Robust Multiresolution Research Articles

COVID-19 Diagnosis from Chest X-ray Images Using a Robust Multi-Resolution Analysis Siamese Neural Network with Super-Resolution Convolutional Neural Network.

Chest X-ray (CXR) is becoming a useful method in the evaluation of coronavirus disease 19 (COVID-19). Despite the global spread of COVID-19, utilizing a computer-aided diagnosis approach for COVID-19 classification based on CXR images could significantly reduce the clinician burden. There is no doubt that low resolution, noise and irrelevant annotations in chest X-ray images are a major constraint to the performance of AI-based COVID-19 diagnosis. While a few studies have made huge progress, they underestimate these bottlenecks. In this study, we propose a super-resolution-based Siamese wavelet multi-resolution convolutional neural network called COVID-SRWCNN for COVID-19 classification using chest X-ray images. Concretely, we first reconstruct high-resolution (HR) counterparts from low-resolution (LR) CXR images in order to enhance the quality of the dataset for improved performance of our model by proposing a novel enhanced fast super-resolution convolutional neural network (EFSRCNN) to capture texture details in each given chest X-ray image. Exploiting a mutual learning approach, the HR images are passed to the proposed Siamese wavelet multi-resolution convolutional neural network to learn the high-level features for COVID-19 classification. We validate the proposed COVID-SRWCNN model on public-source datasets, achieving accuracy of 98.98%. Our screening technique achieves 98.96% AUC, 99.78% sensitivity, 98.53% precision, and 98.86% specificity. Owing to the fact that COVID-19 chest X-ray datasets are low in quality, experimental results show that our proposed algorithm obtains up-to-date performance that is useful for COVID-19 screening.

A new Pansharpening Approach Based on NonSubsampled Contourlet Transform Using Enhanced PCA Applied to SPOT and ALSAT-2A Satellite Images

The Pansharpening process aims to merge the high spatial resolution of the panchromatic (Pan) image with the spectral information of the multispectral (MS) images. The fused images should represent an enhanced spatial resolution and should preserve the spectral information simultaneously. In the two last decades, many pansharpening algorithms have been implemented in the literature such as IHS, PCA, HPF, etc. Therefore, in comparison with the various conventional methods, our contribution is the conception of a new fusion scheme by combining two different approaches: the Principal Component Analysis (PCA) and the NonSubsampled Contourlet Transform (NSCT). The hypothesis in this combination represent the use of PCA, in first, like statistical approach to obtain from the MS bands the main information, followed by the NSCT as a robust multiresolution and multidirectional approach, to give an optimal representation of the characteristics in the image compared to the classical methods (wavelets), in order to overcome the drawback caused by PCA with the spectral distortion. The focus of this study is to show a new way to combine differently from usual those two approaches, to find a compromise between enhancing the spatial resolution and preserving the spectral information at the same time. The quality of the resulted images has been evaluated by the visual interpretation and the statistical assessment to prove its efficiency compared to other conventional methods.

Robust Multiresolution Wavelet Analysis and Window Search Based Approach for Electrocardiogram Features Delineation

Robust Multiresolution Wavelet Analysis and Window Search Based Approach for Electrocardiogram Features Delineation

BRINT: binary rotation invariant and noise tolerant texture classification.

In this paper, we propose a simple, efficient, yet robust multiresolution approach to texture classification-binary rotation invariant and noise tolerant (BRINT). The proposed approach is very fast to build, very compact while remaining robust to illumination variations, rotation changes, and noise. We develop a novel and simple strategy to compute a local binary descriptor based on the conventional local binary pattern (LBP) approach, preserving the advantageous characteristics of uniform LBP. Points are sampled in a circular neighborhood, but keeping the number of bins in a single-scale LBP histogram constant and small, such that arbitrarily large circular neighborhoods can be sampled and compactly encoded over a number of scales. There is no necessity to learn a texton dictionary, as in methods based on clustering, and no tuning of parameters is required to deal with different data sets. Extensive experimental results on representative texture databases show that the proposed BRINT not only demonstrates superior performance to a number of recent state-of-the-art LBP variants under normal conditions, but also performs significantly and consistently better in presence of noise due to its high distinctiveness and robustness. This noise robustness characteristic of the proposed BRINT is evaluated quantitatively with different artificially generated types and levels of noise (including Gaussian, salt and pepper, and speckle noise) in natural texture images.

Robust Multiresolution Coding

In multiresolution coding a source sequence is encoded into a base layer and a refinement layer. The refinement layer, constructed using a conditional codebook, is in general not decodable without the correct reception of the base layer. By relating multiresolution coding with multiple description coding, we show that it is in fact possible to construct multiresolution codes in certain ways so that the refinement layer alone can be used to reconstruct the source to achieve a nontrivial distortion. As a consequence, one can improve the robustness of the existing multiresolution coding schemes without sacrificing the efficiency. Specifically, we obtain an explicit expression of the minimum distortion achievable by the refinement layer for arbitrary finite alphabet sources with Hamming distortion measure. Experimental results show that the information-theoretic limits can be approached using a practical robust multiresolution coding scheme based on low-density generator matrix codes.

Registration-Based Approach for Reconstruction of High-Resolution In Utero Fetal MR Brain Images

This paper describes a novel approach to forming high-resolution MR images of the human fetal brain. It addresses the key problem of fetal motion by proposing a registration-refined compounding of multiple sets of orthogonal fast two-dimensional MRI slices, which are currently acquired for clinical studies, into a single high-resolution MRI volume. A robust multiresolution slice alignment is applied iteratively to the data to correct motion of the fetus that occurs between two-dimensional acquisitions. This is combined with an intensity correction step and a super-resolution reconstruction step, to form a single high isotropic resolution volume of the fetal brain. Experimental validation on synthetic image data with known motion types and underlying anatomy, together with retrospective application to sets of clinical acquisitions, are included. Results indicate that this method promises a unique route to acquiring high-resolution MRI of the fetal brain in vivo allowing comparable quality to that of neonatal MRI. Such data provide a highly valuable window into the process of normal and abnormal brain development, which is directly applicable in a clinical setting.

Robust Multiscale Deformable Registration of 3D Ultrasound Images

In this paper, we embed the minimization scheme of an automatic 3D non-rigid registration method in a multiscale framework. The initial model formulation was expressed as a robust multiresolution and multigrid minimization scheme. At the finest level of the multiresolution pyramid, we introduce a focusing strategy from coarse-to-fine scales which leads to an improvement in the accuracy of the registration process. A focusing strategy has been tested for a linear and a non-linear scale-space. Results on real 3D ultrasound images are discussed.

Range image reconstruction based on robust multiresolution estimation of surface parameters

This paper proposes two robust multiresolution estimation methods of surface parameters for range images. Based on the robust estimation of surface parameters, the proposed methods approximate a patch to a planar surface in the locally adaptive window. Selection of resolution is made pixelwise by comparing a locally computed homogeneity measure with the global threshold obtained by the distribution of the approximation error. The proposed multiresolution surface parameter estimation methods are applied to range image reconstruction and segmentation. Computer simulation results with noisy images contaminated by additive Gaussian noise and impulse noise show that the proposed multiresolution reconstruction methods preserve step and roof edges better than the conventional methods. Also the segmentation methods based on the estimated surface parameters are shown to be robust to noise.

Segmentation of brain 3D MR images using level sets and dense registration

This paper presents a strategy for the segmentation of brain from volumetric MR images which integrates 3D segmentation and 3D registration processes. The segmentation process is based on the level set formalism. A closed 3D surface propagates towards the desired boundaries through the iterative evolution of a 4D implicit function. In this work, the propagation relies on a robust evolution model including adaptive parameters. These depend on the input data and on statistical distribution models. The main contribution of this paper is the use of an automatic registration method to initialize the surface, as an alternative solution to manual initialization. The registration is achieved through a robust multiresolution and multigrid minimization scheme. This coupling significantly improves the quality of the method, since the segmentation is faster, more reliable and fully automatic. Quantitative and qualitative results on both synthetic and real volumetric brain MR images are presented and discussed.

Automatic interpretation and coding of face images using flexible models

Face images are difficult to interpret because they are highly variable. Sources of variability include individual appearance, 3D pose, facial expression, and lighting. We describe a compact parametrized model of facial appearance which takes into account all these sources of variability. The model represents both shape and gray-level appearance, and is created by performing a statistical analysis over a training set of face images. A robust multiresolution search algorithm is used to fit the model to faces in new images. This allows the main facial features to be located, and a set of shape, and gray-level appearance parameters to be recovered. A good approximation to a given face can be reconstructed using less than 100 of these parameters. This representation can be used for tasks such as image coding, person identification, 3D pose recovery, gender recognition, and expression recognition. Experimental results are presented for a database of 690 face images obtained under widely varying conditions of 3D pose, lighting, and facial expression. The system performs well on all the tasks listed above.