Project

Back to overview

Regularized Linear Inverse Problems in Diffusion Magnetic Resonance and Ultrasound Imaging

English title Regularized Linear Inverse Problems in Diffusion Magnetic Resonance and Ultrasound Imaging
Applicant Thiran Jean-Philippe
Number 175974
Funding scheme Project funding
Research institution Laboratoire de traitement des signaux 5 EPFL - STI - IEL - LTS5
Institution of higher education EPF Lausanne - EPFL
Main discipline Information Technology
Start/End 01.11.2017 - 31.10.2021
Approved amount 750'000.00
Show all

Keywords (6)

ultrasound imaging; inverse problems; diffusion MRI; medical imaging; brain connectivity analysis; deep networks

Lay Summary (French)

Lead
L’imagerie médicale occupe une place de choix dans le diagnostic médical, et cette place est appelée à croitre avec l’évolution annoncée de la médecine personnalisée. Dans ce contexte, l’acquisition, la reconstruction et l’analyse des images sont des composantes essentielles de cette évolution.Dans ce projet, nous proposons de développer le cadre général des problèmes inverses linéaires régularisés pour la reconstruction des images médicales, et nous en développerons les composants principaux, dans le contexte de deux modalités d’imagerie majeures : l’imagerie IRM de diffusion et l’imagerie ultrason.
Lay summary

IRM de diffusion : depuis près de 15 ans, le LTS5 de l’EPFL se positionne à l’avant-garde de l’analyse de la connectivité cérébrale par IRM de diffusion. Récemment, nous avons proposé une série de contributions méthodologiques importantes permettant l’estimation robuste de la microstructure de la substance blanche. Dans ce projet, nous continuerons cet effort afin d’obtenir des estimations optimales et validées.

Imagerie ultrason : récemment, le LTS5 a proposé de considérer la reconstruction d’images échographiques comme un problème inverse linéaire. Dans ce projet, nous allons continuer et étendre ces travaux à l’imagerie 3D et nous allons également aborder la question de la complexité computationnelle de ces reconstructions au travers d’approches très originale reposant sur des réseaux de neurones profonds.

A la fin de ce projet, nous aurons donc développé les méthodologies essentielles pour reconstruire efficacement les informations issues de ces deux modalités majeures d’imagerie médicale. Par là, nous contribuerons à l’amélioration des dispositifs d’imagerie médicale, répondant ainsi aux besoins de la communauté de recherche biomédicale.

Direct link to Lay Summary Last update: 29.09.2017

Responsible applicant and co-applicants

Employees

Project partner

Publications

Publication
The diffusion-simulated connectivity (DiSCo) dataset
Rafael-Patino Jonathan, Girard Gabriel, Truffet Raphaël, Pizzolato Marco, Caruyer Emmanuel, Thiran Jean-Philippe (2021), The diffusion-simulated connectivity (DiSCo) dataset, in Data in Brief, 38, 107429-107429.
Computational Diffusion MRI12th International Workshop, CDMRI 2021, Held in Conjunction with MICCAI 2021, Strasbourg, France, October 1, 2021, Proceedings
Rafael-Patino Jonathan, Girard Gabriel, Truffet Raphaël, Pizzolato Marco, Thiran Jean-Philippe, Caruyer Emmanuel (2021), Computational Diffusion MRI12th International Workshop, CDMRI 2021, Held in Conjunction with MICCAI 2021, Strasbourg, France, October 1, 2021, Proceedings, in International Workshop on Computational Diffusion MRI, Springer International Publishing, Cham.
Directional Cross-Correlation for Improved Aberration Phase Estimation in Pulse-Echo Speed-of-Sound Imaging
Beuret Samuel, Heriard-Dubreuil Baptiste, Canales Simon, Thiran Jean-Philippe (2021), Directional Cross-Correlation for Improved Aberration Phase Estimation in Pulse-Echo Speed-of-Sound Imaging, in 2021 IEEE International Ultrasonics Symposium (IUS), Xi'an, ChinaIEEE, Piscataway.
Bundle-Specific Axon Diameter Index as a New Contrast to Differentiate White Matter Tracts
Barakovic Muhamed, Girard Gabriel, Schiavi Simona, Romascano David, Descoteaux Maxime, Granziera Cristina, Jones Derek K., Innocenti Giorgio M., Thiran Jean-Philippe, Daducci Alessandro (2021), Bundle-Specific Axon Diameter Index as a New Contrast to Differentiate White Matter Tracts, in Frontiers in Neuroscience, 15, 646034.
CNN-Based Ultrasound Image Reconstruction for Ultrafast Displacement Tracking
Perdios Dimitris, Vonlanthen Manuel, Martinez Florian, Arditi Marcel, Thiran Jean-Philippe (2021), CNN-Based Ultrasound Image Reconstruction for Ultrafast Displacement Tracking, in IEEE Transactions on Medical Imaging, 40(3), 1078-1089.
Comparison of diffusion MRI and CLARITY fiber orientation estimates in both gray and white matter regions of human and primate brain
Leuze C., Goubran M., Barakovic M., Aswendt M., Tian Q., Hsueh B., Crow A., Weber E.M.M., Steinberg G.K., Zeineh M., Plowey E.D., Daducci A., Innocenti G., Thiran J-P, Deisseroth K., McNab J.A. (2021), Comparison of diffusion MRI and CLARITY fiber orientation estimates in both gray and white matter regions of human and primate brain, in NeuroImage, 228, 117692-117692.
Resolving bundle-specific intra-axonal T2 values within a voxel using diffusion-relaxation tract-based estimation
Barakovic Muhamed, Tax Chantal M.W., Rudrapatna Umesh, Chamberland Maxime, Rafael-Patino Jonathan, Granziera Cristina, Thiran Jean-Philippe, Daducci Alessandro, Canales-Rodríguez Erick J., Jones Derek K. (2021), Resolving bundle-specific intra-axonal T2 values within a voxel using diffusion-relaxation tract-based estimation, in NeuroImage, 227, 117617-117617.
CNN-Based Image Reconstruction Method for Ultrafast Ultrasound Imaging
Perdios Dimitris, Vonlanthen Manuel, Martinez Florian, Arditi Marcel, Thiran Jean-Philippe (2021), CNN-Based Image Reconstruction Method for Ultrafast Ultrasound Imaging, in IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control, 1-1.
Refraction-Aware Integral Operator for Speed-of-Sound Pulse-Echo Imaging
Beuret Samuel, Perdios Dimitris, Thiran Jean-Philippe (2020), Refraction-Aware Integral Operator for Speed-of-Sound Pulse-Echo Imaging, in 2020 IEEE International Ultrasonics Symposium (IUS), Las Vegas, NV, USAIEEE, Piscataway.
Robust Monte-Carlo Simulations in Diffusion-MRI: Effect of the Substrate Complexity and Parameter Choice on the Reproducibility of Results
Rafael-Patino Jonathan, Romascano David, Ramirez-Manzanares Alonso, Canales-Rodríguez Erick Jorge, Girard Gabriel, Thiran Jean-Philippe (2020), Robust Monte-Carlo Simulations in Diffusion-MRI: Effect of the Substrate Complexity and Parameter Choice on the Reproducibility of Results, in Frontiers in Neuroinformatics, 14, 8.
A new method for accurate in vivo mapping of human brain connections using microstructural and anatomical information
Schiavi Simona, Ocampo-Pineda Mario, Barakovic Muhamed, Petit Laurent, Descoteaux Maxime, Thiran Jean-Philippe, Daducci Alessandro (2020), A new method for accurate in vivo mapping of human brain connections using microstructural and anatomical information, in Science advances, 6(31), 8245-8245.
ActiveAxADD: Toward non‐parametric and orientationally invariant axon diameter distribution mapping using PGSE
Romascano David, Barakovic Muhamed, Rafael‐Patino Jonathan, Dyrby Tim Bjørn, Thiran Jean‐Philippe, Daducci Alessandro (2020), ActiveAxADD: Toward non‐parametric and orientationally invariant axon diameter distribution mapping using PGSE, in Magnetic Resonance in Medicine, 83(6), 2322-2330.
Axon morphology is modulated by the local environment and impacts the noninvasive investigation of its structure{\textendash}function relationship
Andersson Mariam, Kjer Hans Martin, Rafael-Patino Jonathan, Pacureanu Alexandra, Pakkenberg Bente, Thiran Jean-Philippe, Ptito Maurice, Bech Martin, Bjorholm Dahl Anders, Andersen Dahl Vedrana, Dyrby Tim B. (2020), Axon morphology is modulated by the local environment and impacts the noninvasive investigation of its structure{\textendash}function relationship, in Proceedings of the National Academy of Sciences, 117(52), 33649-33659.
Single-Shot CNN-Based Ultrasound Imaging with Sparse Linear Arrays
Perdios Dimitris, Vonlanthen Manuel, Martinez Florian, Arditi Marcel, Thiran Jean-Philippe (2020), Single-Shot CNN-Based Ultrasound Imaging with Sparse Linear Arrays, in 2020 IEEE International Ultrasonics Symposium (IUS), 1-4, IEEE, Piscataway1-4.
Deep Learning Based Ultrasound Image Reconstruction Method: A Time Coherence Study
Perdios Dimitris, Vonlanthen Manuel, Martinez Florian, Arditi Marcel, Thiran Jean-Philippe (2019), Deep Learning Based Ultrasound Image Reconstruction Method: A Time Coherence Study, in 2019 IEEE International Ultrasonics Symposium (IUS), Glasgow, United KingdomIEEE, Piscataway.
A Physical Model of Nonstationary Blur in Ultrasound Imaging
Besson Adrien, Roquette Lucien, Perdios Dimitris, Simeoni Matthieu, Arditi Marcel, Hurley Paul, Wiaux Yves, Thiran Jean-Philippe (2019), A Physical Model of Nonstationary Blur in Ultrasound Imaging, in IEEE Transactions on Computational Imaging, 5(3), 381-394.
Learning Global Brain Microstructure Maps Using Trainable Sparse Encoders
Rafael-Patino J., Barakovic M., Girard G., Daducci A., Thiran J.-P. (2019), Learning Global Brain Microstructure Maps Using Trainable Sparse Encoders, in 2019 IEEE International Conference on Image Processing (ICIP), Taipei, TaiwanIEEE, Piscataway.
Information Processing in Medical Imaging26th International Conference, IPMI 2019, Hong Kong, China, June 2–7, 2019, Proceedings
Yu Thomas, Pizzolato Marco, Girard Gabriel, Rafael-Patino Jonathan, Canales-Rodríguez Erick Jorge, Thiran Jean-Philippe (2019), Information Processing in Medical Imaging26th International Conference, IPMI 2019, Hong Kong, China, June 2–7, 2019, Proceedings, in Proc. MICCAI 2019, Springer International Publishing, Cham.
Comparing Fiber Orientation Estimates from CLARITY and Diffusion MRI in Macaque Visual Cortex
Barakovic Muhamed, Leuze Christoph, Crow Ailey, Tian Qiyuan, Daducci Alessandro, Thiran Jean-Philippe, Deisseroth Karl, McNab Jennifer (2019), Comparing Fiber Orientation Estimates from CLARITY and Diffusion MRI in Macaque Visual Cortex, in ISMRM 27th Annual Meeting, Montréal, Canada, (CONF), ISMRM, Montreal(CONF).
HOTmix: characterizing hindered diffusion using a mixture of generalized higher order tensors
Romascano David, Canales-Rodriguez Erick Jorge, Patin Lopez Jonathan Rafael, Pizzolato Marco, Rensonnet Gaëtan, Barakovic Muhamed, Girard Gabriel, Daducci Alessandro, Dyrby Tim B, Thiran Jean-Philippe (2019), HOTmix: characterizing hindered diffusion using a mixture of generalized higher order tensors, in ISMRM 27th Annual Meeting & Exhibition, Montréal, Canada(POST_TALK), iSMRM, Montreal(POST_TALK).
Joint Sparsity With Partially Known Support and Application to Ultrasound Imaging
Besson Adrien, Perdios Dimitris, Wiaux Yves, Thiran Jean-Philippe (2019), Joint Sparsity With Partially Known Support and Application to Ultrasound Imaging, in IEEE Signal Processing Letters, 26(1), 84-88.
Uncovering 3D Axonal Morphologies with Synchrotron Imaging: Impact on Microstructure Imaging with Diffusion MRI
Andersson Mariam, Kjer Hans Martin, Rafael-Patino Jonathan, Dahl Vedrana Andersen, Pacureanu Alexandra, Thiran Jean-Philippe, Bech Martin, Dahl Anders Bjorholm, Dyrby Tim B (2019), Uncovering 3D Axonal Morphologies with Synchrotron Imaging: Impact on Microstructure Imaging with Diffusion MRI, in ISMRM 27th Annual Meeting & Exhibition, ISMRM, Monréal.
Compressive Multiplexing of Ultrasound Signals
Besson Adrien, Perdios Dimitris, Arditi Marcel, Wiaux Yves, Thiran Jean-Philippe (2018), Compressive Multiplexing of Ultrasound Signals, in 2018 IEEE International Ultrasonics Symposium (IUS), Kobeieee, Piscataway.
Deep Convolutional Neural Network for Ultrasound Image Enhancement
Perdios Dimitris, Vonlanthen Manuel, Besson Adrien, Martinez Florian, Arditi Marcel, Thiran Jean-Philippe (2018), Deep Convolutional Neural Network for Ultrasound Image Enhancement, in 2018 IEEE International Ultrasonics Symposium (IUS), KobeIEEE, Piscataway.
Pulse-Stream Models in Time-of-Flight Imaging
Besson Adrien, Perdios Dimitris, Wiaux Yves, Thiran Jean-Philippe (2018), Pulse-Stream Models in Time-of-Flight Imaging, in ICASSP 2018 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, ABIEEE, Piscataway.
Assessing feasibility and reproducibility of a bundle-specific framework on in vivo axon diameter estimates at 300mT/m
Barakovic Muhamed, Girard Gabriel, Romascano David Paul Roger, Patin Lopez Jonathan Rafael, Descoteaux Maxime, Innocenti Giorgio, Jones Derek K, Thiran Jean-Philippe, Daducci Alessandro (2018), Assessing feasibility and reproducibility of a bundle-specific framework on in vivo axon diameter estimates at 300mT/m, in 26th annual meeting of the International Society for Magnetic Resonance in Medicine (ISMRM), Paris(CONF), International Society for Magnetic Resonance in Medicine (ISMRM), Paris(CONF).
Estimation of the brain microstructure in the presence of crossing fascicles from a dictionary of Monte Carlo signals
Rensonnet Gaëtan Olivier D, Scherrer Benoit, Girard Gabriel, Patin Lopez Jonathan Rafael, Warfield Simon K, Macq Benoit, Thiran Jean-Philippe, Taquet Maxime (2018), Estimation of the brain microstructure in the presence of crossing fascicles from a dictionary of Monte Carlo signals, in 26th annual meeting of the International Society for Magnetic Resonance in Medicine (ISMRM), (CONF), International Society for Magnetic Resonance in Medicine (ISMRM), Paris(CONF).
Non-parametric axon diameter distribution mapping with PGSE: reconstruction of uni-and multimodal distributions
Romascano David Paul Roger, Patin Lopez Jonathan Rafael, Barakovic Muhamed, Daducci Alessandro, Thiran Jean-Philippe, Dyrby Tim B (2018), Non-parametric axon diameter distribution mapping with PGSE: reconstruction of uni-and multimodal distributions, in 26th annual meeting of the International Society for Magnetic Resonance in Medicine (ISMRM), (CONF), International Society for Magnetic Resonance in Medicine (ISMRM), Paris, France(CONF).
Realistic 3D Fiber Crossing Phantom Models for Monte Carlo Diffusion Simulations
Patin Lopez Jonathan Rafael, Girard Gabriel, Romascano David Paul Roger, Barakovic Muhamed, Rensonnet Gaëtan Olivier D, Thiran Jean-Philippe, Daducci Alessandro (2018), Realistic 3D Fiber Crossing Phantom Models for Monte Carlo Diffusion Simulations, in 26th Annual meeting of the International Society for Magnetic Resonance in Medicine, (CONF), International Society for Magnetic Resonance in Medicine, Paris, France(CONF).
Reducing false positives in tractography with microstructural and anatomical priors
Daducci Alessandro, Barakovic Muhamed, Girard Gabriel, Descoteaux Maxime, Thiran Jean-Philippe (2018), Reducing false positives in tractography with microstructural and anatomical priors, in Joint Annual Meeting ISMRM-ESMRMB, (CONF), ISMRM, Paris(CONF).
Sparse Recovery of Strong Reflectors with an Application to Non-Destructive Evaluation
Bezzam E., Besson A., Pan H., Perdios D., Thiran J., Vetterli M. (2018), Sparse Recovery of Strong Reflectors with an Application to Non-Destructive Evaluation, in 2018 IEEE International Ultrasonics Symposium (IUS), 1-4, IEEE, Piscataway1-4.
Voxel size matters: big voxels are required to generate realistic extra-axonal DMRI signals from monte carlo simulations
Romascano David, Rafael-Patino Jonathan, Jelescu Ileana, Barakovic Muhamed, Dyrby Tim B, Thiran Jean-Philippe, Daducci Alessandro (2018), Voxel size matters: big voxels are required to generate realistic extra-axonal DMRI signals from monte carlo simulations, in Joint Annual Meeting ISMRM-ESMRMB 2018, ISMRM, Paris.

Associated projects

Number Title Start Funding scheme
157063 Towards micro-structure-based tractography for quantitative brain connectivity analysis 01.10.2014 Project funding
138311 Advanced signal processing on the sphere for high angular resolution diffusion magnetic resonance imaging 01.04.2012 Project funding
170758 High-End 3D Ultrasound Open Research Platform 01.12.2016 R'EQUIP
207486 Deep learning-based Ultrafast Ultrasound Image Reconstruction: simulations, transfer learning and sparse arrays 01.04.2022 Project funding
204097 Diffusion Magnetic Resonance Microstructure Imaging by Tissue Modeling and Simulation 01.12.2021 Project funding
170873 Exploring brain communication pathways by combining diffusion based quantitative structural connectivity and EEG source imaging : application to physiological and epileptic networks 01.03.2017 Sinergia

Abstract

Medical imaging occupies a place of choice in medical diagnosis, and this place will keep growing in the future the development of new imaging modalities and with the increasing need for personalized medicine. In this context, medical image acquisition, reconstruction and analysis are key technical components, subject to intense research all over the World, to provide the medical community with the most advanced and robust methods to extract information from the fantastic existing and future image modalities.In this project, we will promote the framework of regularized linear inverse problems in medical image acquisition and reconstruction, and develop some of its essential components, in the context of two very attractive medical imaging modalities: diffusion Magnetic Resonance Imaging (dMRI) and Ultrasound (US) imaging. This project is built as a continuation and extension of two important research lines pursued at the Signal Processing Laboratory (LTS5) of EPFL, and addresses key questions in these domains in a unified methodological framework. Indeed, in our previous works both in brain connectivity analysis by dMRI and in US image reconstruction, we proposed to formulate the data/image reconstruction aspects as regularized linear inverse problems and obtained significant preliminary results.Diffusion MRI: For the last 15 years, LTS5 has pioneered the field of brain connectivity analysis by dMRI, establishing the principle of MR connectomics. Recently, we developed an additional major contribution to the field, by reformulating the dMRI white matter microstructure estimation problems into linear inverse problems, for both microstructure imaging and microstructure informed tractography. In this project, we will continue this effort by investigating some of the key issues to obtain optimal estimation, namely dictionary design and learning as well as validation. Ultrasound imaging: Although now a mature field, medical US remains a modality supported by intense research and with extensive diagnostic and therapeutic indications in routine clinical use worldwide. Even if the research is very active, the basic component of US imaging, i.e. the beamforming method called Delay-and-Sum (DAS), has been largely untouched for several decades. While being very effective thanks to its simplicity, this method is largely suboptimal. Recently, LTS5 has developed the idea of addressing US image reconstruction as a linear inverse problem. Preliminary results already demonstrate outstanding performances in 2D imaging, both in image quality and data reduction. In this project, we will continue this effort by addressing some of the key aspects of this new paradigm, that will be required for this innovative method to become effective and have the expected impact. We will first extend it to 3D US imaging, where our framework has the potential to have the strongest impact, by enabling a high image quality while drastically reducing the data requirement and therefore making this technology appropriate for a much larger diffusion in the medical community. Secondly, we will address the computational complexity of US image reconstruction through regularized inverse problems by exploring and developing the remarkably promising idea of exploiting deep neural networks for image reconstruction.At the end of this project, we will thus have developed a series of new medical image acquisition and reconstruction methods, that will allow an optimal exploitation of these two amazing technologies: dMRI and US imaging. Finally, by improving medical imaging technologies, we will play our role of engineers, and contribute to the development of enhanced medical imaging devices, serving the need of the biomedical community, to ultimately provide new tools and methods for better understanding the human body and improved treatments for patients.
-