diabetic Retinopathy, hemorrhages and exudates whose importance and location are a good marker of the seriousness of the retinal disease.
2. The method for Automated Retrieval (from an annotated image database) of the images closest to the retina image under analysis (request image). The images of the database and the request image are indexed by defining signatures.

The main current issue is to create large databases of retina images and to use them in order to evaluate the various existing algorithms.

Databases

The two main databases will contain color images of the retina, acquired using a retinograph with or without pupil dilation during routine clinical examinations. These examinations will be performed in the four ophthalmology departments involved in the program. To make their diagnosis, ophthalmologists are generally using a central picture and two peripheral pictures of the retina. We will proceed in the same way and we will record the three images in the databases. However, during the Messidor project, only the central image will be annotated.

The images will be saved as uncompressed TIFF format with a 1440 * 960 pixel resolution that is about 4 MB per image.

Training set

This database will be used for testing and improving the available algorithms as well as for validating the methods used to evaluate the algorithms. For each image, the following data will be saved:

• The stage of Diabetic Retinopathy.
• The number of and/or the surface of microaneurysms.
• The degree of exudation: the degree is function of the surface that is occupied by exudates and their locations with respect to the center of vision (Macula).
• The level of hemorrhage, which is defined with respect to the number and/or the surface occupied by hemorrhages.

This database will contain about 300 images. Microaneurysms, exudates and hemorrhages will be marked individually on at least fifty of these images.

Evaluation set

This database will contain about a thousand of images. Its purpose will be the evaluation of algorithms. All images in the evaluation set will be annotated in the same way as for the training set. On a hundred of them, microaneurysms, exudates and hemorrhages will be marked individually as in the training set.

Testing implementation

To evaluate a method used for automated detection and image interpretation, it is necessary to compare the result that is obtained by this method with a reference that is considered to be the ground truth. This raises two questions:

1. What is the ground truth or the reference?
2. Which measures should be used to perform the evaluation?

How to obtain references?

To determine the number of microaneurysms, the stage of retinopathy, the degree of exudation and the level of hemorrhage, all images of the training and the evaluation sets will be analyzed by all the ophthalmology departments involved in the project and annotated with respect to their conclusions.

For the individual marking of microaneurysms, images will be annotated by two specialists in each ophthalmology department. If there is only a slight difference between departments, we will retain the marking proposed by the department that has provided the images; if there is a significant difference, we will try to reach an agreement between the different departments and/or new rules for selecting microaneurysms will be proposed.

The individual marking of exudates and hemorrhages is not a real problem as there are less ambiguous cases as with microaneurysms. Therefore working towards a consensus between the different departments should be less necessary.

Protocols and metrics

Before adopting a given metrics, we have first to consider the audience to which this evaluation is intended, in other words the people who may be interested in the obtained results. We will first address the medical community. Therefore we must select a metrics that is commonly used in the medical field in the evaluation as well as in the presentation of the results. Second, this work is intended to the scientific researchers who develop automatic image processing methods. Then we will have to select the metrics used by these scientists. We propose to compute and describe the results in two different ways: by applying first the performance measurements used by physicians, and second the more detailed statistics commonly used in image processing. The Analysis – Quantization algorithms will be applied to all the images of the evaluation database. We will do the same for the Indexing – Retrieval algorithms for which every image of the evaluation database will serve as the requested image.

Hence, the algorithms will be evaluated from two points of view:

Evaluation for the medical community

It has been decided to classify Diabetic Retinopathy into 6 stages of seriousness, 4 stages of exudation and 3 stages of hemorrhage and to indicate the number of microaneurysms for each image.

An efficiency indicator will be used, whose implementation remains to be more precisely defined, in order to evaluate performance with respect to medical diagnosis. This efficiency indicator will consist in the percentage of automated diagnoses in agreement with medical diagnoses.

The Indexing – Retrieval algorithms will be evaluated with respect to the stages of seriousness of Diabetic Retinopathy.

The Segmentation – Quantization algorithms will be evaluated with respect to the stages of exudation and hemorrhage as well as to the number of microaneurysms.

Detailed evaluation of algorithms

In order to evaluate Indexing – Retrieval algorithms, we will use the classical
comparison and evaluation criteria applied to retrieval performances (Precision / Recall). These measurements will be done from the annotations concerning the stage of seriousness of Diabetic Retinopathy. And to evaluate Segmentation – Quantization algorithms, we will assess their sensitivity and specificity with respect to the detection of microaneurysms, exudates and hemorrhages that have been marked individually by ophthalmologists.

Expected results

The first expected result is to have a good knowledge of the efficacy, performance, limitations and drawbacks of the algorithms. This should help to:

• Convince ophthalmologists to use automatic methods for diabetic retinopathy evaluation by providing them with quantitative assessments of the efficacy, performance, and potential limitations of available methods.
• Establish a strong collaboration between the Messidor partners to foster the development of practical, supported, software products to be used in tracking-down services, telemedicine, pathology tracking, and as a diagnostic aid in the field of diabetic retinopathy. The successful accomplishment of the Messidor project goals will be a major breakthrough in the field of public health and the treatment of eye disease.

The second expected result is the creation of large databases, which are indispensable to the scientific community which is currently working on retinal images.

Communication and exploitation of results

Communication of scientific results

The scientific results will be communicated through the Messidor internet web site, scientific papers and congress communications.

Exploitation of data and software tools

After the research campaign, the databases will be accessible to the scientific community by signed agreements taking into account any related legal constraints. The value and industrialization of the software tools will be developed according to the rules defined and adopted by all the partners in the exploitation plan which will soon be elaborated. The value of indexing and retrieval algorithms and methods will also be developed in internet teaching applications. This could be another important benefit of Messidor program.

Messidor Related Publications

• [1] LAŸ B. Analyse automatique des images angiofluorographiques au cours de la rétinopathie diabétique, CMM, École Nationale Supérieure des Mines de Paris.Thèse de Docteur-Ingénieur, mai 1983.
• [2] ZANA F. Une approche morphologique pour les détections et Bayésienne pour le recalage d’images multimodales  Application aux images rétiniennes, CMM, École Nationale Supérieure des Mines de Paris, Thèse de Docteur-Ingénieur, mai 1999.
• [3] WALTER T. Application de la Morphologie Mathématique au diagnostic de la Rétinopathie Diabétique à partir d’images couleur, CMM, École Nationale Supérieure des Mines de Paris, Thèse de Docteur-Ingénieur, septembre 2003.
• [4] ZANA F, KLEIN JC. A Multi-Modal Registration Algorithm of Eye Fundus Images Using Vessels Detection and Hough Transform, IEEE Transaction on Medical Imaging, vol. 18, no. 5, pp. 419-428, 1999.
• [5] ZANA F, KLEIN JC. Segmentation of Vessel-Like Patterns using Mathematical Morphology and Curvature Evaluation, IEEE Transaction on Image Processing, vol. 10, no. 7, pp. 1010-1019, 2001.
• [6] WALTER T, KLEIN JC, MASSIN P, ERGINAY A. A Contribution of Image Processing to the Diagnosis of Diabetic Retinopathy – Detection of Exudates in Color Fundus Images of the Human Retina. IEEE Transaction on Medical Imaging, 21(10): 1236-1244, October 2002.
• [7] WALTER T, KLEIN JC, MASSIN P, ZANA F. Automatic segmentation and registration of retinal fluorescein angiographies- Application to diabetic retinopathy, First International Workshop on Computer Assisted Fundus Image Analysis (CAFIA) May 29-30, 2000, Copenhagen, Denmark.
• [8] WALTER T, KLEIN JC. Segmentation of color fundus images of the human retina: Detection of the optic disc and the vascular tree using morphological techniques, Second International Symposium on Medical Data Analysis (ISMDA) October 9-11, 2001, Madrid, Spain.
• [9] WALTER T, KLEIN JC. A Computational Approach to Diagnosis of Diabetic Retinopathy, 6th Conference on Systemics, Cybernetics and Informatics (SCI) July 15-18, 2002, Orlando, Florida.
• [10] WALTER T, KLEIN JC. Detection of microaneurysms in color fundus images of the human retina, IN: A.Colosimo, A. Giuliani, P. Sirabella: Lecture Notes in Computer Science (LNCS), Vol. 2526, pp. 210-220, Springer-Verlag Berlin Heidelberg, October 2002, Third International Symposium on Medical Data Analysis (ISMDA).
• [11] WALTER T, KLEIN JC, MASSIN P, ERGINAY A. Detection of the median axis of vessels in retinal images, European Journal of Ophthalmology, 13(2): 236, Mars 2003; Third International Workshop on Computer Assisted Fundus Image Analysis (CAFIA) March 28-30, 2003, Torino, Italy.
• [12] MASSIN P. Dépistage de la Rétinopathie Diabétique – Aspects techniques et organisationnels Thèse, Université de Paris 7 – Denis Diderot, UFR Lariboisière-Saint-Louis, Février 2002.
• [13] BENOSMAN R, MASSIN P, ERGINAY A, BEN MEHIDI A, VICTOR Z, HOANG-XUAN T, MARRE M, GAUDRIC A. Dépistage de la rétinopathie diabétique par photographies du fond d’œil et télétransmission  résultats d’un an d’expérience. 109^ème Congrès de la Société Française d’Ophtalmologie France 11-14 mai 2003.
• [14] WALTER T, KLEIN JC, MASSIN P, ERGINAY A. Contribution of image processing to the diagnosis of diabetic retinopathy, Diabetes & Metabolism, 11th Meeting of the European Association for the Study of Diabetic Eye Complications (EASDEC) May 18-20 2001, Paris, France.
• [15] ERGINAY A, MASSIN P, BEN MEHIDI A, AUBERT JP et le Réseau de Santé Paris-Nord. Screening for diabetic retinopathy using fundus photography and teletransmission. European Association for the Study of Diabetes Eye Complication Study Group (EASDec) Prague 23-25 mai 2003.
• [16] MASSIN P, AUBERT JP ESWEGE E et le Réseau de Santé Paris-Nord. Dépistage de la rétinopathie diabétique par photographies du fond d’œil. Expérience du Réseau de Santé Paris-Nord. Congrès de l’ALFEDIAM, Bordeaux, Mars 2003.
• [17] MASSIN P, ANGIOI-DUPREZ K, BACIN F, CATHELINEAU B, CATHELINEAU G, CHAINE G, COSCAS G, FLAMENT J, SAHEL J, TURUT P, GUILLAUSSEAU PJ, GAUDRIC A. Recommandations de l’ALFEDIAM pour le dépistage et la surveillance de la rétinopathie diabétique, Diabetes Metab, 1996, 22, 203-209.
• [18] MASSIN P, ERGINAY A, BEN MEHIDI A, VICAUT E, QUENTEL G, GUILLAUSSEAU PJ, BERTRAND D, MARRE M, GAUDRIC A. Evaluation of the TRC-NW6S nonmydriatic digital camera for detection of diabetic retinopathy, Diabet Med. 2003 Aug;20(8):635-41.
• [19] HOOVER, A. Locating the Optic Nerve in a Retinal Image Using the Fuzzy convergence of the Blood Vessels. dans IEEE – Transactions on Medical Imaging. Vol. 22, N° 8, Août 2003. Base de données téléchargeable sous http://cecas.clemson.edu/~ahoover/stare/.
• [20] STAAL JJ, ABRAMOFF MD, NIEMEIJER M, VIERGEVER MA, VAN GINNEKEN B. Ridge based vessel segmentation in color images of the retina dans IEEE Transactions on Medical Imaging, vol.23, N°4, April 2004. Base de données téléchargeable sous http://www.isi.uu.nl/Research/Databases/DRIVE/.
• [21] NIEMEIJER M, STAAL JJ, VAN GINNEKEN B, LOOG M, ABRAMOFF MD. Comparative study of retinal vessel segmentation methods on a new publicly available database, in: SPIE Medical Imaging, Editor(s): J. Michael Fitzpatrick, M. Sonka, SPIE, 2004, vol. 5370, p. 648-656.
• [22] STAAL JJ, KALITZIN SN, VAN GINNEKEN B, ABRAMOFF MD, BERENDSCHOT T, VIERGEVER MA. Classifying convex sets for vessel detection in retinal images in: International Symposium on Biomedical Imaging, 2002, p. 269-272.
• [23] ORDONEZ JR. Indexation et recherche d’images par le contenu, utilisant des informations de compression d’images : application aux images médicales Thèse, Lab. de Traitement de l’Information Médicale (LaTIM) – ENST Bretagne, Université de Rennes 1.
• [24] CAZUGUEL G, ORDONEZ JR, PUENTES J, CAUVIN JM, SOLAIMAN B, ROUX C. Recherche d’images médicales par leur contenu numérique dans le domaine compressé : comparaisons de signatures construites à partir de la quantification vectorielle et des normes JPEG. COmpression et REprésentation des Signaux Audiovisuels (CORESA2004). Lille, France, 25-26 mai 2004.
• [25] CAZUGUEL G, COLIN J, CONAN S, THERIER L, BERNARD F. Serveur d’expertise multicentrique en ophtalmologie (SEMO), Congrès Mondial de Télémédecine,Toulouse, 2000.
• [26] CAUVIN JM, LE GUILLOU C, SOLAIMAN C, ROBASZKIEWICZ M, GOUEROU H, ROUX C. Diagnostic Reasoning Model Validation in Digestive Endoscopy. 23th Conference of the IEEE Engineering in Medicine and Biology Society, 2001.
• [27] LE GUILLOU C, CAUVIN JM, SOLAIMAN B, ROBASZKIEWICZ M, ROUX C. Information processing in upper digestive endoscopy. IEEE-EMBS Information Technology Applications in Biomedicine, 2000.
• [28] ORDONEZ JR, CAZUGUEL G, PUENTES J, SOLAIMAN B, ROUX C. Spatial-textural medical image indexing based on vector quantization, 25th annual conference of the IEEE EMBS, Cancun Mexico, 17-21 September 2003.
• [29] ORDONEZ JR, CAZUGUEL G, PUENTES J, SOLAIMAN B, ROUX C. Content based image retrieval using spatial and spectral information from JPEG-2000, 12^éme Forum des Jeunes Chercheurs en Génie Biologique et Médicale, Nantes – France, 21-23 Mai 2003.
• [30] ORDONEZ JR, CAZUGUEL G, PUENTES J, SOLAIMAN B, ROUX C. L’utilisation des moments spatiaux pour la recherche d’images médicales par leur contenu dans le domaine compressé : application à la quantification vectorielle et le standard JPEG-DCT. TAIMA 2003, Hammameth, Tunisie, 1^er au 3 octobre 2003.
• [31] CONAN S, CAZUGUEL G, COLIN J, ROUX C. Mise en place et développement du serveur internet d’ophtalmologie du CHU de Brest. 105^ème Congrès de la Société Française d’Ophtalmologie, Paris, 1999.
• [32] LAMARD M, COCHENER B. Modélisation de l’œil en vue de simulations de chirurgies réfractives. J.Fr. Ophtalmol,2001,24(8):813-822
• [33] Colin J, Cochener B, Le Floch G: Excimer laser treatment of myopic astigmatism. Ophthalmology,1998,105:1182-1188.
• [34] MANOLI P, DEB N, GARCIN AF, GERMAIN N, MILLOT L, THURET G, ESTOUR B, GAIN P. Dépistage de la rétinopathie diabétique par rétinographie numérique non mydriatique : mydriase ou non ? Société Française d’Ophtalmologie, Paris, mai 2004 (oral).
• [35] MANOLI P, DEB N, GARCIN AF, GERMAIN N, MILLOT L, THURET G, ESTOUR B, GAIN P. Dépistage de la rétinopathie diabétique par rétinographie numérique. Avantage de la dilatation pharmacologique, Société Rhône Alpes d’Ophtalmologie Lyon, juin 2004 (oral).
• [36] MILLOT L, GERMAIN N, DEB N, THURET G, MANOLI P, GARCIN AF, GAIN P, ESTOUR B. Dépistage de la rétinopathie diabétique par rétinographe numérique : avantages de la dilatation pharmacologique, Société Française d’Endocrinologie Paris, sept 2004. (accepté oral).
• [37] GAIN P, DEB N, MANOLI P, GARCIN AF, GERMAIN N, MILLOT L, THURET G, ESTOUR B. Screening of diabetic retinopathy by “non mydriatic digital camera”: advantages of mydriasis. Association for Research in Vision and Ophthalmology (ARVO), Fort Lauderdale, USA, avril 2004 (poster).
• [38] DEB N, THURET G, GAVET Y, MANOLI P, GARCIN AF, GERMAIN N, MILLOT L, ESTOUR B, GAIN P. Screening of diabetic retinopathy by digital retinograph: advantages of pharmacological dilatation. EVER (European association for Vision and Eye Research), Villamora, Portugal, sept 2004 (poster).
• [39] DEB N, THURET G, ESTOUR B, MASSIN P, GAIN P. Screening for diabetic retinopathy in France. Diabetes Metab. 2004;30:140-5.
• [40] MASSIN P, ANGIOI-DUPREZ K, BACIN F, CATHELINEAU B, CATHELINEAU G, CHAINE G, COSCAS G, FLAMENT J, SAHEL J, TURUT P, GUILLAUSSEAU PJ, GAUDRIC A. Dépistage, surveillance et traitement de la rétinopathie diabétique. Diabetes & Metabolism (Paris). 1996, 22:203-9.
• [41] MASSIN P, ANGIOI-DUPREZ K, BACIN F, CATHELINEAU B, CATHELINEAU G, CHAINE G, COSCAS G, FLAMENT J, SAHEL J, TURUT P, GUILLAUSSEAU PJ, GAUDRIC A. Recommandations de l’ALFEDIAM pour le dépistage et la surveillance de la rétinopathie diabétique. J Fr Ophtalmol. 1997, 20:302-10.
• [42] GUERCI B, MEYER L, SOMMER S, GEORGE JL, ZIEGLER O, DROUIN P, ANGIOI-DUPREZ K. Severity of diabetic retinopathy is linked to lipoprotein(a) in type 1 diabetic patients. Diabetes & Metabolism. 1999, 25:412-8.
• [43] ANGIOI-DUPREZ K, GUERCI B, MAALOUF T, DROUIN P. Intérêt des caméras non mydriatiques dans le dépistage de la rétinopathie diabétique : résultats d’une enquête nationale. Diabète & Métabolisme, 2002, 28, 242-3.
• [44] BOUCHER MC, GRESSET J, ANGIOI K, OLIVIER S. Effectiveness and safety of screening for diabetic retinopathy with two non-mydriatic digital images as compared with the seven standard stereoscopic photographic fields. Can J Ophthalmol. 2003;38:537-2.
• [45] PERRIER M, BOUCHER MC, ANGIOI K, GRESSET J, OLIVIER S. Comparison of two, three and four 45-degree image fields with the Topcon CRW6 non-mydriatic camera for screening for diabetic retinopathy. Can J Ophthalmol. 2003;38:569-74.
• [46] LAMARD M, COCHENER B. Modélisation de l’œil en vue de simulations de chirurgies réfractives. J.Fr. Ophtalmol,2001,24(8):813-822.
• [47] CAZUGUEL G, COLIN J, CONAN S, THERIER L, BERNARD F. Serveur d’expertise multicentrique en ophtalmologie (SEMO), Congrès Mondial de Télémédecine,Toulouse, 2000.
• [48] CONAN S, CAZUGUEL G, COLIN J, ROUX C. Mise en place et développement du serveur internet d’ophtalmologie du CHU de Brest. 105^ème Congrès de la Société Française d’Ophtalmologie, Paris, 1999.
• [49] LARABI MC, RICHARD N, FERNANDEZ-MALOIGNE C, MACAIRE L. Aide au diagnostic pour les cancers de peau basée sur une indexation par la couleur, la texture et la peau. ICISP′2001. 3-5 mai 2001. Agadir, Maroc.
• [50] FERNANDEZ-MALOIGNE C, RICHARD N, LAIZÉ E. Content-based image indexing with color texture descriptors. Dans SCI′2001, Artificial Intelligence And Cognitive Science Within Virtual Environments. 22-25 juillet 2001. Orlando, Florida, USA.
• [51] LARABI MC, RICHARD N, FERNANDEZ-MALOIGNE C. Using statistical attributes and quantization for cancer diagnosis by query by content. Annales des Télécommunications, 2002.
• [52] LARABI MC, RICHARD N, COLOT O, FERNANDEZ-MALOIGNE C. Modélisation du savoir-faire des experts pour l’indexation de la base ornementale, CORESA 2003, 16-17 janvier, Lyon, France.
• [53] VERTAN C, STOICA A, FERNANDEZ-MALOIGNE C. Sur les caractéristiques dominantes de similarité des couleurs CORESA 2003, 16-17 janvier, Lyon, France.
• [54] LARABI MC. Codage et analyse d’images couleur : application à l’indexation de bases d’images réparties, Journée GdR I3-GRCE, Palais des congrès, Paris, 06 Mars, 2003.
• [55] LARABI MC, RICHARD N, COLOT O, FERNANDEZ-MALOIGNE C. Using a CBIR Scheme Based on Experts knowledge for a Computer-Aided Classification of Ornamental Stones, 6th Int. Conf. on Quality Control by Artificial Vision 2003 Gatlinburg, Tennessee, USA, May 19-23, 2003.
• [56] LARABI MC, RICHARD N, COLOT O, FERNANDEZ-MALOIGNE C. Utilisation de l’indexation d’images pour l’aide au diagnostic dédié aux cancers de peau, La chaîne d’acquisition et de traitements d’images couleur, inclus dans le chapitre Applications. ed. Dunod, 2003.
• [57] FERNANDEZ-MALOIGNE C, LARABI MC, RICHARD N, LAIZÉ E. Content-based Image Indexing with Color Texture Descriptors: Application to Computer Aided Diagnosis , SCI 2004, July 18-21, 2004 – Orlando, Florida, USA.
• [58] GUNES V, MENARD M, LOONIS P, PETIT-RENAUD S. Combination, cooperation, and selection of classifiers. International Journal of Pattern Recognition and Artificial Intelligence. to published, 17(8):1-22, 2004.
• [59] MENARD M, DARDIGNAC P, CHIBELUSHI CC. Non-extensive thermostatistics and extreme physical information for fuzzy clustering. Invited paper. International Journal of Computational Cognition., 2(4):1-63, December 2004.
• [60] COURBOULAY V, MENARD M, EBOUEYA M, COURTELLEMONT P. Fuzzy Multi-local Image Relief Classification. In Fuzz-IEEE, IEEE International Conference on Fuzzy Systems. Hawaii, 2002.
• [61] SEMANI D, FRELICOT C, COURTELLEMONT P. Feature selection using an ambiguity measure based on fuzzy OR-2 operators. In 10th International Fuzzy Systems Association World Congress, IFSA′2003, Istanbul, Turkey, pages 265–268, Jully 2003.
• [62] COUDRAY R, BESSERER B. Feature Point Extraction in Compressed Domain. Proc. of IS&T/SPIE, Storage and Retrieval for Media Database, 5021, 2003.
• [63] GARDES J, ADAM S, OGIER J-M, CARIOU C. A Scale and Rotation Parameters Estimator: Application to Technical Document Interpretation. Lecture Notes in Computer Science – Springer Verlag, 2390:257-264, 2002.
• [64] MULLOT R, OGIER J-M. Un système de reconnaissance automatique de documents techniques – Application aux plans de cadastre. Techniques et Sciences Informatiques, 21(10):1-27, 2002.
• [65] LECOURTIER Y, ADAM S, OGIER J-M, CARIOU, MULLOT R, GARDES J. Utilisation de la Transformée de Fourier-Mellin pour la reconnaissance de formes multi-orientées et multi-échelles : application à l’analyse automatique de documents techniques. Traitement du Signal, 18(1):17-33, October 2001.
• [66] METHRE BM, KANKANHALLI M, NARASIMHALU AD, MAN GC. Color matching for image retrieval. Pattern Recognition Letters, 16: 325-331, 1995.