Jobs & Internships opportunities
The Institut du Cerveau et de la Moelle épinière – ICM (Brain & Spine Institute) – is an international brain and spinal cord research center. ICM brings patients, doctors and researchers together with the aim of rapidly developing treatments for disorders of the nervous system.
The Centre for Neuroinformatics is a transverse structure in the Institute, gathering researchers, engineers, and IT people, united to promote excellence in data management, data analysis, and scientific computing accross the whole ICM.
ICM is ideally located in the centre of Paris, within the Hôpital de la Pitié Salpétrière. Every week, ICM is buzzing with formal and informal events related to the human brain, which you are encouraged to attend. Salsa and yoga lessons are also available, among the many other non-scientific activities available at ICM and the hospital.
Additionnally, the Centre for Neuroinformatics acts a relay for the internship offers within ICM, for projects with a strong Data Science/Mathematical component. These are unique opportunities to work within one the 28 research teams.
Deep Learning for automatic surface reconstruction in MRI
At Cenir, MRI acquisition core facility
Deep learning has been now widely applied in the MRI field, but always considering the MRI volume as a pixel images, neglecting the true nature of 3D MRI volume where pixels have a spatial dimension, and localization. We aim to develop a machine learning method, to re-construct brain tissue surfaces from several MRI volumetric acquisitions.
We want to train the neural network with simulated data from the direct model that predict the voxel intensity value from the precise localization of the surface boundary (this can be simply computed from the partial volume and the intensity value of the 2 structures). Having thus different contrast acquisition will further constrain the solution, even in the case of lower spatial resolution.
The main difficulty will be in the prediction of a high resolution surfaces, we want to explore if Convolutional graph neural networks (http://geometricdeeplearning.com/) can be used to better estimate the solution.
Possibility to continue on a PhD.
More information here.
Stratification of Alzheimer Diseases patients by automated detection of peptide accumulation in whole slide images using Deep Learning
At AramisLab, Brain Data Science
Alzheimer’s disease (AD), the most frequent neurodegenerative disease, is defined by the misfolding and accumulation of Aß peptides and of tau proteins in the brain (see Figure). Clinically, sporadic Alzheimer’s disease (AD) most commonly presents in later life as an amnestic syndrome. However, the clinical presentation of the patients is more heterogeneous and different subtypes or clusters of brain lesions have been described. In particular, the rapidly progressive subtype of AD (rpAD) is frequently misdiagnosed as Creutzfeldt-Jakob disease. The team “Alzheimer’s and prions diseases” at the ICM has contributed to describe specific traits associated with rpAD not observed in standard AD cases with slower progression.
More information here.