Medical Diagnostic by Artificial Intelligence applied to LIBS Elemental Microscopy – dIAg-EM

WP0: Management and coordination (PI: Partner 1 / Other contributions: All partners)
WP1: Development and validation of the AI methodology (PI: Partner 3 / Other contributions: Partners 1 and 4)
WP2: Collection of animal and human lung biopsies (PI: Partner 2 / Other contribution: Partner 5)
WP3: AI-LIBS analysis of the collected samples (PI: Partner 1 / Other contribution: Partner 3)
WP4: Interpretation of the results (PI: Partner 2 / Other contribution: Partner 5)
WP5: Implementation of the LIBS-AI solution (PI: Partner 1)

IAB(2) - CHUGA(5) - ILM(1): Analysis of rare pathologies
a) Sarcoidosis: Analysis of r, 6 lung biopsies from Belgian patients. Collaboration Dr. Steven Ronsmans (University Hospital of Leuven).
b) Podoconiosis (a rare tropical disease that can cause swelling of the legs). The collections of samples analyzed consisted of biopsies of the patient's skin and lymph nodes. Collaboration with Brighton and Sussex Medical School.

LP3(4) – ILM(1): Spectrum Simulation Methodology – application to self-absorption and simulations of Al and Ti (1 article published, 1 in progress). The comparison between measured and calculated spectra allowed us to identify several spectral lines of the aluminum atom for which the Einstein coefficients of spontaneous emission are not listed in the spectroscopic databases (NIST and Kurucz). These lines, belonging to the second configuration of the atom, are of great interest for temperature measurements because of their high excitation energy. We therefore measured these Einstein coefficients and compared the values ??to those obtained by atomic structure calculations. Good agreement was observed, and these results will be published in 2023.

Lasire(3) – ILM(1): Implementation of a network structure for Calcium Carbonates. Development of the AI ??methodology. Ms. Qiecheng Wu's thesis (defence scheduled for December 15, 2022). This work also gave rise to the development of a new strategy for analyzing LIBS data from biopsies carried out by partner 3, named IFF (Interesting Features Finder) with 1 article published and 1 article in the process of being published.

xxx

1. Interesting features finder (IFF): Another way to explore spectroscopic imaging data sets giving minor compounds and traces a chance to express themselves, Qicheng Wu, César Marina-Montes, Jorge O. Caceres, Jesus Anzano, Vincent Motto-Ros, Ludovic Duponchel, Spectrochimica Acta Part B: Atomic Spectroscopy 195 (2022) 106508
2. Measurement error due to self-absorption in calibration-free laser-induced breakdown spectroscopy, Aya Taleb, Vincent Motto-Ros, Mauro Carru, Emanuel Axente, Valentin Craciun, Frédéric Pelascini, Jörg Hermann, Analytica Chimica Acta, 2021, 1185, pp.339070
3. Artificial Neural Network for high-throughput spectral data processing in LIBS imaging: application to archaeological mortar, N. Herreyrea, A. Cormier, S. Hermelin, C. Oberlin, A. Schmitt, V. Thirion-Merle, A. Borlenghi, D. Prigent, C. Coquidé, A. Valois, C. Dujardin, P. Dugourd, L. Duponchel, C. Comby-Zerbino, and V. Motto-Ros, Submitted to JAAS (Nov 2022)
4. Short-Pulse Lasers: A Versatile Tool in Creating Novel Nano-/Micro-Structures and Compositional Analysis for Healthcare and Wellbeing Challenges, Ahmed Al-Kattan , David Grojo , Christophe Drouet, Alexandros Mouskeftaras , Philippe Delaporte, Adrien Casanova, Jérôme D. Robin, Frédérique Magdinier, Patricia Alloncle, Catalin Constantinescu, Vincent Motto-Ros and Jörg Hermann, Nanomaterials 2021, 11, 712. doi.org/10.3390/nano11030712
5. Recent advances and future perspectives in Laser induced breakdown spectroscopy imaging for material and biomedical applications, V. Gardette, V. Motto-Ros, C. Alvares, L. Sancey, L. Duponchel, and B. Busser, Accepted Analytical Chemistry Dec 2022

Books:

1. LIBS Imaging Applications (Chapter) V. Motto-Ros, S. Moncayo, C. Fabre, and B. Busser, pages 329-346, Laser Induced Breakdown Spectroscopy, 2nd Edition (Editors Jagdish P. Singh & Surya N. Thakur) Publisher Elsevier Science, 2020, 620 p. ISBN: 978-0-12-818829-3
2. Optical Spectroscopy for Cancer Diagnostics, World scientific publishing company. Chapter 13 Laser Induced Breakdown Imaging of Biomedical Samples: A Short Review and Perspectives, Vincent Motto-Ros, Lucie Sancey, Vincent Bonneterre and Benoit Busser
3. Laser-Induced Breakdown Spectroscopy in Biological, Forensic and Materials Sciences 1st ed. 2022 Edition by Gábor Galbács (Editor). LIBS imaging for Preclinical Applications. Vincent Motto-Ros, Lucie Sancey, Vincent Bonneterre and Benoit Busser

The overall goal of the DIAg-EM project is to use laser-induced breakdown spectroscopy (LIBS) elemental-microscopy with artificial intelligence processing to identify, localize and quantify pathogen elements present in selected human lung biopsies. We are proposing to develop a deep learning method able to perform, in real time, a non-supervised elemental identification, and to generate quantitative results over large areas of complex human specimens. A prospective clinical study will be initiated to collect samples from different hospitals in France, and from patients with various type of lung pathologies, caused by occupational exposures to inhaled mineral particles, metals, and dust. We expect to bring major inputs in the daily diagnoses of lung occupational and environmental diseases, and to produce useful data about past- or present exposure to agents that would help clinicians to better understand the disease of a given patient, therefore reinforcing his clinical management.