Powered by OpenAIRE graph
Found an issue? Give us feedback

IMAGERIE ADAPTATIVE DIAGNOSTIQUE ET INTERVENTIONNELLE - INSERM U947

Country: France

IMAGERIE ADAPTATIVE DIAGNOSTIQUE ET INTERVENTIONNELLE - INSERM U947

9 Projects, page 1 of 2
  • Funder: French National Research Agency (ANR) Project Code: ANR-23-CE19-0030
    Funder Contribution: 800,318 EUR

    INOCA (ischemia with non-obstructive coronary arteries) is a cardiovascular disease affecting primarily women, and its diagnosis is challenging. Coronarography is the reference examination, however it is invasive, ionizing, and costly. Stress cardiac magnetic resonance imaging (CMR) is a promising alternative, though the quality, comfort and robustness of the exam need to be improved. The goal of SWEETHEART is the development of a wearable electrocardiogram (ECG) mapping device designed to leverage the potential of stress CMR. The device will allow a robust cardiorespiratory monitoring during the whole examination. Several technological breakthroughs will be addressed: design of high-sensitivity, flexible biosensors; design of quantitative, motion-robust and contrast-free MRI methods; methodology demonstrating the MRI safety of wearable devices. The consortium comprises three academic teams with complementary expertise, in the design of electronic textiles (GEMTEX, Roubaix), in MR-compatible instrumentation and motion correction (IADI, Nancy), and in advanced CMR methods (LIRYC, Bordeaux), and two industrial partners. Epsidy (Nancy) develops MRI compatible instrumentation and associated tools for denoising and real-time analysis of signal, based on artificial intelligence. Healtis (Nancy) is an international expert in MRI safety (bench testing and simulation). The expected results will demonstrate the clinical feasibility of the developed technological tools, and the relevance of a non-invasive, non-ionizing screening technique for INOCA patients which can be used for further research on human beings.

    more_vert
  • Funder: French National Research Agency (ANR) Project Code: ANR-21-FAI1-0007
    Funder Contribution: 196,543 EUR

    Magnetic Resonance Imaging (MRI) is the recommended medical imaging modality for a wide range of cardiovascular pathologies, and the use of cardiac MRI in clinical practice is only going to be even more widespread given the pace of technology developments in the last years. Deep Learning (DL) and other types of so-called Intelligence Artificial (IA) techniques have recently hit the computer vision communities and has allowed reaching levels of performance on par with humans for several tasks (object classification, … ). These techniques have therefore naturally been translated to the medical imaging field with similar successes, although specific limitations are inherent to the medical fields (such as the relatively scarceness of annotated datasets). More recently, DL-based medical imaging reconstruction techniques have been proposed, as they could allow for a faster acquisition and reconstruction data, and therefore speedup MRI examination and lessen their costs on healthcare. The MEDICARE project aims at bringing the expertise of both partners, MRI reconstruction and physiological data analysis for the IADI lab and Medical Imaging analysis for the IMI, in order to develop a Motion Integrated AI-based cardiac MRI reconstruction technique allowing for whole heart cardiac imaging during free-breathing. Such a solution would open up a vast range of clinical applications (accelerated high resolution CINE images, accelerated acquisition of T1/T2 maps). Overcome certain limitations need to be overcome before transferring such AI-based solution into clinical practice, mostly based on the need to gain radiologists trust by building robust solutions (avoiding oversimplified regularization biased towards healthy tissues) and providing confidence maps along with reconstructed images to help radiologist taking a rational diagnosis decision. The overall goal of developing a Motion-Integrated AI-based cardiac reconstruction technique will be achieved through the following four sub-objectives: • Develop accelerated AI-based MRI reconstruction that incorporate uncertainty modelling into the analysis to enhance the trustworthiness of image quality • Advance MRI reconstruction of subtle abnormal anatomical details to avoid bias of healthy tissues in AI-models and improve clinical reliability • Develop and incorporate AI-based 4D motion prediction without full reconstruction for faster sparse k-space sampling for MRI acquisition • Enhance the explainability of AI methods for MR image processing by combining AI based feature extraction with robust graph-based optimization strategies

    more_vert
  • Funder: French National Research Agency (ANR) Project Code: ANR-17-CE19-0022
    Funder Contribution: 344,304 EUR

    Magnetic Resonance Imaging (MRI) is the technique of reference to replace ionizing X-ray mammography for screening of breast cancer for women at risk. However, conventional MR mammography has several drawbacks in terms of specificity due to low temporal resolution, patient comfort and adaptation to breast morphology. The objective of BRACOIL is to develop a clinically viable, new hard- and software package enabling a paradigm-shift in MR mammography. This objective will be reached by four breakthroughs in conception and technology of the breast MRI screening procedure: 1. We propose to perform the measurement in a face-up (supine) position to gain in patient comfort and to stay in the same position as during second stage diagnostics (i.e., biopsy, ultrasound). 2. Light-weight and shape-adapted breast coils will be designed to fit the patient just like a bra. In addition, owing to the better form-fitting of these coils as compared to the state-of-the art “one-size-fits-all” breast coils, the sensitivity of the measurement will be strongly improved. 3. The expected additional motion artefacts arising from the supine positioning due to breathing will be corrected for by employing sophisticated motion management techniques based on sensors for motion and impedance monitoring, combined with mathematical correction algorithms. 4. With the gained sensitivity from breakthroughs 2 and 3, the way is paved for more advanced MR imaging techniques that provide more specific contrasts like diffusion or arterial spin labelling. Within this project we will investigate another imaging modality based on impedance measurements with all radio frequency coil elements, called impedance tomography, which can be used as an additional imaging contrast in parallel to the MRI acquisition. With the availability of such multi-contrast imaging techniques, we might enable completely non-invasive breast screening exams by rendering the use of contrast agents unnecessary. To achieve breakthrough 1, mechanically adjustable breast holders in three different cup sizes will be developed using 3D scanning and 3D printing technologies. For breakthrough 2, new radiofrequency coil array concepts based on transmission line resonators will be employed. These sensitive and extremely light-weight coil elements will be built in housings that perfectly fit the shape of the breast holders, increasing the MRI signal-to-noise ratio. Breakthrough 3 will be achieved by integrating a localization system (with motion and impedance sensors, and markers) in the novel device to correct for motion of the patient, leading to a strong improvement in diagnostic value of the acquired images. For breakthrough 4, another innovative contrast mechanism is introduced. We will use the scattering parameter data of the coil array elements to obtain an “impedance tomography” image by mathematically solving an inverse problem. The final phase of the project is dedicated to an in-vivo validation study of the developed setup in healthy volunteers, investigating both the technical performance (in Vienna) and the clinical usability performance (in Nancy). The consortium includes expert partners in the field of breast MRI and motion management (Nancy, France), light-weight and flexible transmission line radio frequency coil elements (Paris, France), and coil array design development and medical product certification (Vienna, Austria). The consortium is accompanied by outstanding medical experts in breast screening. The project outcome will be valorized by patents and commercialization of the developed technology package together with industrial partners, as has already been successfully demonstrated for other innovative coil technologies by the Vienna group. In conclusion, BRACOIL has the potential to develop disruptive technology in the field of breast cancer screening and would improve both patient comfort and specificity of the diagnosis.

    more_vert
  • Funder: French National Research Agency (ANR) Project Code: ANR-22-CE19-0023
    Funder Contribution: 250,578 EUR

    Magnetic Resonance Elastography (MRE) is a non-invasive clinical tool for liver fibrosis characterization, yielding tissue stiffness values maps correlated to fibrosis stages. In the case of short T2 relaxation occurring in hemochromatosis, conventional MRE with its longer echo-time fails to deliver exploitable results due to a too low SNR. The liver is particularly affected in the case of hemochromatosis due to high iron deposition. If untreated the initial liver fibrosis can evolve to hepatocarcinoma with dire consequences for patients. Being able to properly assess the liver is therefore essential and doing so by MRI ideal since MRI is used for for non-invasive assessment of hepatic iron. Optimal Control (OC) MRE is a newly proposed alternative by our team, enabling higher SNR and coupled to ultra short echo-time (UTE) detection, evaluation of the stiffness of in vitro samples having T2 as low as 1 ms. OC-MRE is thus a technically suitable option and this project vows to produce an experimental demonstration of its applicability on hemochromatosis patients. To do so, the project is divided in different steps and the cornerstone is being able to apply OC-MRE on clinical MRIs. Until now, all developments have been carried out on pre-clinical MRIs having different technical specifications (field gradient strengths, RF amplitude etc...). A second challenge lies in accelerating the OC-MRE acquisition since using UTE detection leads to long acquisition time. Different K-space sampling will be considered and free-breathing acquisitions developed in particular with navigator sequences and dynamic slice positioning. Pre-clinical studies on mouse models will be carried out since they provide a good platform for clinical MRI developments that are contemplated. Once satisfactory preclinical and clinical in-vitro results are obtained, a feasibility study involving two hospital with two different vendor MRIs will be launched.

    more_vert
  • Funder: French National Research Agency (ANR) Project Code: ANR-15-CE23-0024
    Funder Contribution: 500,118 EUR

    The objective is to synthesize speech from text via the numerical simulation of the human speech production processes, i.e. the articulatory, aerodynamic and acoustic aspects. Corpus based approaches have taken a hegemonic place in text to speech synthesis. They exploit very good acoustic quality speech databases while covering a high number of expressions and of phonetic contexts. This is sufficient to produce intelligible speech. However, these approaches face almost insurmountable obstacles as soon as parameters intimately related to the physical process of speech production have to be modified. On the contrary, an approach which rests on the simulation of the physical speech production process makes explicitly use of source parameters, anatomy and geometry of the vocal tract, and of a temporal supervision strategy. It thus offers a direct control on the nature of the synthetic speech. The project is organized in 5 work packages: 1. Aerodynamic and acoustic simulations so as to produce a speech acoustic signal from the knowledge of the transversal area at any point of all the cavities of the vocal tract, 2. Source and coordination scenarios so as to coordinate sources together with the temporal evolution of the vocal tract, which is crucial for the production of consonants in order to ensure their identification by human listeners, 3. Supervision of the temporal evolution of the vocal tract geometry so as to anticipate the production of upcoming sounds and generate realistic articulatory gestures, 4. Acquisition of speech production data essential to know the vocal fold activation, aerodynamic parameters, and the geometrical shape of the vocal tract (via MRI at a high sampling rate), 5. General architecture to incorporate the different levels and synthesize an acoustic signal from the text. The development of realistic simulations of the speech production processes will be a key asset to understand the respective contributions of the anatomical characteristics, the coordination capabilities, and the control of the vocal folds in the resulting speech signal. The scope of this project goes far beyond the comprehension of speech production phenomena and concerns phonetics, motor control, and within the domain of automatic speech processing, at least text to speech synthesis. There is a number of applications. They concern situations in which standard text-to-speech synthesis is not well suited as foreign language learning or language acquisition. This project also opens new perspectives in the domain of expressive speech synthesis, and thus within the framework of conversational agents. In the medical field applications involve MRI acquisition protocols offering a high sampling rate applicable to organs which deform quickly over time, speech production pathologies, or evaluating the impact of surgery on the vocal folds or vocal tract. We firmly believe that ArtSpeech will realize scientific and major scientific and technical advances, and will demonstrate the interest of the physical approach whether to open new research perspectives, or develop highly innovative applications in the domain of speech production in the broadest sense. The consortium consists of four remarkably complementary research teams with leading international theoretical and practical experiences in the domains of: • aerodynamic and acoustic simulation of speech production, and modeling of the source and the geometry of the vocal tract, • magnetic resonance imaging and other acquisition techniques of speech production data.

    more_vert
  • chevron_left
  • 1
  • 2
  • chevron_right

Do the share buttons not appear? Please make sure, any blocking addon is disabled, and then reload the page.

Content report
No reports available
Funder report
No option selected
arrow_drop_down

Do you wish to download a CSV file? Note that this process may take a while.

There was an error in csv downloading. Please try again later.