[Comp-neuro] PhD position in machine learning at EPFL (Lausanne, Switzerland)

Milekovic Tomislav tomislav.milekovic at epfl.ch
Sun Aug 9 12:20:41 CEST 2020

PhD position in the lab of Prof. Gregoire Courtine at EPFL (Lausanne, Switzerland)

Machine learning techniques to develop and enhance computational models of the spinal cord

The laboratory of Prof. Gregoire Courtine at the Swiss Federal Institute of Technology (EPFL) in Lausanne, Switzerland, is looking to fill a fully funded PhD position. The qualified candidate will benefit from joining a very dynamic and multidisciplinary group working at the interface of computational neuroscience, neuroengineering, prosthetics and biology. EPFL provides state-of-the-art facilities and is one of the leading technical universities worldwide. PhD salaries at EPFL rank the highest in the world.

The offered position will be based at the Defitech Center for interventional Neurotherapies (NeuroRestore) - a research and innovation center joining EPFL's lab of Prof. Gregoire Courtine and the University Hospital of Lausanne (CHUV) lab of Prof. Jocelyne Bloch. NeuroRestore conceives, develops and applies medical therapies aimed to restore neurological functions. To this end, NeuroRestore integrates implantable neurotechnologies with innovative treatments developed through rigorous preclinical and clinical studies. By working with our network of vibrant high-tech start-ups and established medical technology companies, NeuroRestore is committed to validate our medical therapy concepts. The overarching goal of NeuroRestore is to see our medical therapies used every day in hospitals and rehabilitation clinics worldwide.

A therapy based on epidural electrical stimulation (EES) of the spinal cord can restore the ability to walk to people paralyzed by spinal cord injury. EES does this by recruiting sensory axons within dorsal spinal roots that enter the spinal cord between the vertebrae. Yet, clinically available electrode arrays used to deliver the EES were not designed to target individual spinal roots. Data-driven design of the electrode arrays has the potential to substantially improve the specificity of spinal EES and, therefore, dramatically improve the recovery of people with spinal cord injury. The efficacy of EES can be enhanced through computational algorithms capable of designing EES protocols that fully utilize the interaction between the electrode array and patient's anatomy. These two developments are critical for deployment of the EES-based therapy to clinics around the world to help millions of people suffering from spinal cord injury.
We have created a computational pipeline capable of creating detailed computational models of spinal columns from CT, MRI and fMRI recordings. These hybrid models are composed of 3D finite element models (FEM) to characterize the electric current and potential in the spinal cord of individuals, and various abstractions of compartmental cable models and network models of spinal cord neuronal populations and their connections to calculate the effects of EES on the spinal networks and, in turn, the activation of muscles. This computational approach has the potential to optimize the efficacy of EES on a personalized basis, lead to novel superior electrode array designs, and further our understanding of the mechanisms by which spinal cord controls movement.
The successful candidate will work to automatize our computational pipeline in order to make the described approaches useful in applied clinical practice. They will work on the development of efficient and robust computer vision algorithms to automatically segment medical imaging datasets. They will also further develop our computational pipeline to enable automatic definition of personalized EES stimulation protocols. Furthermore, they will implement a computational framework around our pipeline that can perform a large-scale and diverse sensitivity and uncertainty analysis. This framework will be critical to enhance the efficacy and explore possible novel applications of spinal cord EES.

-          Master's Degree in Physics, Computer Science, Mathematics, Microengineering, Electrical Engineering or related

-          Proficiency in Python, Matlab and C++

-          Experience with computer vision and / or other machine learning techniques

-          Good written and verbal skills in English
Applications including a CV and a cover letter describing your background and interest should be sent to MachineLearningPhD.Courtine at gmail.com. Informal inquiries are welcome.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.tnb.ua.ac.be/pipermail/comp-neuro/attachments/20200809/69c41d19/attachment-0001.html>

More information about the Comp-neuro mailing list