In the wood industry, logs are commonly quality screened by discrete X-ray scans on a moving conveyor belt from a few source positions. Typically, the measurements are obtained in a single two-dimensional (2D) plane (a “slice”) by a sequential scanning geometry. The data from each slice alone does not carry sufficient information for a three-dimensional tomographic reconstruction in which biological features of interest in the log are well preserved. In the present work, we propose a learned iterative reconstruction method based on the Learned Primal-Dual neural network, suited for sequential scanning geometries. Our method accumulates information between neighbouring slices, instead of only accounting for single slices during reconstruction. Evaluations were performed by training U-Nets on segmentation of knots (branches), which are crucial features in wood processing. Our quantitative and qualitative evaluations show that with as few as five source positions our method yields reconstructions of logs that are sufficiently accurate to identify biological features like knots (branches), heartwood and sapwood.

Abstract. We address recovery of the three-dimensional backbone structure of single polypeptide proteins from single-particle cryo–electron microscopy (Cryo-SPA) data. Cryo-SPA produces noisy tomographic projections of electrostatic potentials of macromolecules. From these projections, we use methods from shape analysis to recover the three-dimensional backbone structure. Thus, we view the reconstruction problem as an indirect matching problem, where a point cloud representation of the protein backbone is deformed to match two-dimensional tomography data. The deformations are obtained via the action of a matrix Lie group. By selecting a deformation energy, the optimality conditions are obtained, which lead to computational algorithms for optimal deformations. We showcase our approach on synthetic data, for which we recover the three-dimensional structure of the backbone.

We propose to learn a data-adaptive convex regularizer, which is parameterized using an input-convex neural network (ICNN), for variational image reconstruction. The regularizer parameters are learned adversarially by telling apart clean images from the artifact-ridden ones in a training dataset. Convexity of the regularizer is theoretically and practically important since (i) one can establish well-posedness guarantees for the corresponding variational reconstruction problem and (ii) devise provably convergent optimization algorithms for reconstruction. In particular, the resulting method is shown to be convergent in the sense of regularization and can be solved provably using a gradient-based solver. To demonstrate the performance of our approach for solving inverse problems, we consider deblurring natural images and reconstruction in X-ray computed tomography (CT) and show that the proposed convex regularizer is on par with and sometimes superior to state-of-the-art classical and data-driven techniques for inverse problems, especially with severely ill-posed forward operators (such as in limited-angle tomography).

Abstract. Motivated by the trade-off between noise robustness and data consistency for joint three-imensional (3D) map reconstruction and rotation estimation in single particle cryogenic-electron microscopy (Cryo-EM), we propose ellipsoidal support lifting (ESL), a measure-based lifting scheme for regularizing and approximating the global minimizer of a smooth function over a Riemannian manifold. Under a uniqueness assumption on the minimizer we show several theoretical results, in particular well-posedness of the method and an error bound due to the induced bias with respect to the global minimizer. Additionally, we use the developed theory to integrate the measure-based lifting scheme into an alternating update method for joint homogeneous 3D map reconstruction and rotation estimation, where typically tens of thousands of manifold-valued minimization problems have to be solved and where regularization is necessary because of the high noise levels in the data. The joint recovery method is used to test both the theoretical predictions and algorithmic performance through numerical experiments with Cryo-EM data. In particular, the induced bias due to the regularizing effect of ESL empirically estimates better rotations, i.e., rotations closer to the ground truth, than global optimization would.

This work presents an approach for image reconstruction in clinical low-dose tomography that combines principles from sparse signal processing with ideas from deep learning. First, we describe sparse signal representation in terms of dictionaries from a statistical perspective and interpret dictionary learning as a process of aligning the distribution that arises from a generative model with the empirical distribution of true signals. As a result, we can see that sparse coding with learned dictionaries resembles a specific variational autoencoder, where the encoder is a sparse coding algorithm and the decoder is a linear function. Next, we show that dictionary learning can also benefit from computational advancements introduced in the context of deep learning, such as parallelism and stochastic optimization. Finally, we show that regularization by dictionaries achieves competitive performance in computed tomography reconstruction compared to state-of-the-art model-based and data-driven approaches, while being unsupervised with respect to tomographic data.

We propose a new approach for learning end-to-end reconstruction operators based on unpaired training data for ill-posed inverse problems. The proposed method combines the classical variational framework with iterative unrolling and essentially seeks to minimize a weighted combination of the expected distortion in the measurement space and the Wasserstein-1 distance between the distributions of the reconstruction and the ground-truth. More specifically, the regularizer in the variational setting is parametrized by a deep neural network and learned simultaneously with the unrolled reconstruction operator. The variational problem is then initialized with the output of the reconstruction network and solved iteratively till convergence. Notably, it takes significantly fewer iterations to converge as compared to variational methods, thanks to the excellent initialization obtained via the unrolled operator. The resulting approach combines the computational efficiency of end-to-end unrolled reconstruction with the well-posedness and noise-stability guarantees of the variational setting. Moreover, we demonstrate with the example of image reconstruction in X-ray computed tomography (CT) that our approach outperforms state-of-the-art unsupervised methods and that it outperforms or is at least on par with state-of-the-art supervised data-driven reconstruction approaches.

Microlocal analysis provides deep insight into singularity structures and is often crucial for solving inverse problems, predominately, in imaging sciences. Of particular importance is the analysis of wavefront sets and the correct extraction of those. In this paper, we introduce the first algorithmic approach to extract the wavefront set of images, which combines data-based and model-based methods. Based on a celebrated property of the shearlet transform to unravel information on the wavefront set, we extract the wavefront set of an image by first applying a discrete shearlet transform and then feeding local patches of this transform to a deep convolutional neural network trained on labeled data. The resulting algorithm outperforms all competing algorithms in edge-orientation and ramp-orientation detection.

We propose a new variational model for joint image reconstruction and motion estimation applicable to spatiotemporal imaging, which is investigated along a general framework that we present with shape theory. This model consists of two parts, one that conducts modified image reconstruction in a static setting and the other that estimates the motion by sequentially indirect image registration. For the latter, we generalize the large deformation diffeomorphic metric mapping framework into the sequentially indirect registration setting. The proposed model is compared theoretically against alternative approaches (optical flow based model and diffeomorphic motion models), and we demonstrate that the proposed model has desirable properties in terms of the optimal solution. The theoretical derivations and efficient algorithms are also presented for a time-discretized scenario of the proposed model, which show that the optimal solution of the time-discretized version is consistent with that of the time-continuous one, and most of the computational components are the easily implemented linearized deformations. The complexity of the algorithm is analyzed as well. This work is concluded by some numerical examples in two-dimensional space + time tomography with very sparse and/or highly noisy data.

The task of separating an image into distinct components that represent different features plays an important role in many applications. Traditionally, such separation techniques are applied once the image in question has been reconstructed from measured data. We propose an efficient iterative algorithm, where reconstruction is performed jointly with the task of separation. A key assumption is that the image components have different sparse representations. The algorithm is based on a scheme that minimizes a functional composed of a data discrepancy term and the l1-norm of the coefficients of the different components with respect to their corresponding dictionaries. The performance is demonstrated for joint 2D deconvolution and separation into curve- and point-like components, and tests are performed on synthetic data as well as experimental stimulated emission depletion and confocal microscopy data. Experiments show that such a joint approach outperforms a sequential approach, where one first deconvolves data and then applies image separation.

Inverse Problems in medical imaging and computer vision are traditionally solved using purely model-based methods. Among those variational regularization models are one of the most popular approaches. We propose a new framework for applying data-driven approaches to inverse problems, using a neural network as a regularization functional. The network learns to discriminate between the distribution of ground truth images and the distribution of unregularized reconstructions. Once trained, the network is applied to the inverse problem by solving the corresponding variational problem. Unlike other data-based approaches for inverse problems, the algorithm can be applied even if only unsupervised training data is available. Experiments demonstrate the potential of the framework for denoising on the BSDS dataset and for computer tomography reconstruction on the LIDC dataset.

This paper adapts the large deformation diffeomorphic metric mapping framework for image registration to the indirect setting, where a template is registered against a target that is given through indirect noisy observations. The registration uses diffeomorphisms that transform the template through a (group) action. These diffeomorphisms are generated by solving a flow equation that is defined by a velocity field with certain regularity. The theoretical analysis includes a proof that indirect image registration has solutions (existence) that are stable and that converge as the data error tends to zero, so it becomes a well-defined regularization method. The paper concludes with examples of indirect image registration in 2D tomography with very sparse and/or highly noisy data.

We propose the Learned Primal-Dual algorithm for tomographic reconstruction. The algorithm accounts for a (possibly non-linear) forward operator in a deep neural network by unrolling a proximal primal-dual optimization method, but where the proximal operators have been replaced with convolutional neural networks. The algorithm is trained end-to-end, working directly from raw measured data and it does not depend on any initial reconstruction such as filtered back-projection (FBP). We compare performance of the proposed method on low dose computed tomography reconstruction against FBP, total variation (TV), and deep learning based post-processing of FBP. For the Shepp-Logan phantom we obtain >6 dB peak signal to noise ratio improvement against all compared methods. For human phantoms the corresponding improvement is 6.6 dB over TV and 2.2 dB over learned post-processing along with a substantial improvement in the structural similarity index. Finally, our algorithm involves only ten forward-back-projection computations, making the method feasible for time critical clinical applications.

We introduce a tomographic reconstruction method implemented using a shape-based regularization technique. Spatial models of known features in the structure being reconstructed are integrated into the reconstruction process as regularizers. Our regularization scheme is driven locally through shape information obtained from segmentation and compared with a known spatial model. We demonstrated our method on tomography data from digital phantoms, simulated data, and experimental electron tomography (ET) data of virus complexes. Our reconstruction showed reduced blurring and an improvement in the resolution of the reconstructed volume was also measured. This method also produced improved demarcation of spike boundaries in viral membranes when compared with popular techniques like weighted back projection and the algebraic reconstruction technique. Improved ET reconstructions will provide better structure elucidation and improved feature visualization, which can aid in solving key biological issues. Our method can also be generalized to other tomographic modalities.