Distributed deep learning for classifying multimodal, uncertain and rare data in ophthalmology

• The joint laboratory ADMIRE (Distributed deep learning for the classification of Multimodal, Uncertain and Rare data in ophthalmology), selected as a LabCom in 2019 by the ANR, reinforces the collaboration of Evolucare Technologies with the laboratory LaTIM Inserm UMR1101/UBO.

• The purpose of the partnership is to develop innovative algorithms for the detection of various ocular pathologies or those visible through the eye, while respecting the privacy rights of patients.

.

Evolucare & LaTIM = a common goal

• The common objective of LaTIM and Evolucare Technologies is to extend the screening to all pathologies affecting the eye, or visible through the eye (cardiovascular pathologies, neurodegenerative pathologies, etc.). In order for each of these diseases to be represented by a sufficient number of examples, the images must come from a much more varied population than the diabetic population. This is only possible if the data come from several clinical centers. Thus, within the framework of the ADMIRE LabCom, the clinical centers using the Evolucare Technologies cloud participate if they wish in the progressive enrichment of the artificial intelligence (AI). In addition to a retrospective analysis of each center’s data, users’ feedback on AI diagnoses helps refine the learning process over time. 

• The implementation of this distributed and secure AI platform will also enable the two partners to jointly address new clinical issues in the coming years.