New Web page

 

My new web page is here :

https://sites.google.com/view/jehanbesson-research/home

Scientific talk, FIL (Fédération Informatique de Lyon) January 2023

I presented my research activities on 19 January 2023 to the members of the FIL federation.

https://fil.cnrs.fr/event/fil-seminar-january-19/

You can find the pdf of the presentation below :

Presentation FIL, January 2019

Scientific workshop on reproducibility, 8 december 2022, Lyon

The LABEX Primes organized a scientific day around the notion of reproducibility the 8 december of 2022.

I had the pleasure to give a talk on "Shape metrics for the evaluation of variability in deep learning segmentation methods for medical imaging" in collaboration with P. Clarysse , H. J. Ling, O. Bernard, T. Grenier and M. Sdika.

Please find the pdf of the talk below :

LABEX Presentation 8 december 2022

Session on "Geometric features extraction in medical imaging" at the conference GSI 2023

Page updated on January 12th

We are organizing a session on "Geometric features extraction in medical imaging" at the GSI (Geometric Science of Information) conference 2023. 

We would like to focus on papers that involve geometric features extraction in medical imaging using physical or geometric properties of the images or the associated signals. We also focus on papers that explain how to analyse and compare these geometric features using appropriate metrics. 

The goal is to encourage links at the frontier between medical imaging and fundamentals mathematics related to geometric science of information. 

Invited authors who wish to have their paper published in the Springer LNCS associated with the conference should follow the submission process of the conference website and pay attention to the fact that they must submit original work that has not been published before. Springer has strict ethics concerning both the novelty and review process.

**********

If you are interested by the session, please contact us:

Stéphanie Jehan-Besson (CR CNRS, CREATIS)

contact : stephanie.jehan-besson@cnrs.fr  

stephanie.jehan-besson@creatis.insa-lyon.fr

or 

Patrick Clarysse (DR CNRS, CREATIS)

patrick.clarysse@creatis.insa-lyon.fr

You are also welcome to submit your paper directly via the website and choose your preferred session. In this case we can not guarantee that the submitted paper will belong to our session. 

*********

Conference GSI “Geometric Science of Information”, GSI’23
from August 30th to September 1st 2023
location : Saint-Malo in France

conference chairs : Frédéric Barbaresco and Frank Nielsen

https://gsi2023.org/

    Deadline for 8 pages SPRINGER LNCS format: February 20th, 2023
    Notification of acceptance: April 21st, 2023
    Final paper submission: May 12th, 2023

The call for papers is available here : CallForPapers_GSI2023.pdf

********

The overall objective of this conference is to bring together pure/applied mathematicians and engineers, with common interest for Geometric tools and their applications for Information analysis and Learning. It emphasizes an active participation of young researchers to discuss emerging areas of collaborative research on “Geometric Science of Information and their Applications". 

The conference presents a panorama of Geometric Tools emphasizing mathematical theory, physical model, computational methods, and applications in mathematics, physics, statistics, engineering, signal/image processing, machine learning and data science. This conference will be an interdisciplinary event and will unify skills from Geometry, Probability and Information Theory.

Conference Curves and Surfaces 2022

We had the great pleasure to attend the Conference Curves and Surfaces 2022 in Arcachon France, a conference that takes place every 4 years.

Here is the link to the conference :

https://cs2022.sciencesconf.org/

We presented our work on the "Optimization of a mutual shape based on the Fréchet-Nikodym metric for 3D shapes fusion"

The poster is given here below (click on the image to open the pdf)

CREATIS, Medical Imaging Research Laboratory

Since January 2022, I joined the laboratory CREATIS UMR CNRS 5220 as a permanent CNRS researcher. This laboratory is specialized in medical imaging. 

I will continue my current work on mutual shapes for segmentation fusion and evaluation while also participating in new projects in the field of medical imaging.

I belong to the MYRIAD team whose presentation is given via the link below:

 https://creatis-myriad.github.io/

and to the Labex PRIMES whose presentation is given via the following link :

https://primes.universite-lyon.fr/

 

Paper and presentation for GSI 2021

Our conference paper is available using the link below:

Springer conference paper web page

The associated presentation is available using the link below  :

Presentation PDF

Conference GSI 5th conference on Geometric Science of Information

 The final program and schedule for the conference GSI 5th Conference on Geometric Science of Information is now available. The Conference takes place in Paris, Sorbonne University in July.

I will chair the session "Manifolds and optimization" with Bin Gao (UCLouvain)

Don't miss the talks of the Keynote Speakers :

• Yvette Kosmann-Schwarzbach on Structures of Poisson Geometry: old and new
• Max Welling on Exploring Quantum Statistics for Machine Learning
• Michel Broniatowski on Some insights on statistical divergences and choice of models
• Maurice de Gosson on Gaussian states from a symplectic geometry point of view
• Jean Petitot on The primary visual cortex as a Cartan engine
• Giuseppe Longo on Use and abuse of "digital information" in life sciences, is Geometry of Information a way out?

Abstracts of GSI'21 keynote speakers are available here:
https://www.see.asso.fr/en/wiki/367468_keynote-speakers
Information on GSI'21 registration:
https://www.see.asso.fr/en/wiki/367782_registration

Conference GSI 2021

 Our paper 

Optimization of a shape metric based on information theory applied to segmentation fusion and evaluation in multimodal MRI for DIPG tumor analysis, Stéphanie Jehan-Besson (CNRS, LITO U1288 INSERM, Institut Curie), Régis Clouard (Normandie Univ, ENSICAEN), Nathalie Boddaert (Hôpital Necker Enfants Malades, AP-HP Imagine), Jacques Grill (Gustave Roussy, Inserm), Frédérique Frouin (LITO U1288 INSERM, Institut Curie).

has been accepted to the 5th conference on Geometric Science of Information in PARIS, Sorbonne University GSI 2021. As for previous editions, GSI’21 Proceedings will be published in SPRINGER LNCS. See GSI’19 Proceedings.

It takes place in the project BIOMEDE : https://www.lito-web.fr/en/projects/94-biomede-ia-2

Presentation, LITO, Institut Curie

I will present my research work the 7th april 2021 on the topic of segmentation and evaluation/fusion of ROIs in multimodal MRI. This work takes place within the BIOMEDE project (collaboration Hôpital Necker des enfants malades, Institut Gustave Roussy).

Article

 Our conference paper has been submitted (lecture notes in computer sciences)

Project BIOMEDE

Since january 2021, I am mainly involved in the BIOMEDE project.

This project aims at better characterizing, by using machine learning or deep learning methods, the tumors of patients with diffuse intrinsic pontine gliomas (DIPG) which is a rare pediatric cancer with a very poor prognosis. The analysis is based on clinical and imaging (multi-parametric MRI) features. 

https://www.lito-web.fr/en/projects/94-biomede-ia-2

Preprint ArXiv

Our preprint is now available on ArXiv

https://arxiv.org/abs/2102.08939

A Mutual Reference Shape for Segmentation Fusion and Evaluation

Abstract : This paper proposes the estimation of a mutual shape from a set of different segmentation results using both active contours and information theory. The mutual shape is here defined as a consensus shape estimated from a set of different segmentations of the same object. In an original manner, such a shape is defined as the minimum of a criterion that benefits from both the mutual information and the joint entropy of the input segmentations. This energy criterion is justified using similarities between information theory quantities and area measures, and presented in a continuous variational framework. In order to solve this shape optimization problem, shape derivatives are computed for each term of the criterion and interpreted as an evolution equation of an active contour. A mutual shape is then estimated together with the sensitivity and specificity of each segmentation. Some synthetic examples allow us to cast the light on the difference between the mutual shape and an average shape. The applicability of our framework has also been tested for segmentation evaluation and fusion of different types of real images (natural color images, old manuscripts, medical images).      

Welcome

 

Welcome on my research page under construction 

Link towards the news of the Laboratory LITO U1288, INSERM, Institut Curie :

https://www.lito-web.fr/fr/actualites