DESCRIPTION :
Multiple Sclerosis (MS) is a common and potentially debilitating disease affecting around 3 millions persons in the world. Currently, Magnetic Resonance Imaging (MRI) plays a central role in this context and in particular allows the identification of MS lesions in the central nervous system.
The identification of these lesions on a given MRI image, and of new lesions between pairs of longitudinal MRI images, is a complex and mentally demanding task that often leads to an underestimation of disease activity, even for most experienced radiologists. There is thus a need for dedicated systems that can provide clinicians an aid for accurate and robust identification of MS lesions in the brain as in the spinal cord.
The development and the evaluation of such system is one of the research topic of the Empenn research team. In practice such systems generally stand on deep-learning methods. Such methods rely on an extensive use of annotated and non-annotated data. To allow the design and the evaluation of methods efficiently and robustly dealing with real-life data, the characteristics of data and annotations must be well documented and accessible. Moreover, data annotations must be iteratively revised to improve the quality of the database. Therefore, initiating and accumulating a high-quality annotated database for such a medical purpose needs dedicated tools to ease the different associated operations. The development and maintenance of these tools as well as the participation to the different projects exploiting the databases will consist of the two main missions of the selected candidate.
The selected candidate will join the research lab Empenn in Inria-Irisa, located in Rennes, France. Empenn (https://team.inria.fr/empenn) is jointly affiliated with Inria, Inserm (National Institute of Health and Scientific Research), CNRS (INS2I institute), and the University of Rennes I. The Empenn group operates the Neurinfo imaging facility in the context of a partnership with the University Hospital of Rennes, Inria, the CNRS, and the Cancer Research Center. The team has access to several computing facilities (e.g. IGRIDA cluster) and established collaborations with other Inria/Irisa research teams in the field of machine learning., The selected candidate will focus on i) mastering and developing tools to monitor, populate and exploit the databases and ii) managing the data and ease the data usage for the different projects exploiting the database. More specifically, he/she will:
* ensure the development of the MS imaging database. This includes the maintaining and development of tools to:
+ identify and organize MR images, experts annotations and associated metadata,
+ populate the database,
+ control data integrity,
+ ease data segmentations/annotations,
+ automate numerical and graphical summaries of data, extract relevant subsets of data from a variety of conditions,
be involved in the different projects exploiting the databases. We continuously work on several research projects involving the MS databases. Each of these projects comes with its own specificity regarding data characteristics, annotation and data access. The selected candidate will help the responsible of the different projects to summarize and access the available data related to their particular purposes. Depending on the candidate's skills and motivations, he/she will participate in the elaboration of the experiments or the development of specific tools for some of these projects.
* be involved in the valorization of the database. In particular, the team organized the past two international MS segmentation challenges (MSSEG-1 and MSSEG-2) and will organise in 2025 an international challenge devoted to the segmentation of spinal cord MS lesions (MS-Multi-Spine). Moreover, several other data sources could be included in this aspect of the work.
More generally, the selected candidates will collaborate with the other engineers, researchers and clinicians of the team involved in MS research and image processing as well as with the OFSEP, the French National Cohort of MS patients.
Principales activités
From a technical perspective, the activities will include :
* the maintaining of existing R/python code as well a the developpement, documentation and maintaining of new R/python scripts to:
+ identify and organize MR images, experts annotations and associated metadata,
+ populate the database
+ control data integrity,
+ ease data segmentations/annotations,
+ automate numerical and graphical summaries of data,
+ extract relevant subsets of data from a variety of conditions.
* (depending on candidate skills) the developpement and maintaining of image processing tools associated to the ongoing projects related to the database.
* the collaboration with different members of the associated projects to design and extract dataset relevant to their needs.
Code d'emploi : Architecte de Données (h/f)
Domaine professionnel actuel : Spécialistes Bases de Données
Temps partiel / Temps plein : Plein temps
Type de contrat : Contrat à durée indéterminée (CDI)
Compétences : Analyse des Données, Programmation Informatique, Bases de Données, Intégrité des Données, Sécurité des Données, Python (Langage de Programmation), Machine Learning, Deep Learning, Axé sur le Succès, Motivation Personnelle, Recherche, Systèmes Automatisés, Imagerie Médicale, Travaux Cliniques, Expérimentation, Traitement d'Image, Lesion, Imagerie par Résonance Magnétique (IRM), Maintenance et Dépannage, Sclérose en Plaque, Systèmes Nerveux, Radiologie Conventionnelle, Recherche Scientifique, Imagerie, Annotations, Recherche contre le Cancer
Courriel :
benoit.combes@inria.fr
Téléphone :
0299847100
Type d'annonceur : Employeur direct