Super-resolution of brain MR images: from research to the clinic through machine learning approaches.
Magnetic Resonance Imaging (MRI) has become a reference modality for diagnosing and monitoring neurological disorders. However, acquiring high-resolution (HR) brain images remains challenging in clinical practice due to limited scan time, patient comfort constraints, and image degradation caused by patient motion. The increased signal enabled by higher magnetic field strengths can be invested to achieve higher spatial resolution within the same acquisition time. This project aims at taking advantage of the unprecedented spatial resolution achievable with the 11.7T Iseult MRI scanner, currently the most powerful MR scanner in the world, to train a machine learning-based super-resolution (SR) model that enhances the spatial resolution of 3T MRI images acquired in clinical practice. Current SR approaches are typically trained on public datasets, using pairs of high- and low-resolution images, with the low-resolution data synthetically generated from the high-resolution images. In this project we will use a real dataset consisting of 3T and 11.7T images acquired from the same cohort, ensuring higher anatomical fidelity and enabling a rigorous assessment of hallucination risks, i.e. of generating anatomically incorrect details that could be misinterpreted by the radiologists. The project will involve the following steps: improving the quality of 11.7T images (through motion correction and artifact reduction), acquiring pairs of images at 3T and 11.7T, developing and validating SR models, and finally assessing their generalizability on public datasets. This work supports the integration of reliable SR methods into clinical practice, allowing conventional MRI scanners to benefit indirectly from Iseult's unique capabilities.
Ultra-low frequency wireless power transmission for sensor node charging
Wireless power transfer (WPT) technologies are rapidly expanding, particularly for wireless charging of everyday electronic devices and for powering wireless communicating sensor nodes. However, their transmission ranges remain limited, and the high operating frequencies typically used prevent energy transfer in the presence of, or through, conductive media (such as metallic barriers or seawater). This constraint significantly limits their adoption in complex environments (industrial, biomedical, etc.).The ultra-low-frequency technology investigated in our laboratory is based on an electromechanical receiver system comprising a coil and a magnet set into motion by a remotely generated magnetic field. The objective of this PhD project is to propose and develop novel ultra-low-frequency concepts to increase transmission range while maintaining sufficient power density for supplying sensor systems. The work will therefore involve studying, designing, optimizing, and experimentally validating the performance of new topologies (emitter field shaping, receiver geometries and materials, etc.). The candidate will develop analytical and numerical models to identify key system parameters and compare performance with the state of the art (range, power density, sensitivity to orientation). In addition, the candidate will propose, design, and experimentally evaluate innovative energy conversion electronics, on the transmitter and/or receiver side, to assess their impact on the overall system performance. A joint optimization of the electromechanical system and its associated power electronics will ultimately lead to the realization of a high-performance wireless power transfer system. A multidisciplinary profile with a strong orientation toward physics and mechatronics is sought for this PhD project. In addition to solid theoretical foundations, the PhD candidate must demonstrate the ability to work effectively in a team environment as well as a strong aptitude for experimental work. The PhD candidate will be integrated into the Systems Department of CEA-Leti, within a team of researchers with strong expertise in the development and optimization of electronic and mechatronic systems, combining innovative solutions for energy harvesting, wireless power transfer, low-power electronics, and sensor integration aimed at the development of autonomous systems.
Development of an integrated solid state nanopore analysis system
The identification of biological material (DNA, RNA, proteins,…) is generally done thanks to cumbersome lab equipment and/or rely on ultra-specific and proprietary sensitive reagents. We aim to develop a new platform based on the solid-state nanopore technology which could produce label-free results on field.
One way to pierce a nanopore in an ultra-fine dielectric membrane is to use an electron beam. An ion current is obtained when placing this pierced membrane in-between two insulated reservoirs filled with electrolytes and applying a low voltage. A particle going through the pore modifies this ionic current giving us information on its size, charge or conformation.
For this technique to yield the best results we need control over each bit of the platform: the dielectric assembly and nanopore within; the high speed and precision electronic apparatus to measure ionic current; the fluidic integration and even the algorithm responsible for deciphering the current trace. Starting from the simplest setup possible, the PhD candidate will have to push forward every aspect of this ambitious project, aiming for protein sequencing, relying on the multiple expertise of the Leti and the Lambe laboratory.
Lightweight CNN and Causal GNN for scene understanding
Scene understanding is a major challenge in computer vision, with recent approaches dominated by transformers (ViT, LLM, MLLM), which offer high performance but at a significant computational cost. This thesis proposes an innovative alternative combining lightweight convolutional neural networks (Lightweight CNN) and causal graph neural networks (Causal GNN) for efficient spatio-temporal analysis while optimizing computational resources. Lightweight CNNs enable high-performance extraction of visual features, while causal GNNs model dynamic relationships between objects in a scene graph, addressing challenges in object detection and relationship prediction in complex environments. Unlike current transformer-based models, this approach aims to reduce computational complexity while maintaining competitive accuracy, with potential applications in embedded vision and real-time systems.
Development of automatic gamma spectrum analysis using a hybrid machine learning algorithm for the radiological characterization of nuclear facilities decommissioning.
The application of gamma spectrometry to radiological characterization in nuclear facility decommissioning, requires the development of specific algorithms for automatic gamma spectrum analysis. In particular, the classification of concrete waste according to its level of contamination, is a crucial issue for controlling decommissioning costs.
Within CEA/List, LNHB, in collaboration with CEA/DEDIP, has been involved for several years in the development of tools for the automatic analysis of low-statistics gamma spectra, which can be applied to scintillator detectors (NaI(Tl), plastics). In this context, an original approach based on a hybrid machine learning/statistics spectral unmixing algorithm has been developed for the identification and quantification of radionuclides in the presence of significant deformations in the measured spectrum, due in particular to interactions between the gamma emission from the radioactive source and its environment.
The proposed subject follows on from thesis work that led to the development of the hybrid algorithm with the aim of extending this approach to the radiological characterization of concrete surfaces. The candidate will be involved in the evolution of the hybrid machine learning/statistical algorithm for the characterization of concrete for classification as conventional waste. The work will include a feasibility study of modeling the deviations of the learned model to optimize the robustness of decision-making.
Optimized control of a modular energy hub with minimal EMC signature
The integration of renewable energy sources (RES) has become an important issue for power converters. The increasing number of these converters and their average utilization rate allows for a rethink of energy exchange management at the system level. This leads us to the concept of an energy hub, which can interface, for example, a photovoltaic (PV) system, an electric vehicle, a grid, and stationary storage with loads.
The main objective of this thesis is to improve the efficiency, compactness, and modularity of the energy hub through control. Several ideas emerge to achieve this, such as advanced control to minimize losses, the use of AC input opposition to reduce electromagnetic compatibility (EMC) filtering, series/parallel DC output configurations to address 400Vdc/800Vdc batteries, and increasing the switching frequency to reduce volume, etc.
Thus, this thesis will, in the medium term, lead to the development of an optimal converter in terms of both energy efficiency and environmental impact.
Learning Mechanisms for Detecting Abnormal Behaviors in Embedded Systems
Embedded systems are increasingly used in critical infrastructures (e.g., energy production networks) and are therefore prime targets for malicious actors. The use of intrusion detection systems (IDS) that dynamically analyze the system's state is becoming necessary to detect an attack before its impacts become harmful.
The IDS that interest us are based on machine learning anomaly detection methods and allow learning the normal behavior of a system and raising an alert at the slightest deviation. However, the learning of normal behavior by the model is done only once beforehand on a static dataset, even though the embedded systems considered can evolve over time with updates affecting their nominal behavior or the addition of new behaviors deemed legitimate.
The subject of this thesis therefore focuses on studying re-learning mechanisms for anomaly detection models to update the model's knowledge of normal behavior without losing information about its prior knowledge. Other learning paradigms, such as reinforcement learning or federated learning, may also be studied to improve the performance of IDS and enable learning from the behavior of multiple systems.
Side-Channel based Reverse-Engineering
The characterization of the security of embedded systems in "black box" or "gray box" against Side-Channel attacks often requires a preparatory phase of Reverse-Engineering, which can be particularly time-consuming, especially on a complex System-on-Chip that can be found in smartphones or in the automotive industry. This phase can, for example, consist of detecting a cryptographic primitive within Side-Channel measurements for a future observation attack, or a target routine for a fault injection attack. The objective of this thesis is to develop a methodology and non-profiled tools that allow the automation of this detection phase, while enabling the exploitation of prior knowledge of a potential attacker.
Gyrokinetic modelling of the nonlinear interaction between energetic particle-driven instabilities and microturbulence in tokamak plasmas
Tokamak plasmas are strongly nonlinear systems far from thermodynamic equilibrium, in which instabilities of very different spatial scales coexist, ranging from large-scale macroscopic oscillations to microturbulence. The presence of energetic ions produced by fusion reactions or by auxiliary heating further enhances these instabilities through wave–particle resonances. Microturbulence is responsible for heat and particle transport in the thermal plasma, while instabilities driven by energetic particles can induce their radial transport and, consequently, their losses. Both phenomena degrade the performance of present tokamak plasmas, and possibly also those of burning plasmas such as ITER.
Recent results, however, show that these instabilities, which have long been studied separately, can interact nonlinearly, and that this interaction may lead to an unexpected improvement of plasma confinement.
The objective of this project is to investigate these multiscale interactions using the gyrokinetic code GTC, which is able to simultaneously simulate turbulence and energetic-particle-driven instabilities. This work aims to improve the understanding of the nonlinear mechanisms governing plasma confinement and to identify optimal regimes for future fusion plasmas.
Electromagnetic Signature Modeling and AI for Radar Object Recognition
This PhD thesis offers a unique opportunity to work at the crossroads of electromagnetics, numerical simulations, and artificial intelligence, contributing to the development of next-generation intelligent sensing and recognition systems. The intern will join the Antenna & Propagation Laboratory at CEA-LETI, Grenoble (France), a world-class research environment equipped with state-of-the-art tools for propagation channel characterization and modelling. A collaboration with the University of Bologna (Italy) is planned during the PhD.
This PhD thesis aims to develop advanced electromagnetic models of near-field radar backscattering, tailored to radar and Joint Communication and Sensing (JCAS) systems operating at mmWave and THz frequencies. The research will focus on the physics-based modeling of the radar signatures of extended objects, accounting for near-field effects, multistatic and multi-antenna configurations, as well as the influence of target materials and orientations. These models will be validated through electromagnetic simulations and dedicated measurement campaigns, and subsequently integrated into scene-level and multipath propagation simulation tools based on ray tracing. The resulting radar signatures will be exploited to train artificial intelligence algorithms for object recognition, material property inference, and radar imaging. In parallel, physics-assisted AI approaches will be investigated to accelerate electromagnetic simulations and reduce their computational complexity. The final objective of the thesis is to integrate radar backscattering-based information into a 3D Semantic Radio SLAM framework, in order to improve localization, mapping, and environmental understanding in complex or partially obstructed scenarios.
We are seeking a student at engineering school or Master’s level (MSc/M2), with a strong background in signal processing, electromagnetics, radar, or telecommunications. An interest in artificial intelligence, physics-based modeling, and numerical simulation is expected. Programming skills in Matlab and/or Python are appreciated, as well as the ability to work at the interface between theoretical models, simulations, and experimental validation. Scientific curiosity, autonomy, and strong motivation for research are essential.The application must include a CV, academic transcripts, and a motivation letter.