Within the framework of the EviRed RHU project (Intelligent Evaluation of Diabetic Retinopathy), the LaTIM laboratory is recruiting a postdoctoral researcher in artificial intelligence and image processing.
Diabetic retinopathy (DR) is a priority cause of blindness worldwide. An important obstacle to fight DR is the use of a classification based on old imaging techniques insufficient to finely predict its evolution: in ~50% of cases, ophthalmologists over or underestimate the appearance of complications. New available imaging techniques are superior: ultrawide-field fundus photography gives useful information on the periphery of the retina, not seen on standard photography. Structural optical coherence tomography, which produces few microns resolution cross sectional 3-D images, is the reference for diagnosis of diabetic macular edema. It has been enriched with OCT angiography (OCTA), which can show the vasculature of the retina non-invasively. The main objective of the EviRed project is to develop an expert system based on these new imaging techniques that will replace the current DR classification, with improved diagnosis and prediction abilities. This should help ophthalmologists make better decisions during DR follow-up, which would lead to critical progress in DR management.
This project, led by AP-HP, involves the LaTIM laboratory, as well as three industrial partners: ADCIS, Evolucare and Zeiss. Within this consortium, the LaTIM will lead AI research and development.
The LaTIM (for "Laboratoire de Traitement de l’Information Médicale", i.e. the laboratory of medical information processing) develops a multidisciplinary research where Health sciences meet Information sciences. The laboratory groups together researchers from the University of Western Brittany, the IMT Atlantique engineering school, the INSERM research institute and Brest University Hospital. Information is at the heart of LaTIM’s research project: by nature multimodal, complex, heterogeneous, shared and distributed, it is integrated by researchers into methodological solutions for the purpose of improving the quality of care.
Within the EviRed project, the postdoctoral researcher will develop innovative deep learning solutions for DR diagnosis and DR progression prediction. He or she will help supervise two PhD students and another postdoc working on specific aspects of this complex artificial intelligence problem. He or she will supervise all aspects of this team effort: data management, software specifications, development and validation, publication, etc.
The candidate must have a PhD in artificial intelligence with at least one experience in deep learning for image processing, ideally in the medical domain. We are looking indifferently for a new doctor or a doctor with a first postdoctoral experience. However, the candidate must have demonstrated excellent abilities for innovation, through scientific publications and/or patents, and for team work.
The postdoctoral position will start in early 2020 (between January and March). The candidate will be hosted by the LaTIM laboratory in Brest, France. According to the Express magazine, Brest was in 2018 the 3rd best place to live in France (https://www.lexpress.fr/region/qualite-de-vie-le-top-10-des-villes-francaises_2033780.html). This position is funded for 5 years by the National Agency for Research (ANR): our goal is to help the candidate find a permanent researcher position in the laboratory before the end of this 5-year period.
The interested candidates should contact Gwenolé Quellec (firstname.lastname@example.org) and Mathieu Lamard (email@example.com) with a full CV and a reference letter.
(c) GdR 720 ISIS - CNRS - 2011-2020.