Development of machine learning algorithms to improve image acquisition and processing in radiological imaging
The Nuclear Measurements Laboratory at the LNPA (Laboratory for the Study of Digital Technologies and Advanced Processes) in Marcoule consists of a team specializing in nuclear measurements in the field. Its activities are divided between developing measurement systems and providing technical expertise to CEA facilities and external partners (ORANO, EDF, IAEA).
The LNPA has been developing and using radiological imagers (gamma and alpha) for several years. Some of the developments have resulted in industrial products, while other imagers are still being developed and improved. Alpha imaging, in particular, is a process that allows alpha contamination zones to be detected remotely. Locating the alpha source is an important step in glove boxes, whether for a cleanup and dismantling project, for maintenance during operation, or for the radiation protection of workers. The alpha camera is the tool that makes alpha mapping accessible remotely and from outside glove boxes.
The objective of the thesis is to develop and implement mathematical prediction and denoising solutions to improve the acquisition and post-processing of radiological images, and in particular alpha camera images.
Two main areas of research will be explored in depth:
- The development of real-time or post-processing image denoising algorithms
- The development of predictive algorithms to generate high-statistics images based on samples of real images.
To do this, an experimental and simulation database will be established to feed the AI algorithms.
These two areas of research will be brought to fruition through the creation of a prototype imager incorporating machine learning capabilities and an image acquisition and processing interface, which will be used in an experimental implementation.
Through this thesis, students will gain solid knowledge of nuclear measurements, radiation/matter interaction, and scientific image processing, and will develop a clear understanding of radiological requirements in the context of remediation/decommissioning projects.
Characterisation of reaction pathways leading to thermal runaway for new battery technologies
The development of all-solid-state cells is no longer a mere hypothesis today. As part of the Safelimove project, we assessed the safety of hybrid polymer cells of 1 Ah and 3 Ah, which led to a publication. Additionally, within the Sublime project, we evaluated the safety of 1 Ah sulfide-based cells (argyrodite), and a publication is currently being submitted.
With the arrival of these new cells, it becomes even more crucial to support their development with a detailed safety assessment and the identification of the complex mechanisms involved. Large-scale instruments such as synchrotrons and neutron reactors offer a powerful opportunity to achieve this goal, as they provide the best spatial and temporal resolutions. For example, thanks to fast X-ray radiography at ESRF, it is possible to visualize the inside of a cell during thermal runaway, thereby identifying the local impact of (electro)chemical reactions on the microstructure of components and validating our thermal runaway models. Moreover, with wide-angle X-ray scattering (WAXS), it is possible to monitor in situ the evolution of the crystalline structure of active materials during a very rapid thermal runaway reaction. Indeed, synchrotron radiation allows the acquisition of one diffractogram every 3 milliseconds. The neutron beam at ILL also enables us to track the evolution of lithium metal structure before, during, and after runaway. It is important to emphasize that these three techniques are currently mastered by the LAPS teams and have already led, or will lead, to publications.
Furthermore, new complementary techniques may be explored, such as studying the impact of thermal/mechanical stress on active materials using the BM32 beamline, or evaluating the oxidation states of metals via X-ray absorption spectroscopy (XAS) on ID26.
More conventional laboratory characterizations will also be carried out, such as DSC, TGA-MS, and XRD.
As part of our various collaborations, the cathode active materials will likely include NMC, LMFP, and NVPF. The electrolytes used will be based on sulfide, halide, or polymer, while the anode will consist of lithium metal, lithium-silicon alloy, or hard carbon. The thesis will aim, among other things, to identify, depending on the materials used, whether reactions occur before cathode destabilization, whether the solid electrolyte reacts with the oxygen from the cathode or with the anode material, and whether these parallel reactions contribute to better or worse cell safety.
The three years of the PhD will be structured as follows: the first year will be dedicated to a literature review and the characterization of sulfide technology. Following the first milestones (1st CSI) and the evaluation of ongoing work on sulfides, the second year will focus either on sodium-ion technology or on further development of sulfide technology. Finally, the third year, in addition to the thesis writing, will concentrate more specifically on the impact of the identified materials on safety.
CONTEXT: strain - texture neutron instrumentation for ICONE
The CEA and the CNRS have launched an initiative to design a new neutron source using low-energy proton accelerators, the ICONE project. The objective is to build a facility that will offer an instrumental suite of about ten spectrometers available to the French and European scientific community. The project is currently in the Preliminary Design phase, with the aim of refining as much as possible all technical aspects.
We are proposing a PhD thesis on the modeling and development of a new neutron scattering spectrometer for measuring textures and stresses in materials. This technique makes it possible to probe residual stresses in materials after machining, heat treatment, and/or use, and to measure the crystallographic anisotropy of alloys to exploit the induced mechanical properties.
Part of the work will take advantage of the start-up of the DREAM and MAGIC spectrometers at ESS in Sweden, in which the LLB participated in the construction, so that the candidate can become familiar with time-of-flight neutron scattering techniques (measurements and data analysis).
In the second part of this work, we propose to implement statistical modulation techniques for the construction of an instrument, CONTEXT, on ICONE, which will allow to best exploit the potential of ICONE's long pulses. The objective will be to create a digital twin of the future instrument using various Monte Carlo simulation tools.
Ultra-fast pathogenic bacteria detection in human blood
This project aims to develop a versatile and easy-to-use surface plasmon resonance imaging (SPRi) instrument for the rapid and broad-spectrum detection of low concentrations of pathogenic bacteria in complex samples, particularly blood. SPRi is a label-free technique that allows real-time probing of a sample (regardless of its optical transparency). Due to the high sensitivity of the plasmon phenomenon, the dynamic range of measurable index variation is limited by SPRi detection when reading is performed at a fixed angle, as is the case in commercially available devices. This reduces the use of such optical instruments to the study of environments whose index remains relatively stable during the experiment and whose molecular probes have molecular weights comparable to the targets (monitoring of bimolecular interactions).
This considerably limits the detection of growing bacteria in complex environments. Our laboratory has developed original solutions for the detection of very low levels of contamination in food matrices (creation of a start-up in 2012), but SPRi is unsuitable for the detection of bacteria in blood, partly due to the very high intrinsic variability of this matrix.
These limitations will be overcome by integrating five complementary components:
1. The design of an instrument optimized for real-time recording of SPR images over a defined range of illumination angles;
2. The development of dedicated SPR data analysis and processing to extract the most relevant information for each probe from the images in real time;
3. The functionalization of biochips through a combination of appropriate probes (series of peptides such as antimicrobial peptides (AMPs), antibodies, and even bacteriophages) to optimize the number of possible identifications with a reduced set of probes;
4. The learning of specific “4D-SPRi signatures” of model strains in blood matrices;
5. Validation of the performance of the new “4D-SPRi” instrument as a tool for detecting and characterizing bacteria from hospital strains compared to reference techniques.