arXiv subjects

Simon Arridge

Publications and source records attributed to Simon Arridge.

At least 37 records · Page 2Linked to original sources

arXiv2020

Quantifying Sources of Uncertainty in Deep Learning-Based Image Reconstruction

Image reconstruction methods based on deep neural networks have shown outstanding performance, equalling or exceeding the state-of-the-art results of conventional approaches, but often do not provide uncertainty information about the reconstruction. In this work we propose a scalable and efficient framework to simultaneously quantify aleatoric and epistemic uncertainties in learned iterative image reconstruction. We build on a Bayesian deep gradient descent method for quantifying epistemic uncertainty, and incorporate the heteroscedastic variance of the noise to account for the aleatoric uncertainty. We show that our method exhibits competitive performance against conventional benchmarks for computed tomography with both sparse view and limited angle data. The estimated uncertainty captures the variability in the reconstructions, caused by the restricted measurement model, and by missing information, due to the limited angle geometry.

cs.CV↗

arXiv2020

Penalized PET/CT Reconstruction Algorithms with Automatic Realignment for Anatomical Priors

Two algorithms for solving misalignment issues in penalized PET/CT reconstruction using anatomical priors are proposed. Both approaches are based on a recently published joint motion estimation and image reconstruction method. The first approach deforms the anatomical image to align it with the functional one while the second approach deforms both images to align them with the measured data. Our current implementation alternates between image reconstruction and alignment estimation. To evaluate the potential of these approaches, we have chosen Parallel Level Sets (PLS) as a representative anatomical penalty, incorporating a spatially-variant penalty strength to achieve uniform local contrast. The performance was evaluated using simulated non-TOF data generated with an XCAT phantom in the thorax region. We used the attenuation image in the anatomical prior. The results demonstrated that both methods can estimate the misalignment and deform the anatomical image accordingly. However, the performance of the first approach depends highly on the workflow of the alternating process. The second approach shows a faster convergence rate to the correct alignment and is less sensitive to the workflow. Interestingly, the presence of anatomical information can improve the convergence rate of misalignment estimation for the second approach but slow it down for the first approach.

physics.med-ph↗

arXiv2020

On Learned Operator Correction in Inverse Problems

We discuss the possibility to learn a data-driven explicit model correction for inverse problems and whether such a model correction can be used within a variational framework to obtain regularised reconstructions. This paper discusses the conceptual difficulty to learn such a forward model correction and proceeds to present a possible solution as forward-adjoint correction that explicitly corrects in both data and solution spaces. We then derive conditions under which solutions to the variational problem with a learned correction converge to solutions obtained with the correct operator. The proposed approach is evaluated on an application to limited view photoacoustic tomography and compared to the established framework of Bayesian approximation error method.

math.NA↗

arXiv2020

Quantifying Model Uncertainty in Inverse Problems via Bayesian Deep Gradient Descent

Recent advances in reconstruction methods for inverse problems leverage powerful data-driven models, e.g., deep neural networks. These techniques have demonstrated state-of-the-art performances for several imaging tasks, but they often do not provide uncertainty on the obtained reconstruction. In this work, we develop a scalable, data-driven, knowledge-aided computational framework to quantify the model uncertainty via Bayesian neural networks. The approach builds on, and extends deep gradient descent, a recently developed greedy iterative training scheme, and recasts it within a probabilistic framework. Scalability is achieved by being hybrid in the architecture: only the last layer of each block is Bayesian, while the others remain deterministic, and by being greedy in training. The framework is showcased on one representative medical imaging modality, viz. computed tomography with either sparse view or limited view data, and exhibits competitive performance with respect to state-of-the-art benchmarks, e.g., total variation, deep gradient descent and learned primal-dual.

cs.CV↗

arXiv2020

Representation and reconstruction of covariance operators in linear inverse problems

We introduce a framework for the reconstruction and representation of functions in a setting where these objects cannot be directly observed, but only indirect and noisy measurements are available, namely an inverse problem setting. The proposed methodology can be applied either to the analysis of indirectly observed functional images or to the associated covariance operators, representing second-order information, and thus lying on a non-Euclidean space. To deal with the ill-posedness of the inverse problem, we exploit the spatial structure of the sample data by introducing a flexible regularizing term embedded in the model. Thanks to its efficiency, the proposed model is applied to MEG data, leading to a novel approach to the investigation of functional connectivity.

stat.ME↗

arXiv2020

Efficient inversion strategies for estimating optical properties with Monte Carlo radiative transport models

Indirect imaging problems in biomedical optics generally require repeated evaluation of forward models of radiative transport, for which Monte Carlo is accurate yet computationally costly. We develop a novel approach to reduce this bottleneck which has significant implications for quantitative tomographic imaging in a variety of medical and industrial applications. Using Monte Carlo we compute a fully stochastic gradient of an objective function for a given imaging problem. Leveraging techniques from the machine learning community we then adaptively control the accuracy of this gradient throughout the iterative inversion scheme, in order to substantially reduce computational resources at each step. For example problems of Quantitative Photoacoustic Tomography and Ultrasound Modulated Optical Tomography, we demonstrate that solutions are attainable using a total computational expense that is comparable to (or less than) that which is required for a single high accuracy forward run of the same Monte Carlo model. This approach demonstrates significant computational savings when approaching the full non-linear inverse problem of optical property estimation using stochastic methods.

physics.comp-ph↗

arXiv2020

Joint Reconstruction and Low-Rank Decomposition for Dynamic Inverse Problems

A primary interest in dynamic inverse problems is to identify the underlying temporal behaviour of the system from outside measurements. In this work we consider the case, where the target can be represented by a decomposition of spatial and temporal basis functions and hence can be efficiently represented by a low-rank decomposition. We then propose a joint reconstruction and low-rank decomposition method based on the Nonnegative Matrix Factorisation to obtain the unknown from highly undersampled dynamic measurement data. The proposed framework allows for flexible incorporation of separate regularisers for spatial and temporal features. For the special case of a stationary operator, we can effectively use the decomposition to reduce the computational complexity and obtain a substantial speed-up. The proposed methods are evaluated for two simulated phantoms and we compare the obtained results to a separate low-rank reconstruction and subsequent decomposition approach based on the widely used principal component analysis.

math.NA↗

arXiv2020

Multi-Scale Learned Iterative Reconstruction

Model-based learned iterative reconstruction methods have recently been shown to outperform classical reconstruction algorithms. Applicability of these methods to large scale inverse problems is however limited by the available memory for training and extensive training times, the latter due to computationally expensive forward models. As a possible solution to these restrictions we propose a multi-scale learned iterative reconstruction scheme that computes iterates on discretisations of increasing resolution. This procedure does not only reduce memory requirements, it also considerably speeds up reconstruction and training times, but most importantly is scalable to large scale inverse problems with non-trivial forward operators, such as those that arise in many 3D tomographic applications. In particular, we propose a hybrid network that combines the multi-scale iterative approach with a particularly expressive network architecture which in combination exhibits excellent scalability in 3D. Applicability of the algorithm is demonstrated for 3D cone beam computed tomography from real measurement data of an organic phantom. Additionally, we examine scalability and reconstruction quality in comparison to established learned reconstruction methods in two dimensions for low dose computed tomography on human phantoms.

eess.IV↗

arXiv2019

Rapid Whole-Heart CMR with Single Volume Super-resolution

Background: Three-dimensional, whole heart, balanced steady state free precession (WH-bSSFP) sequences provide delineation of intra-cardiac and vascular anatomy. However, they have long acquisition times. Here, we propose significant speed ups using a deep learning single volume super resolution reconstruction, to recover high resolution features from rapidly acquired low resolution WH-bSSFP images. Methods: A 3D residual U-Net was trained using synthetic data, created from a library of high-resolution WH-bSSFP images by simulating 0.5 slice resolution and 0.5 phase resolution. The trained network was validated with synthetic test data, as well as prospective low-resolution data. Results: Synthetic low-resolution data had significantly better image quality after super-resolution reconstruction. Qualitative image scores showed super-resolved images had better edge sharpness, fewer residual artefacts and less image distortion than low-resolution images, with similar scores to high-resolution data. Quantitative image scores showed super-resolved images had significantly better edge sharpness than low-resolution or high-resolution images, with significantly better signal-to-noise ratio than high-resolution data. Vessel diameters measurements showed over-estimation in the low-resolution measurements, compared to the high-resolution data. No significant differences and no bias was found in the super-resolution measurements. Conclusion: This paper demonstrates the potential of using a residual U-Net for super-resolution reconstruction of rapidly acquired low-resolution whole heart bSSFP data within a clinical setting. The resulting network can be applied very quickly, making these techniques particularly appealing within busy clinical workflow. Thus, we believe that this technique may help speed up whole heart CMR in clinical practice.

eess.IV↗

arXiv2019

Expectation Propagation for Poisson Data

The Poisson distribution arises naturally when dealing with data involving counts, and it has found many applications in inverse problems and imaging. In this work, we develop an approximate Bayesian inference technique based on expectation propagation for approximating the posterior distribution formed from the Poisson likelihood function and a Laplace type prior distribution, e.g., the anisotropic total variation prior. The approach iteratively yields a Gaussian approximation, and at each iteration, it updates the Gaussian approximation to one factor of the posterior distribution by moment matching. We derive explicit update formulas in terms of one-dimensional integrals, and also discuss stable and efficient quadrature rules for evaluating these integrals. The method is showcased on two-dimensional PET images.

math.NA↗

arXiv2018

Networks for Nonlinear Diffusion Problems in Imaging

A multitude of imaging and vision tasks have seen recently a major transformation by deep learning methods and in particular by the application of convolutional neural networks. These methods achieve impressive results, even for applications where it is not apparent that convolutions are suited to capture the underlying physics. In this work we develop a network architecture based on nonlinear diffusion processes, named DiffNet. By design, we obtain a nonlinear network architecture that is well suited for diffusion related problems in imaging. Furthermore, the performed updates are explicit, by which we obtain better interpretability and generalisability compared to classical convolutional neural network architectures. The performance of DiffNet tested on the inverse problem of nonlinear diffusion with the Perona-Malik filter on the STL-10 image dataset. We obtain competitive results to the established U-Net architecture, with a fraction of parameters and necessary training data.

cs.CV↗

arXiv2018

Approximate k-space models and Deep Learning for fast photoacoustic reconstruction

We present a framework for accelerated iterative reconstructions using a fast and approximate forward model that is based on k-space methods for photoacoustic tomography. The approximate model introduces aliasing artefacts in the gradient information for the iterative reconstruction, but these artefacts are highly structured and we can train a CNN that can use the approximate information to perform an iterative reconstruction. We show feasibility of the method for human in-vivo measurements in a limited-view geometry. The proposed method is able to produce superior results to total variation reconstructions with a speed-up of 32 times.

cs.CV↗

arXiv2018

Enhancing Compressed Sensing 4D Photoacoustic Tomography by Simultaneous Motion Estimation

A crucial limitation of current high-resolution 3D photoacoustic tomography (PAT) devices that employ sequential scanning is their long acquisition time. In previous work, we demonstrated how to use compressed sensing techniques to improve upon this: images with good spatial resolution and contrast can be obtained from suitably sub-sampled PAT data acquired by novel acoustic scanning systems if sparsity-constrained image reconstruction techniques such as total variation regularization are used. Now, we show how a further increase of image quality can be achieved for imaging dynamic processes in living tissue (4D PAT). The key idea is to exploit the additional temporal redundancy of the data by coupling the previously used spatial image reconstruction models with sparsity-constrained motion estimation models. While simulated data from a two-dimensional numerical phantom will be used to illustrate the main properties of this recently developed joint-image-reconstruction-and-motion-estimation framework, measured data from a dynamic experimental phantom will also be used to demonstrate their potential for challenging, large-scale, real-world, three-dimensional scenarios. The latter only becomes feasible if a carefully designed combination of tailored optimization schemes is employed, which we describe and examine in more detail.

math.NA↗

arXiv2018

Real-time Cardiovascular MR with Spatio-temporal Artifact Suppression using Deep Learning - Proof of Concept in Congenital Heart Disease

PURPOSE: Real-time assessment of ventricular volumes requires high acceleration factors. Residual convolutional neural networks (CNN) have shown potential for removing artifacts caused by data undersampling. In this study we investigated the effect of different radial sampling patterns on the accuracy of a CNN. We also acquired actual real-time undersampled radial data in patients with congenital heart disease (CHD), and compare CNN reconstruction to Compressed Sensing (CS). METHODS: A 3D (2D plus time) CNN architecture was developed, and trained using 2276 gold-standard paired 3D data sets, with 14x radial undersampling. Four sampling schemes were tested, using 169 previously unseen 3D 'synthetic' test data sets. Actual real-time tiny Golden Angle (tGA) radial SSFP data was acquired in 10 new patients (122 3D data sets), and reconstructed using the 3D CNN as well as a CS algorithm; GRASP. RESULTS: Sampling pattern was shown to be important for image quality, and accurate visualisation of cardiac structures. For actual real-time data, overall reconstruction time with CNN (including creation of aliased images) was shown to be more than 5x faster than GRASP. Additionally, CNN image quality and accuracy of biventricular volumes was observed to be superior to GRASP for the same raw data. CONCLUSION: This paper has demonstrated the potential for the use of a 3D CNN for deep de-aliasing of real-time radial data, within the clinical setting. Clinical measures of ventricular volumes using real-time data with CNN reconstruction are not statistically significantly different from the gold-standard, cardiac gated, BH techniques.

cs.CV↗

arXiv2018

Model based learning for accelerated, limited-view 3D photoacoustic tomography

Recent advances in deep learning for tomographic reconstructions have shown great potential to create accurate and high quality images with a considerable speed-up. In this work we present a deep neural network that is specifically designed to provide high resolution 3D images from restricted photoacoustic measurements. The network is designed to represent an iterative scheme and incorporates gradient information of the data fit to compensate for limited view artefacts. Due to the high complexity of the photoacoustic forward operator, we separate training and computation of the gradient information. A suitable prior for the desired image structures is learned as part of the training. The resulting network is trained and tested on a set of segmented vessels from lung CT scans and then applied to in-vivo photoacoustic measurement data.

cs.CV↗

arXiv2017

Variational Gaussian Approximation for Poisson Data

The Poisson model is frequently employed to describe count data, but in a Bayesian context it leads to an analytically intractable posterior probability distribution. In this work, we analyze a variational Gaussian approximation to the posterior distribution arising from the Poisson model with a Gaussian prior. This is achieved by seeking an optimal Gaussian distribution minimizing the Kullback-Leibler divergence from the posterior distribution to the approximation, or equivalently maximizing the lower bound for the model evidence. We derive an explicit expression for the lower bound, and show the existence and uniqueness of the optimal Gaussian approximation. The lower bound functional can be viewed as a variant of classical Tikhonov regularization that penalizes also the covariance. Then we develop an efficient alternating direction maximization algorithm for solving the optimization problem, and analyze its convergence. We discuss strategies for reducing the computational complexity via low rank structure of the forward operator and the sparsity of the covariance. Further, as an application of the lower bound, we discuss hierarchical Bayesian modeling for selecting the hyperparameter in the prior distribution, and propose a monotonically convergent algorithm for determining the hyperparameter. We present extensive numerical experiments to illustrate the Gaussian approximation and the algorithms.

math.NA↗

arXiv2017

Fast Estimation of Haemoglobin Concentration in Tissue Via Wavelet Decomposition

Tissue oxygenation and perfusion can be an indicator for organ viability during minimally invasive surgery, for example allowing real-time assessment of tissue perfusion and oxygen saturation. Multispectral imaging is an optical modality that can inspect tissue perfusion in wide field images without contact. In this paper, we present a novel, fast method for using RGB images for MSI, which while limiting the spectral resolution of the modality allows normal laparoscopic systems to be used. We exploit the discrete Haar decomposition to separate individual video frames into low pass and directional coefficients and we utilise a different multispectral estimation technique on each. The increase in speed is achieved by using fast Tikhonov regularisation on the directional coefficients and more accurate Bayesian estimation on the low pass component. The pipeline is implemented using a graphics processing unit (GPU) architecture and achieves a frame rate of approximately 15Hz. We validate the method on animal models and on human data captured using a da Vinci stereo laparoscope.

cs.CV↗

arXiv2017

Inference of Haemoglobin Concentration From Stereo RGB

Multispectral imaging (MSI) can provide information about tissue oxygenation, perfusion and potentially function during surgery. In this paper we present a novel, near real-time technique for intrinsic measurements of total haemoglobin (THb) and blood oxygenation (SO2) in tissue using only RGB images from a stereo laparoscope. The high degree of spectral overlap between channels makes inference of haemoglobin concentration challenging, non-linear and under constrained. We decompose the problem into two constrained linear sub-problems and show that with Tikhonov regularisation the estimation significantly improves, giving robust estimation of the Thb. We demonstrate by using the co-registered stereo image data from two cameras it is possible to get robust SO2 estimation as well. Our method is closed from, providing computational efficiency even with multiple cameras. The method we present requires only spectral response calibration of each camera, without modification of existing laparoscopic imaging hardware. We validate our technique on synthetic data from Monte Carlo simulation % of light transport through soft tissue containing submerged blood vessels and further, in vivo, on a multispectral porcine data set.

cs.CV↗