Please download the attached pdf file for a detailed description of this PhD project
Summary
Application of machine learning (ML) to healthcare is among the most challenging ones with the potential to exploit information provided by an exponentially growing mass of heterogeneous data (images, semantic information, biological parameters,..). Those models require a large amount of data to perform well, particularly in the era of large-scale deep neural networks. One option to increase the training population is to promote multi-centre clinical studies, which opens many privacy-related problems since data producers lose control over their data as well as huge data traffic. Federated learning (FL) is a new ML approach that was recently introduced to counterbalance the need to access large databases by the responsibility to maintain the privacy of individual participants. In this context, FL appears as a very promising technique, first to account for patient privacy thus complying with the increasingly stringent general data protection regulations (GDPR) and then to limit the huge amount of data traffic required when gathering medical data to a centralized server. This research field is in its early premise and needs to address key challenges related to the specificity of medical data. The aim of this PhD is to investigate methodological research in this domain with application to the design of diagnosis and prognosis models of brain pathology based on multimodality imaging.
Keywords : Federated Machine Learning – Medical Imaging – Diagnosis and Prognosis Models – Privacy and Security
Thesis supervision and collaboration
The PhD candidate will be co-supervised by Stefan Duffner (MCF INSA HDR – LIRIS) and Carole Lartizien (DR CNRS – CREATIS). Carole Lartizien, has expertise in machine learning for medical image analysis. She will contribute to provide her expertise on AI based diagnosis models of neuroimaging data and access to the imaging datasets. Stefan Duffner has strong expertise in machine learning for computer vision. He will contribute to this collaboration with his extensive knowledge and competence in neural network models and learning algorithms under challenging conditions (e.g. few, non i.i.d. data; uncertainty/noise; heterogeneity) applied to this new medical image analysis context.
Working environment and salary
The doctoral student will share his/her time between the two laboratories according to the needs and the progress of the project. He/she will participate in team meetings in both laboratories to benefit as much as possible from the two scientific stimulating environment of the MYRIAD and IMAGINE teams. The PhD candidate will benefit from ongoing collaborations with external experts in the machine learning and neuroimaging domains. He/she will have access to multimodality imaging databases that have been collected for the two use case applications considered in the PhD project.
Employment would ideally start in Fall 2021 and is funded half by INSA Lyon  and the French National Research Agency (ANR) under the IADoc Research program. Salary is around 1700 euros net per month (+ teaching)
Profil of the Applicant
The candidate is expected to have strong knowledge in machine learning and some experiment in image processing. Some prior experience with medical image processing would be appreciated but is not required. Good programming skills (python..) are also required. We are looking for an enthusiastic and autonomous student with strong motivation and interest in multidisciplinary research (image processing and machine learning in a medical context).
Contact
For more details on the position, please contact carole.lartizien@creatis.insa-lyon.fr and stefan.duffner@insa-lyon.fr with your CV.
The formal application procedure will be detailed upon request. Deadline for application is 23rd of April 21.