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.

Jobs

Scientific Application Engineer

Centre for Neuroinformatics

You will participate in the implementation, management, development and administration of applications (mainly from the academic world) whose purpose is to organize and structure the Institute’s scientific data: biological and clinical data, neuro-imaging, electrophysiological data, genomic data, etc.

More information here.

Full Stack Web Developer (PHP and/or Java)

Centre for Neuroinformatics

You will participate in the development of applications aimed at organizing, structuring and exploiting all of the Institute’s scientific data: biological and clinical data, neuroimaging, electrophysiological data and genomic data.

More information here.

PhD fellowship

AramisLab

Multimodal analysis of neuroimaging and transcriptomic data in genetic fronto-temporal dementia

More information here.

Internships

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.

Pseudo-healthy image synthesis for the detection of anomalies in the brain, a deep learning approach

At AramisLab, Brain Data Science

Neuroimaging offers an unmatched description of the brain’s structure and physiology, which explains its crucial role in the understanding, diagnosis, and treatment of neurological disorders. However, identifying subtle pathological changes simply by looking at images of the brain can be a difficult task. For this reason, images are often transported to a standard space where they can be visually or quantitatively compared to images of normal controls. The main limitation of this approach is its lack of sensitivity due to variabilities between subjects in non-pathological areas.

A solution has been proposed by our team to mitigate this limitation [1,2]. The approach consists of generating a healthy-looking image specific to the patient under investigation. When compared to the real image of the patient, the pseudo-healthy model can be used to detect the areas of the image that show abnormalities. These abnormality maps could help clinicians in their diagnosis by highlighting pathological areas in a data-driven fashion, and improve the interpretability of subsequent analyses, such as computer-aided diagnosis or spatio-temporal modelling.

More information here.

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.

Effect of exposure to radiofrequency electromagnetic fields on cerebral electrical activity

At Cenir, MRI acquisition core facility

In the current context of questioning about the possible effects of electromagnetic fields in humans, Ineris is conducting a study on the effects of radiofrequency (RF) electromagnetic fields (EMF) on resting state EEG. An exposure protocol with mobile phones was set up to study the effects of EMC-RF on wakeful EEG in healthy volunteers.

The goal of this internship is to better understand the alteration of the alpha band and cortical structures involved in these changes, due to RF exposure in healthy volunteers.

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.

For other job offers at ICM, see the recruitment website (in english) and in french.