RESEARCH


On going Research Project : 

Project SHAMI (SHApe Mutual Information)
Shape metrics for evaluation and fusion of segmentation methods in medical imaging

Summary of the project : In the field of delineation of 2D or 3D regions of interest (ROI) in medical imaging, and especially due to the development of multimodal and multiparametric image acquisition devices, the combination of segmentations of anatomical structures from different sources is of interest. It is also essential to accurately evaluate the variability between experts delineation or algorithms with different parameters. Finally, it seems important to be able to merge heterogeneous information from different modalities and acquisition methods in order to synthesize them. In this project, our aim is to propose the estimation of a reference shape defined as the optimum of a continuous criterion or using deep learning approaches. We want to compare different metrics for segmentation evaluation and fusion and to compare these metrics to the well-known STAPLE approach. This work will also help us to evaluate the variability of deep learning methods and to combine segmentation results for more reproducibility.

keywords : Evaluation of fusion of segmentation methods using shape metrics, 2D and 3D Shape Analysis, Mean Shape, Mutual Shape, Mutual Information, shape gradients

Publications 

ArXiv 2021 "Mutual Reference Shape for Segmentation Fusion and Evaluation", S. Jehan-Besson, R. Clouard, C. Tilmant, A. de Cesare, A. Lalande, J. Lebenberg, P. Clarysse, L. Sarry, F. Frouin, M. Garreau,  arXiv:2102.08939février 2021

CS2022 "Optimization of a mutual shape based on the Fréchet-Nikodym metric for 3D shapes fusion". S.Jehan-Besson, P. Clarysse, R. Clouard, F. Frouin.  International Conference on Curves and Surfaces, Jun 2022, Arcachon, France. ⟨hal-03697975⟩

GSI2021 "Optimization of a shape metric based on information theory applied to segmentation fusion and evaluation in multimodal MRI for DIPG tumor analysis", S. Jehan-Besson, R. Clouard, N. Boddaert, J. Grill, F. Frouin, book chapter in LNCS, 5th International Conference on Geometric Science of Information GSI 2021, July Paris

link towards the pdf of the presentation


Recent Presentations

FIL (Fédération Informatique Lyon) january 2023, "Optimization of a shape metric based on information theory for segmentation evaluation and fusion in 2D or 3D medical image analysis", seminar for new researchers in Lyon, 19 January 2023

links towards the pdf of the presentation


LABEX PRIMES december 2022, "Shape metrics for the evaluation of variability in deep learning segmentation methods for medical imaging", 8 december 2022.

 links towards the pdf of the presentation.


Software

We recruited an internship in 2023 followed by an engineering contract financed by the LABEX Primes (September 2023 to January 2024) and then financed by the CREATIS laboratory (January to April 2024) in order to provide a module for the estimaton of mutual shapes in 2D, 3D and multi-labels, compatible with the ITK library which is widely used for medical imaging. Soon available on request.


Summary of past research activities

CNRS researcher in image and video processing, my research interests concern the design and the optimization of statistical continuous criteria designed for various applications (segmentation of medical structures in 2D or 3D images, motion estimation and tracking in video sequences, filtering using total variation, evaluation of segmentation methods without gold standard, fusion of ROIs for multimodal segmentation). These methods are based on the introduction of rigorous mathematical models to characterize the problem (parametric or non parametric pdfs, optimization of divergences, shape metrics based on information theory, total variation) and on the implementation of optimization approaches which are well-adapted to each problem (e.g. shape optimization, dual approaches, convex optimization). Since my integration in the MYRIAD team of the CREATIS laboratory, I am progressively involved in deep learning approaches for medical image analysis. 

Main research interests

  • Design of 2D or 3D deformable models using shape gradients based on shape optimization theory using parametric and non parametric statistical criteria
  • Segmentation fusion and evaluation without gold standard using a criterion based on information theory
  • 2D or 3D segmentation, evaluation, fusion, motion estimation or segmentation using continuous optimization methods
  • Color image filtering based on total variation and dual approaches
  • Statistical inequalities for region matching.
  • Applications : Medical Image Analysis (echocardiography, cardiac MRI, multimodal brain MRI, perfusion cardiac MRI), Video image analysis, Color image filtering 

Scientific Links




Some presentations

GSI  07-21 "Optimization of a shape metric based on information theory applied to segmentation fusion and evaluation in multimodal MRI for DIPG tumor analysis", S. Jehan-Besson, R. Clouard, N. Boddaert, J. Grill, F. Frouin, book chapter in LNCS, 5th International Conference on Geometric Science of Information GSI 2021, July Paris, link towards the conference paper in Springer, Link towards the pdf of the presentation GSI

LITO Institut Curie 04-07 "Optimisation de critères statistiques pour la segmentation, l'évaluation ou la fusion de données, présentation de la méthodologie et étude des GITCs en IRM multimodale", S. Jehan-Besson, presentation within the LITO, 7 april 2021, Link towards the pdf of the presentation

GREYC 2017 "Approches variationnelles pour la segmentation, le filtrage et l'évaluation",  S. Jehan-Besson réunion, Overview of research activities, January 2017, Link towards the pdf of the presentation

GDR 06-13 "Approches variationnelles pour la segmentation : le point sur les critères à optimiser et les méthodes de résolution associées'', S. Jehan-Besson, invited speaker, Journées conjointes du GDR ISIS et du GDR Stic-Santé, Segmentation d'images médicales : approches variationnelles et statistiques, juin 2013, Link towards the pdf of presentation


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-1...