MICCAI 2024- DIAMOND Challenge Launch : Who will participate ?

In the framework of the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2024), taking place in Marrakesh, Morocco, in October 2024, the EviRed consortium organizes an AI challenge on Device-Independent diAbetic Macular edema ONset preDiction (DIAMOND).

The challenge’s focus is on center-involved Diabetic Macular Edema (ci-DME), a critical form of DME responsible for significant vision impairment. The presence of DME is generally assessed through 3D optical coherence tomography (OCT) imaging. As a sub-objective of EviRed, DIAMOND seeks to revolutionize the approach to diagnosing and treating ci-DME by integrating AI and deep learning with 2D ultra-wide-field color fundus photography (UWF-CFP). More challenging than assessing the presence of ci-DME, the goal is to develop and evaluate models that can predict if a patient will develop ci-DME within a year, using UWF-CFP images alone. Success in this challenge could significantly improve early detection and treatment planning, reduce vision loss incidents, and exemplify AI’s efficacy in healthcare.

For training, the DIAMOND Challenge uses data collected in the framework of EviRed. For performance evaluation, DIAMOND will also use independent data from the LAZOUNI Ophthalmology Clinic in Tlemcen, Algeria. By leveraging diverse datasets, the challenge underscores its commitment to developing solutions that are universally applicable, transcending geographic and demographic boundaries. This generality is critical in ensuring that the predictive models developed are robust and effective across different population groups, enhancing their clinical utility on a global scale.

Participants in this challenge will not have access to the training, validation, or test datasets and, consequently, will not have the opportunity to train their models directly. Instead, they are required to submit their code to the organizing committee, who will then run it on a specialized cloud-based cluster. This methodology not only challenges participants to develop highly generalizable models but also prepares them for real-world situations where data privacy, ethical considerations, and logistical limitations are common.

More information here: https://www.codabench.org/competitions/2333/

EviRed is recruiting- Apply before the 31th of March



To reinforce his team, Prof Tadayoni’s  ophthalmology department is looking for his/her future motivated colleague to join the EVIRED team for a renewable 6-month contract.

The position may be part-time or full-time and the assignments and activities will be distributed following the time and your degree level:

  • 2 to 3 days of activity in the EVIRED reading center as a reader («grader») for the analysis of retinal imageries (photographs of the fundus in ultra-large field, OCT (Optical Coherence Tomography) and OCT-A ( OCT-Angiography) from different types of patient machines included in the EVIRED protocol to allow training and validation of intelligence algorithms
  • 1 to 2 days of activity dedicated to research work either in the department or on  the RHU EVIRED’s ancillary projects
  • 1 to 2 days of observation activity and training in the medical retina department :
    •  at the consultations where you can work in pair with the senior ophthalmologists for the  patient’s follow-up and where you will have  access to a technical platform of retinal imaging, or you can help in the image’s interpretation acquired by the orthoptists of the department
    •  at the IVIs circuit where you will help with IVIs
    •  In  clinical research,  where you can discover the managment  of academic/ institutional research projects.

This position is open to young graduates with knowledge in ophthalmology, orthoptists,   foreign resident or young ophthalmologist with research appetence.  Foreign doctors can apply if they have a solid training and experience in ophthalmology and   can justify their equivalence of diploma and being authorized to work in France (current work authorization/visa)

The required skills are:

  • Rigor and organizational
  • Sense of deadlines and results
  • Autonomy
  • Ease with computer tools
  • Use business software
  • Observation skills
  • Medical research interest
  • Teamwork and/or networking


You are interested, send us your application (CV and cover letter) until  March,31 2024 to recherche.oph.lrb@aphp.fr


Remuneration: Salary according to APHP grid and according to your background and diploma BAC + 2: TEC junior/ BAC + 4: TEC senior/ foreign resident / contractual hospital practitioner

Fourth candle blown for EVIRED

On the February 25th, EviRed celebrated its 4th anniversary.

The consortium members (APHP, ADCIS, EVOLUCARE, LATIM-UBO, UP and ZEISS) worked on patient data collected from the 3182 patients included in the Evired cohort by the 14 investigators sites. Clinical data and images are the key to develop the most innovative and powerful algorithms based on AI for better predicting Progression of the Diabetic Retinopathy.

For 4 years, the entire RHU EviRed team has been working tirelessly for the success of the project and first results will be coming soon.

Stay tuned.

Evired Cohort

On the 21st of December 2023, EviRed’s recruitment ended with an outstanding inclusion of 3182 patients!

As a reminder, 14 French sites participate in this clinical study. Patients are followed every year. Their medical data related to diabetes and eye conditions are collected. Patient’s eyes are imaged with several   modalities and different machines for each modality.

We would like to thank all the teams on the 14 sites for their amazing work and all the patients who agreed to participate in this cohort.

Thesis defense on “Multimodal information fusion for the diagnosis of diabetic retinopathy”.

On the 8th of December, Yihao Li brilliantly defended his PhD thesis entitled “Multimodal information fusion for the diagnosis of diabetic retinopathy”.

The referees were:

–          Professor Florence Rossant, specialized in Signal & Image Processing from ISEP (Institut Supérieur d’Electronique de Paris – France

–          Professor Saïd Mahmoudi, specialized in Informatics, Software and Artificial Intelligence from the University of Mons (Belgium)

Yihao, from China, has started 4 years ago as a Master’s student and then PhD student sponsored by the Evired grant under the supervision of Gwenole Quellec, Research Director at Inserm, and the other LaTIM (UBO) team members (Mostafa, Mathieu, Pierre-Henri).

He supported the EviRed program by developing tools to jointly analyse OCTA and wide-field fundus photography based on Evired data.

Additionally, during this time with us, he’s reached the podium 7 times in international AI competitions

Good luck to Yihao for future researches in China and many thanks for the amazing contribution to the EviRed program!

NB: on the picture from the left to the right  : Saïd Mahmoudi, Mostafa El Habib Daho, Yihao Li, Gwenole Quellec, Mathieu Lamard, Pierre-Henri Conze

Evired AI team works recognized during the MICCAI conference in Vancouver ( Canada)

During the last MICCAI (Medical Image Computing and Computer Assisted Interventions) conference held from October 8-12, 2023, in Vancouver, the  UBO-LATIM team members, in charge of AI for EVIRED has presented three papers :

  1. “Longitudinal self-supervised learning using neural ordinary differential equation”/Zeghlache and al. Predictive Intelligence in Medicine. PRIME 2023. Lecture Notes in Computer Science, vol 14277. Springer, Cham. https://doi.org/10.1007/978-3-031-46005-0_1
  2. “LMT: Longitudinal Mixing Training, a framework to predict disease progression from a single image.”/ Zeghlache and al. Machine Learning in Medical Imaging. MLMI 2023. Lecture Notes in Computer Science, vol 14349. Springer, Cham. https://doi.org/10.1007/978-3-031-45676-3_3
  3. “Improved Automatic Diabetic Retinopathy Severity Classification Using Deep Multimodal Fusion of UWF-CFP and OCTA Images”/El Habib Daho, et al. Ophthalmic Medical Image Analysis” . OMIA 2023. Lecture Notes in Computer Science, vol 14096. Springer, Cham.  https://doi.org/10.1007/978-3-031-44013-7_2

Additionally, during this conference, Yihao LI and Mostafa EL HABIB DAHO distinguished themselves during two challenges, organized as part of the congress:

  1. STAGE (Structural Functional Transition in Glaucoma Assessment – https://aistudio.baidu.com/competition/detail/968/0/introduction), organized by A*STAR (Singapore) and Sun Yat-Sen University (Canton) and sponsored by Baidu, finishing 1st on one task and 2nd on another.
  2. MMAC (Myopic Maculopathy Analysis Challenge) – https://codalab.lisn.upsaclay.fr/competitions/12441#learn_the_details-overview), organized by Tsinghua University (Beijing) and Shanghao Jiao Tong University (Shanghai), finishing 1st on one task and 2nd on another.

For context, the MICCAI conference is a premier event that attracts  leading scientists – including biomedical scientists, engineers, and clinicians from a wide range of disciplines –  dedicated to research in medical imaging and computer-assisted intervention.


NB :On the pictures , UBO-LATIM members Rachid Zeghlache, Gwenolé Quellec, and Mostafa El Habib Daho are actively engaged at the MICCAI conference. In the middle-right image, they’re joined by the distinguished Professor Emanuele Trucco, a pioneer in computational vision and medical image analysis. Visitors in the bottom-right are engrossed in discussions around the team’s presented posters, showcasing the significant impact of their research.

An enthusiastic end of April for EviRed !

Two important events occurred in this end of April 2023:


  • More than 2500 patients have been included so far…. This is a great achievement in the study and the investigator sites are still motivated to increase the patient cohort.14 sites in France are participating actively to the study protocol.


  • Three posters were presented by the LATIM guys during the ARVO 2023 in New Orleans during the poster session, one of the most important international annual congress for ophthalmologists to present the promising results already obtained with  Artificial Intelligence
    • 3-D analysis of multiple OCTA acquisitions for the automated diagnosis of diabetic retinopathy.
    • Performance of two ultra-widefield retinal imaging systems for the automatic diagnosis of diabetic retinopathy.
    • Time-aware deep learning models for predicting diabetic retinopathy progression.


Evired is in progress !

Time to meet!

Part of the EVIRED team was able to meet during the Retine en Pratique 2023 congress in Paris.

It was a pleasure to meet: EviRed study coordinators, orthoptists, investigators from all centers around France met with graders and supergraders from the reading center as with the leadership team.*

Evired continues!

* Some of the contributors of the EVIRED project were not present during the photo time.

It’s time to celebrate again!

Happy Birthday EVIRED!

Since 3 years, the whole RHU EviRed team has been working very hard for the success of the project.

We are now half way through with an additional year granted by the ANR.


The consortium members (APHP, ADCIS, EVOLUCARE, LATIM-UBO, UP and Zeiss)  are making significant progress and the 14 investigating sites keep on recruiting and following patients to built one of the largest dataset and to develop the most innovative and powerful algorithms based on AI.


Many thanks to all team members involved in the project… This fantastic journey continues and has the potential to better manage patients all around the world !

Recognition of EVIRED AI team during the 25th MICCAI conference

The MICCAI (Medical Image Computing and Computer Assisted Interventions) is a non-profitable professional organization. This organization includes Scientists doing research work in the fields of Computer Science and Medicine.

During its 25th Conference, from 18-25 September 2022, in Singapore, the work of UBO-LATIM team members, in charge of AI for EVIRED was recognized by the international community

  1.     Yihao LI, Mostafa EL HABIB DAHO and Rachid ZEGHLACHE are on the 3rd step of the podium at the “Diabetic Retinopathy Analysis Challenge”. The aim of the challenge was to classify OCTA images and 74 people participated in this challenge.
  2.     Rachid was honoured by the prize of “best presentation winner 2022” of the Ophthalmology workshop.

Congratulations to Yihao, Mostafa and Rachid*! Research work performed by the LATIM-UBO team has been recognized and much appreciated during this international congress.

EVIRED is proud to have such quality partners on board.

NB : from the left to the right on the picture : Yihao LI, Mostafa El HABIB DAHO and Rachid ZEGHLACHE