Emmanuel Roux

Emmanuel Roux
Claude Bernard University Lyon 1 | UCBL · Centre de recherche en acquisition et traitement de l'image pour la santé (CREATIS)

PhD

About

25
Publications
3,206
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
322
Citations
Citations since 2016
19 Research Items
318 Citations
20162017201820192020202120220204060
20162017201820192020202120220204060
20162017201820192020202120220204060
20162017201820192020202120220204060
Introduction
Assistant Professor at CREATIS Laboratory (University Lyon 1): machine learning for medical imaging (interpretability, realistic simulations, motion estimation, lungs segmentation, multi-modal computer aided diagnosis). Sparse and quantized neural networks. Semi-supervised active deep-learning and transfert learning. PhD in 3-D ultrasound probes optimization. PhD in acoustics: stochastic optimization and information processing for 3-D ultrasound probe optimization.

Publications

Publications (25)
Article
Full-text available
Background PEEP selection in severe COVID-19 patients under extracorporeal membrane oxygenation (ECMO) is challenging as no study has assessed the alveolar recruitability in this setting. The aim of the study was to compare lung recruitability and the impact of PEEP on lung aeration in moderate and severe ARDS patients with or without ECMO, using c...
Conference Paper
When dealing with signal processing and deep learning for classification, the choice of inputting whether the raw signal or transforming it into a time-frequency representation (TFR) remains an open question. In this work, we propose a novel CNN-Transformer model based on multi-feature extraction and learnable representation attention weights per c...
Article
We propose a semi-supervised learning approach to annotate a dataset with reduced requirements for manual annotation and with controlled annotation error. The method is based on feature-space projection and label propagation using local quality metrics. First, an auto-encoder extracts the features of the samples in an unsupervised manner. Then, the...
Article
Full-text available
An ultrasound sparse array consists of a sparse distribution of elements over a 2-D aperture. Such an array is typically characterized by a limited number of elements, which in most cases results compatible with the channel number of the available scanners. Sparse arrays represent an attractive alternative to full 2-D arrays that may require the co...
Article
Purpose: Motion-mask segmentation from thoracic CT images is the process of extracting the region that encompasses lungs and viscera, where large displacements occur during breathing. It has been shown to help image registration between different respiratory phases. This registration step is, for example, useful for radiotherapy planning or calcul...
Article
Full-text available
Three dimensional ultrasound (3-D US) imaging methods based on 2-D array probes are increasingly investigated. However, the experimental test of new 3-D US approaches is contrasted by the need of controlling very large numbers of probe elements. Although this problem may be overcome by the use of 2-D sparse arrays, just a few experimental results h...
Article
Full-text available
Single plane wave (PW) imaging produces ultrasound (US) images of poor quality at high frame rates (ultrafast). High-quality PW imaging usually relies on the coherent compounding of several successive steered emissions (typically more than ten), which in turn results in a decreased frame rate. We propose a new strategy to reduce the number of emitt...
Article
Full matrix arrays are excellent tools for 3-D ultrasound imaging, but the required number of active elements is too high to be individually controlled by an equal number of scanner channels. The number of active elements is significantly reduced by the sparse array techniques, but the position of the remaining elements must be carefully optimized....
Thesis
Today, the use of 3D ultrasound imaging in cardiology is limited because imaging the entire myocardium on a single heartbeat, without apnea, remains a technological challenge. A solution consists in reducing the number of active elements in the 2D ultrasound probes to lighten the acquisition process: this approach leads to sparse arrays. The aim of...
Conference Paper
The role of 2D matrix arrays in the realization of real time 3D ultrasound imaging is crucial as the latter permit to acquire a complete volume. The lack of control systems for these arrays containing thousands of elements and the dimension of connection cables for such a number of elements are the main obstacles to the use of these technologies. T...
Conference Paper
This work deals with the design of optimized 2D sparse arrays transducers for 3D ultrasound imaging. With respect to the approaches based on simplified acoustic models of the single element pressure radiation, a more realistic acoustic simulation software (Field II) unfortunately yields long processing times. As a consequence, ways to accelerate th...
Conference Paper
The non-grid sparse array technique is a promising approach to overcome the connection difficulties of 2D matrix arrays and to partially compensate the energy loss linked to the element number reduction. Being independent from the spatial sampling conditions, this method leads to a significant improvement of the beam pattern when combined to the si...
Conference Paper
In this study, the benefits of integrating a realistic acoustic simulation in the 2-D non-grid sparse array design are investigated. A wideband shape sensitive (WSS) energy function is introduced. New degrees of freedom in 2-D arrays transducer optimization are thus made available. A related consequence is the capability of distinguishing probes co...

Network

Cited By

Projects

Projects (4)
Project
This project is centred on 3D+t ultrasound imaging and all possible development offer by this advanced imaging platform: sparse probe design, flow quantification, advanced volumetric beamforming, motion compensation and new applications.
Project
Improving ULA-OP systems image rendering (but any system can use it). Setting up and leading small statistical tests with clinicians preferences Wondering what we really want to see in a clinical image.