Data driven regularization models of non-linear ill-posed inverse problems in imaging

Imaging technologies are widely used in application fields such as natural sciences, engineering, medicine, and life sciences. A broad class of imaging problems reduces to solve ill-posed inverse problems (IPs). Traditional strategies to solve these ill-posed IPs rely on variational regularization methods, which are based on minimization of suitable energies, and make use of knowledge about the image formation model (forward operator) and prior knowledge on the solution, but lack in incorporating knowledge directly from data. On the other hand, the more recent learned approaches can easily learn the intricate statistics of images depending on a large set of data, but do not have a systematic method for incorporating prior knowledge about the image formation model. The main purpose of this thesis is to discuss data-driven image reconstruction methods which combine the benefits of these two different reconstruction strategies for the solution of highly nonlinear ill-posed inverse problems. Mathematical formulation and numerical approaches for image IPs, including linear as well as strongly nonlinear problems are described. More specifically we address the Electrical impedance Tomography (EIT) reconstruction problem by unrolling the regularized Gauss-Newton method and integrating the regularization learned by a data-adaptive neural network. Furthermore we investigate the solution of non-linear ill-posed IPs introducing a deep-PnP framework that integrates the graph convolutional denoiser into the proximal Gauss-Newton method with a practical application to the EIT, a recently introduced promising imaging technique. Efficient algorithms are then applied to the solution of the limited electrods problem in EIT, combining compressive sensing techniques and deep learning strategies. Finally, a transformer-based neural network architecture is adapted to restore the noisy solution of the Computed Tomography problem recovered using the filtered back-projection method.

The problem of administrative areas : an essay in reconstruction /

Mode of access: Internet.

The rational reconstruction of the research program on classic rationalism: Locke and the empiricist approach

This article intends to rationally reconstruct Locke`s theory of knowledge as incorporated in a research program concerning the nature and structure of the theories and models of rationality. In previous articles we argued that the rationalist program can be subdivided into the classical rationalistic subprogram, which includes the knowledge theories of Descartes, Locke, Hume and Kant, the neoclassical subprogram, which includes the approaches of Duhem, Poincare and Mach, and the critical subprogram of Popper. The subdivision results from the different views of rationality proposed by each one of these subprograms, as well as from the tools made available by each one of them, containing theoretical instruments used to arrange, organize and develop the discussion on rationality, the main one of which is the structure of solution of problems. In this essay we intend to reconstruct the assumptions of Locke`s theory of knowledge, which in our view belongs to the classical rationalistic subprogram because it shares with it the thesis of the identity of (scientific) knowledge and certain knowledge.

QUADRANT-SEARCHING: A NEW TECHNIQUE TO REDUCE THE SEARCH SPACE OF THE INVERSE PROBLEM OF EIT USING BEM TO THE DIRECT PROBLEM

The image reconstruction using the EIT (Electrical Impedance Tomography) technique is a nonlinear and ill-posed inverse problem which demands a powerful direct or iterative method. A typical approach for solving the problem is to minimize an error functional using an iterative method. In this case, an initial solution close enough to the global minimum is mandatory to ensure the convergence to the correct minimum in an appropriate time interval. The aim of this paper is to present a new, simple and low cost technique (quadrant-searching) to reduce the search space and consequently to obtain an initial solution of the inverse problem of EIT. This technique calculates the error functional for four different contrast distributions placing a large prospective inclusion in the four quadrants of the domain. Comparing the four values of the error functional it is possible to get conclusions about the internal electric contrast. For this purpose, initially we performed tests to assess the accuracy of the BEM (Boundary Element Method) when applied to the direct problem of the EIT and to verify the behavior of error functional surface in the search space. Finally, numerical tests have been performed to verify the new technique.

Optimization of breast tomosynthesis image reconstruction using parallel computing

Breast cancer is the most common cancer among women, being a major public health problem. Worldwide, X-ray mammography is the current gold-standard for medical imaging of breast cancer. However, it has associated some well-known limitations. The false-negative rates, up to 66% in symptomatic women, and the false-positive rates, up to 60%, are a continued source of concern and debate. These drawbacks prompt the development of other imaging techniques for breast cancer detection, in which Digital Breast Tomosynthesis (DBT) is included. DBT is a 3D radiographic technique that reduces the obscuring effect of tissue overlap and appears to address both issues of false-negative and false-positive rates. The 3D images in DBT are only achieved through image reconstruction methods. These methods play an important role in a clinical setting since there is a need to implement a reconstruction process that is both accurate and fast. This dissertation deals with the optimization of iterative algorithms, with parallel computing through an implementation on Graphics Processing Units (GPUs) to make the 3D reconstruction faster using Compute Unified Device Architecture (CUDA). Iterative algorithms have shown to produce the highest quality DBT images, but since they are computationally intensive, their clinical use is currently rejected. These algorithms have the potential to reduce patient dose in DBT scans. A method of integrating CUDA in Interactive Data Language (IDL) is proposed in order to accelerate the DBT image reconstructions. This method has never been attempted before for DBT. In this work the system matrix calculation, the most computationally expensive part of iterative algorithms, is accelerated. A speedup of 1.6 is achieved proving the fact that GPUs can accelerate the IDL implementation.

Genome-scale metabolic network reconstruction of Polaromonas sp. strain JS666: analysis of cDCE degradation rates and design of experiments for bioremediation improvement

Release of chloroethene compounds into the environment often results in groundwater contamination, which puts people at risk of exposure by drinking contaminated water. cDCE (cis-1,2-dichloroethene) accumulation on subsurface environments is a common environmental problem due to stagnation and partial degradation of other precursor chloroethene species. Polaromonas sp. strain JS666 apparently requires no exotic growth factors to be used as a bioaugmentation agent for aerobic cDCE degradation. Although being the only suitable microorganism found capable of such, further studies are needed for improving the intrinsic bioremediation rates and fully comprehend the metabolic processes involved. In order to do so, a metabolic model, iJS666, was reconstructed from genome annotation and available bibliographic data. FVA (Flux Variability Analysis) and FBA (Flux Balance Analysis) techniques were used to satisfactory validate the predictive capabilities of the iJS666 model. The iJS666 model was able to predict biomass growth for different previously tested conditions, allowed to design key experiments which should be done for further model improvement and, also, produced viable predictions for the use of biostimulant metabolites in the cDCE biodegradation.

Efficient total variation algorithm for fetal brain MRI reconstruction.

Fetal MRI reconstruction aims at finding a high-resolution image given a small set of low-resolution images. It is usually modeled as an inverse problem where the regularization term plays a central role in the reconstruction quality. Literature has considered several regularization terms s.a. Dirichlet/Laplacian energy, Total Variation (TV)- based energies and more recently non-local means. Although TV energies are quite attractive because of their ability in edge preservation, standard explicit steepest gradient techniques have been applied to optimize fetal-based TV energies. The main contribution of this work lies in the introduction of a well-posed TV algorithm from the point of view of convex optimization. Specifically, our proposed TV optimization algorithm or fetal reconstruction is optimal w.r.t. the asymptotic and iterative convergence speeds O(1/n2) and O(1/√ε), while existing techniques are in O(1/n2) and O(1/√ε). We apply our algorithm to (1) clinical newborn data, considered as ground truth, and (2) clinical fetal acquisitions. Our algorithm compares favorably with the literature in terms of speed and accuracy.

Surface reconstruction from microscopic images in optical lithography.

This paper presents a method to reconstruct 3D surfaces of silicon wafers from 2D images of printed circuits taken with a scanning electron microscope. Our reconstruction method combines the physical model of the optical acquisition system with prior knowledge about the shapes of the patterns in the circuit; the result is a shape-from-shading technique with a shape prior. The reconstruction of the surface is formulated as an optimization problem with an objective functional that combines a data-fidelity term on the microscopic image with two prior terms on the surface. The data term models the acquisition system through the irradiance equation characteristic of the microscope; the first prior is a smoothness penalty on the reconstructed surface, and the second prior constrains the shape of the surface to agree with the expected shape of the pattern in the circuit. In order to account for the variability of the manufacturing process, this second prior includes a deformation field that allows a nonlinear elastic deformation between the expected pattern and the reconstructed surface. As a result, the minimization problem has two unknowns, and the reconstruction method provides two outputs: 1) a reconstructed surface and 2) a deformation field. The reconstructed surface is derived from the shading observed in the image and the prior knowledge about the pattern in the circuit, while the deformation field produces a mapping between the expected shape and the reconstructed surface that provides a measure of deviation between the circuit design models and the real manufacturing process.

Update on the non-prewhitening model observer in computed tomography for the assessment of the adaptive statistical and model-based iterative reconstruction algorithms.

The state of the art to describe image quality in medical imaging is to assess the performance of an observer conducting a task of clinical interest. This can be done by using a model observer leading to a figure of merit such as the signal-to-noise ratio (SNR). Using the non-prewhitening (NPW) model observer, we objectively characterised the evolution of its figure of merit in various acquisition conditions. The NPW model observer usually requires the use of the modulation transfer function (MTF) as well as noise power spectra. However, although the computation of the MTF poses no problem when dealing with the traditional filtered back-projection (FBP) algorithm, this is not the case when using iterative reconstruction (IR) algorithms, such as adaptive statistical iterative reconstruction (ASIR) or model-based iterative reconstruction (MBIR). Given that the target transfer function (TTF) had already shown it could accurately express the system resolution even with non-linear algorithms, we decided to tune the NPW model observer, replacing the standard MTF by the TTF. It was estimated using a custom-made phantom containing cylindrical inserts surrounded by water. The contrast differences between the inserts and water were plotted for each acquisition condition. Then, mathematical transformations were performed leading to the TTF. As expected, the first results showed a dependency of the image contrast and noise levels on the TTF for both ASIR and MBIR. Moreover, FBP also proved to be dependent of the contrast and noise when using the lung kernel. Those results were then introduced in the NPW model observer. We observed an enhancement of SNR every time we switched from FBP to ASIR to MBIR. IR algorithms greatly improve image quality, especially in low-dose conditions. Based on our results, the use of MBIR could lead to further dose reduction in several clinical applications.

Reconstruction of the join time-delay Doppler-scale reflectivity density in the wide-band regime. A frame theory based approach

The inverse scattering problem concerning the determination of the joint time-delayDoppler-scale reflectivity density characterizing continuous target environments is addressed by recourse to the generalized frame theory. A reconstruction formula,involving the echoes of a frame of outgoing signals and its corresponding reciprocalframe, is developed. A ‘‘realistic’’ situation with respect to the transmission ofa finite number of signals is further considered. In such a case, our reconstruction formula is shown to yield the orthogonal projection of the reflectivity density onto a subspace generated by the transmitted signals.

The continuous wavelet transform as a maximum entropy solution of the corresponding inverse problem

The continuous wavelet transform is obtained as a maximumentropy solution of the corresponding inverse problem. It is well knownthat although a signal can be reconstructed from its wavelet transform,the expansion is not unique due to the redundancy of continuous wavelets.Hence, the inverse problem has no unique solution. If we want to recognizeone solution as "optimal", then an appropriate decision criterion hasto be adopted. We show here that the continuous wavelet transform is an"optimal" solution in a maximum entropy sense.

Sparse image reconstruction on the sphere: implications of a new sampling theorem.

We study the impact of sampling theorems on the fidelity of sparse image reconstruction on the sphere. We discuss how a reduction in the number of samples required to represent all information content of a band-limited signal acts to improve the fidelity of sparse image reconstruction, through both the dimensionality and sparsity of signals. To demonstrate this result, we consider a simple inpainting problem on the sphere and consider images sparse in the magnitude of their gradient. We develop a framework for total variation inpainting on the sphere, including fast methods to render the inpainting problem computationally feasible at high resolution. Recently a new sampling theorem on the sphere was developed, reducing the required number of samples by a factor of two for equiangular sampling schemes. Through numerical simulations, we verify the enhanced fidelity of sparse image reconstruction due to the more efficient sampling of the sphere provided by the new sampling theorem.

Reconstruction of 3D Planar Objects with Partial Occlusion

Kolmiulotteisten kappaleiden rekonstruktio on yksi konenäön haastavimmista ongelmista, koska kappaleiden kolmiulotteisia etäisyyksiä ei voida selvittää yhdestä kaksiulotteisesta kuvasta. Ongelma voidaan ratkaista stereonäön avulla, jossa näkymän kolmiulotteinen rakenne päätellään usean kuvan perusteella. Tämä lähestymistapa mahdollistaa kuitenkin vain rekonstruktion niille kappaleiden osille, jotka näkyvät vähintään kahdessa kuvassa. Piilossa olevien osien rekonstruktio ei ole mahdollista pelkästään stereonäön avulla. Tässä työssä on kehitetty uusi menetelmä osittain piilossa olevien kolmiulotteisten tasomaisten kappaleiden rekonstruktioon. Menetelmän avulla voidaan selvittää hyvällä tarkkuudella tasomaisista pinnoista koostuvan kappaleen muoto ja paikka käyttäen kahta kuvaa kappaleesta. Menetelmä perustuu epipolaarigeometriaan, jonka avulla selvitetään molemmissa kuvissa näkyvät kappaleiden osat. Osittain piilossa olevien piirteiden rekonstruointi suoritetaan käyttämäen stereonäköä sekä tietoa kappaleen rakenteesta. Esitettyä ratkaisua voitaisiin käyttää esimerkiksi kolmiulotteisten kappaleiden visualisointiin, robotin navigointiin tai esineentunnistukseen.

Efficient total variation algorithm for fetal MRI reconstruction

Fetal MRI reconstruction aims at finding a high-resolution image given a small set of low-resolution images. It is usually modeled as an inverse problem where the regularization term plays a central role in the reconstruction quality. Literature has considered several regularization terms s.a. Dirichlet/Laplacian energy [1], Total Variation (TV)based energies [2,3] and more recently non-local means [4]. Although TV energies are quite attractive because of their ability in edge preservation, standard explicit steepest gradient techniques have been applied to optimize fetal-based TV energies. The main contribution of this work lies in the introduction of a well-posed TV algorithm from the point of view of convex optimization. Specifically, our proposed TV optimization algorithm for fetal reconstruction is optimal w.r.t. the asymptotic and iterative convergence speeds O(1/n(2)) and O(1/root epsilon), while existing techniques are in O(1/n) and O(1/epsilon). We apply our algorithm to (1) clinical newborn data, considered as ground truth, and (2) clinical fetal acquisitions. Our algorithm compares favorably with the literature in terms of speed and accuracy.

Exploitation de contraintes photométriques et géométriques en vision : application au suivi, au calibrage et à la reconstruction

Cette thése a été réalisée dans le cadre d'une cotutelle avec l'Institut National Polytechnique de Grenoble (France). La recherche a été effectuée au sein des laboratoires de vision 3D (DIRO, UdM) et PERCEPTION-INRIA (Grenoble).