Cardiac strain estimation from ultrasound images is an efficient tool for the diagnosis of cardiac diseases. This study focuses on cardiac amyloidosis, a pathology characterized by non-specific early symptoms such as the increased wall thickness. Recent clinical studies have demonstrated that patients with cardiac amyloidosis present an apex-to-base gradient longitudinal strain pattern, i.e., a normal strain in apex and abnormally lower values for base segments. Existing cardiac motion estimation methods belong to three categories based on optical flow, speckle tracking and elastic registration. To overcome the ill-posedness of motion estimation, they use local parametric models (e.g., affine) or global regularizations (e.g., B-splines). The objective of this study is to evaluate a recently proposed cardiac motion estimation method based on dictionary learning on patients subjected to cardiac amyloidosis.

Le démélange d’images hyperspectrales est un exemple particulier du problème de factorisation en matrices non-négatives (NMF) qui consiste à identifier les signatures spectrales d’un milieu imagé ainsi que leurs proportions dans chacun des pixels. Toutefois, le nombre important de pixels composant ces images peut s’avérer contraignant en termes de mémoire ou de temps de calcul, ce qui peut motiver le développement de techniques d’estimation distribuées (entre plusieurs processeurs et/ou plusieurs machines). Dans cette perspective, nous proposons une approche distribuée du problème de démélange, basée sur de récentes avancées en optimisation distribuée asynchrone inspirées de l’algorithme proximal alternating linearized minimization (PALM). L’intérêt d’une estimation asynchrone par rapport à une procédure synchrone est illustré dans ce contexte sur des données synthétiques.

A classical problem in hyperspectral imaging, referred to as hyperspectral unmixing, consists in estimating spectra associated with each material present in an image and their proportions in each pixel. In practice, illumination variations (e.g., due to declivity or complex interactions with the observed materials) and the possible presence of outliers can result in significant changes in both the shape and the amplitude of the measurements, thus modifying the extracted signatures. In this context, sequences of hyperspectral images are expected to be simultaneously affected by such phenomena when acquired on the same area at different time instants. Thus, we propose a hierarchical Bayesian model to simultaneously account for smooth and abrupt spectral variations affecting a set of multitemporal hyperspectral images to be jointly unmixed. This model assumes that smooth variations can be interpreted as the result of endmember variability, whereas abrupt variations are due to significant changes in the imaged scene (e.g., presence of outliers, additional endmembers, etc.). The parameters of this Bayesian model are estimated using samples generated by a Gibbs sampler according to its posterior. Performance assessment is conducted on synthetic data in comparison with state-of-the-art unmixing methods.

This paper studies a new Bayesian algorithm for the joint reconstruction and classification of reflectance confocal microscopy (RCM) images, with application to the identification of human skin lentigo. The proposed Bayesian approach takes advantage of the distribution of the multiplicative speckle noise affecting the true reflectivity of these images and of appropriate priors for the unknown model parameters. A Markov chain Monte Carlo (MCMC) algorithm is proposed to jointly estimate the model parameters and the image of true reflectivity while classifying images according to the distribution of their reflectivity. Precisely, a Metropolis-within-Gibbs sampler is investigated to sample the posterior distribution of the Bayesian model associated with RCM images and to build estimators of its parameters, including labels indicating the class of each RCM image. The resulting algorithm is applied to synthetic data and to real images from a clinical study containing healthy and lentigo patient.

In the community of remote sensing, nonlinear mixture models have recently received particular attention in hyperspectral image processing. In this paper, we present a novel nonlinear spectral unmixing method following the recent multilinear mixing model of Heylen and Scheunders, which includes an infinite number of terms related to interactions between different endmembers. The proposed unmixing method is unsupervised in the sense that the endmembers are estimated jointly with the abundances and other parameters of interest, i.e., the transition probability of undergoing further interactions. Nonnegativity and sum-to-one constraints are imposed on abun- dances while only nonnegativity is considered for endmembers. The resulting unmixing problem is formulated as a constrained nonlinear optimization problem, which is solved by a block coordinate descent strategy, consisting of updating the end- members, abundances, and transition probability iteratively. The proposed method is evaluated and compared with existing linear and nonlinear unmixing methods for both synthetic and real hyperspectral data sets acquired by the airborne visible/infrared imaging spectrometer sensor. The advantage of using nonlinear unmixing as opposed to linear unmixing is clearly shown in these examples.

This paper studies a data-driven approach to detect faults in flight control systems of civil aircraft. A particular class of failures, referred to as Oscillatory Failure Cases (OFC), impacting the actuator servo loop has motivated the authors to consider a data-driven approach based on distance and correlation measures (see reference [Goupil et al.(2016). A data-driven approach to detect faults in the Airbus flight control system. IFAC-PapersOnLine, 49(17), 52-57] of this paper) leading to promising results compared to the state-of-the-art methods based on analytical redundancy. The present paper extends the formulation and the results of the considered OFC detection approach investigating Support Vector Machine (SVM) techniques to define a more accurate detector based on distance and correlation measures.

The SPOT 6-7 satellite ground segment includes a systematic and automatic cloud detection step in order to feed a catalogue with a binary cloud mask and an appropriate condence measure. However, current approaches for cloud detection, that are mostly based on machine learning and hand crafted features, have shown lack of robustness. In other tasks such as image recognition, deep learning methods have shown outstanding results outperforming many state-of-the-art methods. These methods are known to produce a powerful representation that can capture texture, shape and contextual information. This paper studies the potential of deep learning methods for cloud detection in order to achieve state-of-the-art performance. A comparison between deep learning methods used with classical handcrafted features and classical convolutional neural networks is performed for cloud detection. Experiments are conducted on a SPOT 6 image database with various landscapes and cloud coverage and show promising results.