Using Reflectance Confocal Microscopy (RCM) for lentigo diagnosis is today considered essential. Indeed, RCM allows fast data acquisition with a high spatial resolution of the skin. In this paper, we use a deep convolutional neural network (CNN) to perform RCM image classification in order to detect lentigo. The proposed method relies on an InceptionV3 architecture combined with data augmentation and transfer learning. The method is validated on RCM data and shows very efficient detection performance with more than 98% of accuracy.

This paper deals with the detection of mu- suppression from electroencephalographic (EEG) signals in brain-computer interface (BCI). For this purpose, an efficient algorithm is proposed based on a statistical model and a linear classifier. Precisely, the generalized extreme value distribution (GEV) is proposed to represent the power spectrum density of the EEG signal in the central motor cortex. The associated three parameters are estimated using the maximum likelihood method. Based on these parameters, a simple and efficient linear classifier was designed to classify three types of events: imagery, movement, and resting. Preliminary results show that the proposed statistical model can be used in order to detect precisely the mu-suppression and distinguish different EEG events, with very good classification accuracy.

Prediction methods of glioblastoma tumours growth constitute a hard task due to the lack of medical data, which is mostly related to the patients' privacy, the cost of collecting a large medical data set, and the availability of related notations by experts. In this study, the authors propose a synthetic medical image generator (SMIG) with the purpose of generating synthetic data based on the generative adversarial network in order to provide anonymised data. In addition, to predict the glioblastoma multiform tumour growth the authors developed a tumour growth predictor based on end to end convolution neural network architecture that allows training on a public data set from the cancer imaging archive (TCIA), combined with the generated synthetic data. The authors also highlighted the impact of implicating a synthetic data generated using SMIG as a data augmentation tool. Despite small data size provided by TCIA data set, the obtained results demonstrate valuable tumour growth prediction accuracy.

This paper introduces a hierarchical Bayesian model for the reconstruction of hyperspectral images using compressed sensing measurements. This model exploits known properties of natural images, promoting the recovered image to be sparse on a selected basis and smooth in the image domain. The posterior distribution of this model is too complex to derive closed form expressions for the estimators of its parameters. Therefore, an MCMC method is investigated to sample this posterior distribution. The resulting samples are used to estimate the unknown model parameters and hyperparameters in an unsupervised framework. The results obtained on real data illustrate the improvement in reconstruction quality when compared to some existing techniques.

This paper presents a fast converging Riemannian steepest descent method for nonparametric statistical active contour models, with application to image segmentation. Unlike other fast algorithms, the proposed method is general and can be applied to any statistical active contour model from the exponential family, which comprises most of the models considered in the literature. This is achieved by first identifying the intrinsic statistical manifold associated with this class of active contours, and then constructing a steepest descent on that manifold. A key contribution of this paper is to derive a general and tractable closed-form analytic expression for the manifold's Riemannian metric tensor, which allows computing discrete gradient flows efficiently. The proposed methodology is demonstrated empirically and compared with other state of the art approaches on several standard test images, a phantom positron-emission-tomography scan and a B-mode echography of in-vivo human dermis.

Sparse signal/image recovery is a challenging topic that has captured a great interest during the last decades. To address the ill-posedness of the related inverse problem, regularization is often essential by using appropriate priors that promote the sparsity of the target signal/image. In this context, ℓ0+ ℓ1regularization has been widely investigated. In this paper, we introduce a new prior accounting simultaneously for both sparsity and smoothness of restored signals. We use a Bernoulli-generalized Gauss-Laplace distribution to perform ℓ0+ ℓ1+ ℓ2regularization in a Bayesian framework. Our results show the potential of the proposed approach especially in restoring the non-zero coefficients of the signal/image of interest.

This letter considers the problem of computing the Cramer–Rao bound for the parameters of a Markov random field. Computation of the exact bound is not feasible for most fields of interest because their likelihoods are intractable and have intractable derivatives. We show here how it is possible to formulate the computation of the bound as a statistical inference problem that can be solve approximately, but with arbitrarily high accuracy, by using a Monte Carlo method. The proposed methodology is successfully applied on the Ising and the Potts models.

This paper addresses the problem of estimating the Potts parameter β jointly with the unknown parameters of a Bayesian model within a Markov chain Monte Carlo (MCMC) algorithm. Standard MCMC methods cannot be applied to this problem because performing inference on β requires computing the intractable normalizing constant of the Potts model. In the proposed MCMC method, the estimation of β is conducted using a likelihood-free Metropolis-Hastings algorithm. Experimental results obtained for synthetic data show that estimating β jointly with the other unknown parameters leads to estimation results that are as good as those obtained with the actual value of β. On the other hand, choosing an incorrect value of β can degrade estimation performance significantly. To illustrate the interest of this method, the proposed algorithm is successfully applied to real bidimensional SAR and tridimensional ultrasound images.

This paper addresses the problem of jointly estimating the statistical distribution and segmenting lesions in multiple-tissue high-frequency skin ultrasound images. The distribution of multiple-tissue images is modeled as a spatially coherent finite mixture of heavy-tailed Rayleigh distributions. Spatial coherence inherent to biological tissues is modeled by enforcing local dependence between the mixture components. An original Bayesian algorithm combined with a Markov chain Monte Carlo method is then proposed to jointly estimate the mixture parameters and a label-vector associating each voxel to a tissue. More precisely, a hybrid Metropolis-within-Gibbs sampler is used to draw samples that are asymptotically distributed according to the posterior distribution of the Bayesian model. The Bayesian estimators of the model parameters are then computed from the generated samples. Simulation results are conducted on synthetic data to illustrate the performance of the proposed estimation strategy. The method is then successfully applied to the segmentation of in vivo skin tumors in high-frequency 2-D and 3-D ultrasound images.

This paper addresses the problem of estimating the statistical distribution of multiple-tissue non-stationary ultrasound images of skin. The distribution of multiple-tissue images is modeled as a finite mixture of Heavy-Tailed Rayleigh distributions. An original Bayesian algorithm combined with a Markov chain Monte Carlo method is then derived to jointly estimate the mixture parameters and a label vector associating each voxel to a tissue. Precisely, a hybrid Metropolis-within-Gibbs sampler is proposed to draw samples that are asymptotically distributed according to the posterior distribution of the Bayesian model. These samples are then used to compute the Bayesian estimators of the model parameters. Simulation results are conducted on synthetic data to illustrate the performance of the proposed estimation strategy. The method is then successfully applied to the detection of an in-vivo skin lesion in a high frequency 3D ultrasound image.

This paper deals with segmentation of dermatological OCT images. Classic image segmentation techniques fail to produce accurate results due to the wide presence of speckle. We propose using speckle as source of information in the segmentation process. Different statistical models are analyzed in terms of their ability to differentiate skin layers. The local speckle parameters are used as a features-vector to classify, in a supervised way, different regions. Experimental results are presented using a corpus of twenty three real images delineated by experts. These confirm the potential of the method to generate useful data for robust segmentation.

This paper deals with multifractal characterization of skin cancer in ultrasound images. The proposed method establishes a multifractal analysis framework of such images based on a new multiresolution indicator, called the maximum wavelet coefficient, derived from the wavelet leaders. Two main contributions are brought up: first, it proposes a method for the estimation of multifractal features. Second, it reveals the potential of multifractal features to characterize skin melanoma. In order to study the efficiency of our maximum coefficient estimator, we compare its results on a simulated image against wavelet leaders based estimator. We then apply the approach on various samples from different skin images. Results show that the extracted features make a promising quantitative indicator to distinguish between different tissues.

In Computed tomography (CT) imaging, respiratory motions create artifacts that distort anatomic structures leading to serious difficulties in lung cancer diagnosis and treatment. 4D CT approaches try to remedy this problem by acquiring CT images synchronized to respiration. Reconstruction methods allow the correction of motions to create smooth images. However, such methods rely on the acquisition of a large number of images, increasing the risk of toxicity. In this paper, we develop a method to interpolate accurate CT images at any respiratory volume. The method consists of acquiring few images along with their corresponding respiratory volumes. The bidirectional registration of the two images bounding the target volume produces optical flow fields. The originality of our method lies in the volume-based interpolation of these vector fields at the target position. The weighted backward-mapping of the inverse of these fields produces the desired image. Experimentations using NCAT simulations and real chest images, acquired with RPM system, have been carried out. The results show the good potential of the proposed method.

Segmentation with active contours is heavily dependent on the initialization. In this paper we propose a novel method for a quasi-automatic initialization of deformable models. Our method relies on the use of an additional energy based on the gradient vector flow. We define the centers of strong and weak divergence and use them to set up the initial curve. As our goal is the segmentation of the heart cavities, we also propose a new gradient vector field for ultrasound images based on the coefficient of variation. Results on real ultra-sound images are presented and compared to the boundaries manually outlined by an expert. They confirm the potential of the method.

This paper deals with anisotropic diffusion in images affected by speckle. Two existing methods are reviewed. The first is a robust diffusion technique, non adapted to speckle, based on the Tukey function. The second applies an isotropic diffusion to speckle but lacks robustness. The contribution of this paper is to create a robust anisotropic diffusion filter adapted to speckle. The proposed approach is based on the two reviewed methods and introduces an original diffusion tensor Experimentation results are presented and the performance of the three methods compared. The proposed algorithm shows significant enhancement.

We present the main components of an adaptive tutoring system based on cognitive learning styles. A Bayesian network is used to model the student learning style. An original domain model based on Bloom taxonomy is adopted. An instruction adaptation module matches the student style to the domain model based on pedagogical rules that can be modified.

A high-parallel VLSI core architecture for MPEG-4 motion estimation is proposed. It possesses the characteristics of low memory bandwidth and low clock rate requirements, thus primarily aiming at 3G mobile applications. Based on a one-dimensional tree architecture, the architecture employs the dual-register/buffer technique to reduce the preload and alignment cycles. As an example, a full-search block matching algorithm has been mapped onto this architecture using a 16-PE array that has the ability to calculate the motion vectors of QCIF video sequences in real time at 1 MHz clock rate and using 15.5 Mbytes/s memory bandwidth.

A high-parallel VLSI core architecture for MPEG-4 motion estimation is proposed in this paper. It possesses the characteristics of low memory bandwidth and low clock rate requirements, thus primarily aiming at 3G mobile applications. Based on a one-dimensional tree architecture, the architecture employs the dual-register/buffer technique to reduce the preload and alignment cycles. As an example, full-search block matching algorithm has been mapped onto this architecture using a 16-PE array that has the ability to calculate the motion vectors of QCIF video sequences in real time at 1 MHz clock rate and using 15.5 Mbytes/s memory bandwidth.

The development of information and communication technology has lead to the reorganisation of work methods and processes. More and more tasks are accomplished in a collaborative way by geographically distributed teams. These new working methods require proper training and appropriate skills, especially the ability to work in virtual environments. NETPRO (Network Based Project Learning in Engineering Education) is a European pilot project that addresses these issues. Its objective is to elaborate an innovative network based project learning model for engineering education and to develop web-based tools for implementing and supporting this pedagogy. This paper discusses some features of project-based pedagogy and proposes a model of a project-based learning management system.