The Marie S. Curie Postdoctoral Fellowship (MSCA-PF) programme is a highly prestigious renowned EU-funded scheme. It offers talented scientists a unique chance to set up 2-year research and training projects with the support of a supervising team. Besides providing an attractive grant, it represents a major opportunity to boost the career of promising researchers. 

The LTSI MediCIS Team, INSERM Université de Rennes is thus looking for excellent postdoctoral researchers with an international profile to write a persuasive proposal to apply for a Marie S. Curie Postdoctoral Fellowship in 2025 (deadline of the EU call is set for 10th September 2025). The topic and research team presented below have been identified in this regard.

Main Research Field 

Information Science and Engineering (ENG)

Research sub-fields

Artificial Intelligence, Computer Vision, Surgical Data Science, Medical Imaging 

Keywords

Artificial Intelligence, Computer Vision, Surgical Data Science, ENT surgery, Medical Image Processing

Research project description

Context: Cochlear implants are a rapidly developing treatment for particular types of deafness and hearing disorders in patients ranging from young children to the elderly. However, the surgery required for these implants is very delicate, aligning particular elements of a grid of electrodes to very particular yet microscopic locations within the depths of the inner ear (Carlyon & Goehring, 2021). Additionally, programming the implant stimulation parameters is crucial and it is the combination of surgical and stimulation parameter optimization that will guarantee the best clinical result for the patient. Thus, correctly implementing a cochlear implant is complex and multi-faceted process, relying on expertise from multiple different domains including otology, medical image computing, signal processing, and hardware design.

Objectives: Cochlear implant surgery involves several pre- and post-operative objectives which must be met, three of which form the objectives of this project. Although these three objectives largely correspond with the creation and utilization of functional atlases for cochlear implant surgery, they also illustrate the breadth of techniques necessary for effective research in surgical data science.

Prior to surgery, the patient undergoes CT imaging in order to visualize the anatomy of the inner ear. This allows for the clinician to visualize the structures of the inner ear and to develop a surgical plan. Due to the small size of the internal structures of the cochlea with respect to the CT image resolution, segmentation of these structures has largely depended on inferring them using models of the cochlea taken from high-resolution micro-CT scans (Noble et al. 2011) or to synthesize said high-resolution directly in the patients’ images (Liu et al., 2023). The first objective of this project is to implement both approaches simultaneously, using them as the basis for surgical planning. This will also allow for a high-resolution common co-ordinate space for the cochlea to which multiple patient images, surgical plans, and final implant locations can be registered and compared.

Immediately following the implantation of the electrode grid, imaging is necessary to verify whether or not it is correctly positioned according the surgical plan (Stelter et al., 2012). CT is again used for this task but suffers from artifacts resulting from the implant as well as limited resolution due to the desire to minimize the patient’s exposure to ionizing radiation. In theory, the process of CT image reconstruction process could be facilitated by taking into account the large amount of information present in the patient’s pre-operative CT. The second goal of this project is to use this information to investigate the potential to minimize the number of CT projections needed (and thus minimize radiation exposure) through the use of image registration between a sparse set of CT projections and the patient’s prior CT image. This objective should not only allow for safer CT acquisition, but should also be capable of segmenting introduced structures, notably the cochlear implant, for later analysis.

Finally, once the implant positioned is verified, its stimulation parameters need to determined. Currently, this is done in a non-patient-specific manner, using the same mapping from auditory frequencies to electrodes for all patients. Recently, there has been evidence that patient-specific tunings can improve hearing retention, overcoming variability in the surgery and in the patients themselves (Creff et al., 2024). Through the previous two objectives, we will have developed a methodology for measuring the former which can be used to provide an intelligent initialization for the implant parameters. One the implant parameters are optimized for the individual patient, our anatomical space will allow for population variability to be measured in terms of not only the implant location but also the resulting stimulation. Rather than relying solely on the patient’s observable behavior and reports, we will also make use of EEG to quantitatively and objectively measure the patient’s neurological response to auditory stimuli mediated by the implant (Intartaglia et al., 2022). This will allow us to create population-wide functional atlases of the cochlea that capture patient and disease variability.

This project will rely on the collection of patient data at all stages of the cochlear implantation process collected with collaborating clinicians in the Rennes University Hospital Department of Otorhinolaryngology and in collaboration with the Collin Medical, a French company which develops surgical robots and guidance systems for middle and inner ear surgeries.

1. Carlyon, R. P., & Goehring, T. (2021). Cochlear implant research and development in the twenty-first century: a critical update. Journal of the Association for Research in Otolaryngology, 22(5), 481-508.
2. Creff, G., Lambert, C., Coudert, P., Pean, V., Laurent, S., & Godey, B. (2024). Comparison of Tonotopic and Default Frequency Fitting for Speech Understanding in Noise in New Cochlear Implantees: A Prospective, Randomized, Double-Blind, Cross-Over Study. Ear and Hearing, 45(1), 35-52.
3. Intartaglia, B., Zeitnouni, A. G., & Lehmann, A. (2022). Recording EEG in cochlear implant users: Guidelines for experimental design and data analysis for optimizing signal quality and minimizing artifacts. Journal of neuroscience methods, 375, 109592.
4. Liu, Z., Fan, Y., Lou, A., & Noble, J. H. (2023). Super-Resolution Segmentation Network for Inner-Ear Tissue Segmentation. In International Workshop on Simulation and Synthesis in Medical Imaging (pp. 11-20).
5. Noble, J. H., Labadie, R. F., Majdani, O., & Dawant, B. M. (2011). Automatic segmentation of intracochlear anatomy in conventional CT. IEEE Transactions on Biomedical Engineering, 58(9), 2625-2632.
6. Stelter, K., Ledderose, G., Hempel, J. M., Morhard, D. F., Flatz, W., Krause, E., & Mueller, J. (2012). Image guided navigation by intraoperative CT scan for cochlear implantation. Computer Aided Surgery, 17(3), 153-160.

Supervisors

The Postdoctoral Fellow will be co-supervised by John S.H. Baxter and Pierre Jannin from the MediCIS research group which is part of both Inserm (LTSI, UMR 1099) and the University of Rennes.

Pierre Jannin is an Inserm Research Director at the Faculty of Medicine of the University of Rennes (France) and director of the MediCIS research group. He has more than 30 years of experience in designing and developing computer assisted surgery systems. His research topics include surgical data science, surgical robotics, image-guided surgery, augmented and virtual reality, modeling of surgical procedures and processes, study of surgical expertise, and surgical training. He authored or co-authored more than 150 peer-reviewed international journal papers. He was the President of the International Society of Computer Aided Surgery (ISCAS) from 2014 to 2018. He is the Editor-in-Chief of Computer Assisted Surgery (Taylor&Francis).

John S.H. Baxter is an Inserm Researcher affiliated with the University of Rennes (France) studying the intersection of machine learning and human computer interaction for medical imaging. Despite only obtaining his Ph.D. in 2017, John already has 20 first- or last- authored peer-reviewed papers in international journals and is part of the scientific committees of the annual conference on Computer Assisted Radiology and Surgery (CARS) and the SPIE Medical Imaging Conference on Image-Guided Procedures, Robotic Interventions and Modeling. He is also a member of the MICCAI Society Office which organises the annual conference on Medical Image Computing and Computer Assisted Interventions (MICCAI).

MediCIS webpage: https://medicis.univ-rennes1.fr/

Pierre Jannin profile: https://scholar.google.com/citations?user=yr_qKA0AAAAJ

John S.H. Baxter profile: https://scholar.google.com/citations?user=zB8zUmYAAAAJ

Department/Research                       

The Laboratory of Signal and Image Processing (LTSI), is an INSERM laboratory at the University of Rennes with about 150 researchers dedicated on BioMedical Engineering research. The MediCIS team, located at the medical university, is part of the LTSI and focuses on the study of surgical data science for different applications such as assistance in the OR, surgical robotics and evaluation and training, with the participation of surgeons from the Rennes University Hospital. The primary surgical applications of MediCIS include functional neurosurgery, ob/gyn, urology, and orthopaedics. This research team has published pioneering work in surgical skill assessment, augmented reality in surgery, surgical workflow analysis and procedure modeling, and ontologies for medical imaging and surgery.

https://medicis.univ-rennes1.fr/

Location: Faculty of Medicine, University of Rennes

Skills Requirements 

• A Ph.D. degree in computer science, biomedical engineering, or a related field.
• Strong background in machine learning, computer vision, and medical image processing.
• Proficiency in programming languages such as Python, C++, or MATLAB.
• Experience with deep learning frameworks (e.g., TensorFlow, PyTorch) and relevant libraries.
• Prior exposure to medical imaging or surgical data analysis is advantageous but not mandatory.
• Publications in high impact international scientific journals
• Excellent communication skills and ability to work collaboratively in a multidisciplinary team environment.

Eligibility criteria  for applicants

Academic qualification: By the MSCA-PF call deadline (10 September 2025), applicants must be in possession of a doctoral degree, defined as a successfully defended doctoral thesis, even if the doctoral degree has yet to be awarded.

Research experience: Applicants must have a maximum of 8 years full-time equivalent experience in research, measured from the date applicants were in possession of a doctoral degree. Years of experience outside research and career breaks (e.g. due to parental leave), will not be taken into account.

Nationality & Mobility rules: Applicants can be of any nationality but must not have resided more than 12 months in France in the 36 months immediately prior to the MSCA-PF call deadline (10 September 2025).

Application process

We encourage all motivated and eligible postdoctoral researchers to send their expressions of interest through the EU Survey application form (link here)[1], before 31st May 2025. Your application shall include:

• a CV detailing: (i) for each position you had, the exact dates and location (country) and (ii) a list of accepted publications;
• a cover letter including a research outline (up to 2 pages) identifying the research synergies with the project supervisor(s) and proposed research topics described above.

Estimated timetable

Deadline for sending an expression of interest: 31st May 2025

Selection of the applicant: June 2025 at the latest

Writing the MSCA-PF proposal with the support of the above-mentioned supervisors: June – September 2025

MSCA-PF 2025 call deadline: 10 September 2025

Publication of the MSCA-PF evaluation results: February 2026

Start of the MSCA-PF project (if funded): May 2026 (at the earliest)