Spatially-Adaptive Reconstruction in Computed Tomography Using Neural Networks

Dose reduction in dynamic synaptic vesicle glycoprotein 2A PET imaging using artificial neural networks

Objective. Reducing dose in positron emission tomography (PET) imaging increases noise in reconstructed dynamic frames, which inevitably results in higher noise and possible bias in subsequently estimated images of kinetic parameters than those estimated in the standard dose case. We report the development of a spatiotemporal denoising technique for reduced-count dynamic frames through integrating a cascade artificial neural network (ANN) with the highly constrained back-projection (HYPR) scheme to improve low-dose parametric imaging.Approach. We implemented and assessed the proposed method using imaging data acquired with11C-UCB-J, a PET radioligand bound to synaptic vesicle glycoprotein 2A (SV2A) in the human brain. The patch-based ANN was trained with a reduced-count frame and its full-count correspondence of a subject and was used in cascade to process dynamic frames of other subjects to further take advantage of its denoising capability. The HYPR strategy was then applied to the spatial ANN processed image frames to make use of the temporal information from the entire dynamic scan.Main results. In all the testing subjects including healthy volunteers and Parkinson's disease patients, the proposed method reduced more noise while introducing minimal bias in dynamic frames and the resulting parametric images, as compared with conventional denoising methods.Significance. Achieving 80% noise reduction with a bias of -2% in dynamic frames, which translates into 75% and 70% of noise reduction in the tracer uptake (bias, -2%) and distribution volume (bias, -5%) images, the proposed ANN+HYPR technique demonstrates the denoising capability equivalent to a 11-fold dose increase for dynamic SV2A PET imaging with11C-UCB-J.

Imaging inside highly scattering media using hybrid deep learning and analytical algorithm

Imaging through highly scattering media is a challenging problem with numerous applications in biomedical and remote-sensing fields. Existing methods that use analytical or deep learning tools are limited by simplified forward models or a requirement for prior physical knowledge, resulting in blurry images or a need for large training databases. To address these limitations, we propose a hybrid scheme called Hybrid-DOT that combines analytically derived image estimates with a deep learning network. Our analysis demonstrates that Hybrid-DOT outperforms a state-of-the-art ToF-DOT algorithm by improving the PSNR ratio by 4.6 dB and reducing the resolution by a factor of 2.5. Furthermore, when compared to a deep learning stand-alone model, Hybrid-DOT achieves a 0.8 dB increase in PSNR, 1.5 times the resolution, and a significant reduction in the required dataset size (factor of 1.6-3). The proposed model remains effective at higher depths, providing similar improvements for up to 160 mean-free paths.

ADMM-SVNet: An ADMM-Based Sparse-View CT Reconstruction Network

In clinical medical applications, sparse-view computed tomography (CT) imaging is an effective method for reducing radiation doses. The iterative reconstruction method is usually adopted for sparse-view CT. In the process of optimizing the iterative model, the approach of directly solving the quadratic penalty function of the objective function can be expected to perform poorly. Compared with the direct solution method, the alternating direction method of multipliers (ADMM) algorithm can avoid the ill-posed problem associated with the quadratic penalty function. However, the regularization items, sparsity transform, and parameters in the traditional ADMM iterative model need to be manually adjusted. In this paper, we propose a data-driven ADMM reconstruction method that can automatically optimize the above terms that are difficult to choose within an iterative framework. The main contribution of this paper is that a modified U-net represents the sparse transformation, and the prior information and related parameters are automatically trained by the network. Based on a comparison with other state-of-the-art reconstruction algorithms, the qualitative and quantitative results show the effectiveness of our method for sparse-view CT image reconstruction. The experimental results show that the proposed method performs well in streak artifact elimination and detail structure preservation. The proposed network can deal with a wide range of noise levels and has exceptional performance in low-dose reconstruction tasks.

Improving Diagnostic Accuracy in Low-Dose SPECT Myocardial Perfusion Imaging With Convolutional Denoising Networks

Lowering the administered dose in SPECT myocardial perfusion imaging (MPI) has become an important clinical problem. In this study we investigate the potential benefit of applying a deep learning (DL) approach for suppressing the elevated imaging noise in low-dose SPECT-MPI studies. We adopt a supervised learning approach to train a neural network by using image pairs obtained from full-dose (target) and low-dose (input) acquisitions of the same patients. In the experiments, we made use of acquisitions from 1,052 subjects and demonstrated the approach for two commonly used reconstruction methods in clinical SPECT-MPI: 1) filtered backprojection (FBP), and 2) ordered-subsets expectation-maximization (OSEM) with corrections for attenuation, scatter and resolution. We evaluated the DL output for the clinical task of perfusion-defect detection at a number of successively reduced dose levels (1/2, 1/4, 1/8, 1/16 of full dose). The results indicate that the proposed DL approach can achieve substantial noise reduction and lead to improvement in the diagnostic accuracy of low-dose data. In particular, at 1/2 dose, DL yielded an area-under-the-ROC-curve (AUC) of 0.799, which is nearly identical to the AUC = 0.801 obtained by OSEM at full-dose ( p -value = 0.73); similar results were also obtained for FBP reconstruction. Moreover, even at 1/8 dose, DL achieved AUC = 0.770 for OSEM, which is above the AUC = 0.755 obtained at full-dose by FBP. These results indicate that, compared to conventional reconstruction filtering, DL denoising can allow for additional dose reduction without sacrificing the diagnostic accuracy in SPECT-MPI.

Improved myocardial perfusion PET imaging using artificial neural networks

Myocardial perfusion (MP) PET imaging plays a key role in risk assessment and stratification of patients with coronary artery disease. In this work, we proposed a patch-based artificial neural network (ANN) fusion approach that integrates information from the ML and the post-smoothed ML reconstruction to improve MP PET imaging. The proposed method was applied to images reconstructed from different noise levels to enhance quantification and task-based MP defect detection. Using the XCAT phantom, we simulated three MP PET imaging cases, one with normal perfusion and the other two with non-transmural and transmural regionally reduced perfusion of the left ventricular (LV) myocardium. The proposed ANN fusion technique was quantitatively evaluated in terms of the noise versus bias and noise versus contrast tradeoff, and compared with the post-smoothed ML reconstruction. Using the channelized Hotelling observer, we evaluated the detectability of the non-transmural and transmural defects through the receiver operating characteristic analysis. The quantitative results demonstrated that the ANN enhancement method reduced bias and improved contrast while reaching comparable noise to what the post-smoothed ML reconstruction achieved. Moreover, the ANN fusion technique significantly improved the defect detectability of both the non-transmural and transmural defects. In addition to the simulation study, we further evaluated the proposed method using patient data. Compared with the post-smoothed ML reconstruction, the ANN fusion improved the tradeoff between noise and the mean value on the LV myocardium, indicating its potential clinical application in MP PET imaging.

A Comprehensive Review on Nature Inspired Neural Network based Adaptive Filter for Eliminating Noise in Medical Images

BACKGROUND

Various kind of medical imaging modalities are available for providing noninvasive view and for analyzing any pathological symptoms of human beings. Different noise may appear in those modalities at the time of acquisition, transmission, scanning, or at the time of storing. The removal of noises from the digital medical images without losing any inherent features is always considered a challenging task because a successful diagnosis relies on them. Numerous techniques have been proposed to fulfill this objective, and each having their own benefits and limitations.

DISCUSSION

In this comprehensive review article, more than 65 research articles are investigated to illustrate the applications of Artificial Neural Networks (ANN) in the field of biomedical image denoising. In particular, the zest of this article is to highlight the hybridized filtering model using nature-inspired algorithms and artificial neural networks for suppression of noise. Various other techniques, such as fixed filter, linear adaptive filters and gradient descent learning based neural network filter are also included.

CONCLUSION

This article envisages how to train ANN using derivative free nature-inspired algorithms, and its performance in various medical images modalities and noise conditions.

Deep learning based image reconstruction algorithm for limited-angle translational computed tomography

As a low-end computed tomography (CT) system, translational CT (TCT) is in urgent demand in developing countries. Under some circumstances, in order to reduce the scan time, decrease the X-ray radiation or scan long objects, furthermore, to avoid the inconsistency of the detector for the large angle scanning, we use the limited-angle TCT scanning mode to scan an object within a limited angular range. However, this scanning mode introduces some additional noise and limited-angle artifacts that seriously degrade the imaging quality and affect the diagnosis accuracy. To reconstruct a high-quality image for the limited-angle TCT scanning mode, we develop a limited-angle TCT image reconstruction algorithm based on a U-net convolutional neural network (CNN). First, we use the SART method to the limited-angle TCT projection data, then we import the image reconstructed by SART method to a well-trained CNN which can suppress the artifacts and preserve the structures to obtain a better reconstructed image. Some simulation experiments are implemented to demonstrate the performance of the developed algorithm for the limited-angle TCT scanning mode. Compared with some state-of-the-art methods, the developed algorithm can effectively suppress the noise and the limited-angle artifacts while preserving the image structures.

ADMM-based deep reconstruction for limited-angle CT

In the real applications of computed tomography (CT) imaging, the projection data of the scanned objects are usually acquired within a limited-angle range because of the limitation of the scanning condition. Under these circumstances, conventional analytical algorithms, such as filtered back-projection (FBP), do not work because the projection data are incomplete. The regularization method has proven to be effective for tomographic reconstruction from under-sampled measurements. To deal with the limited-angle CT reconstruction problem, the regularization method is commonly used, but it is difficult to find a generic regularization term and choose the regularization parameters. Moreover, in some cases, the quality of reconstructed images is less than satisfactory. To solve this problem, we developed an alternating direction method of multipliers (ADMM)-based deep reconstruction (ADMMBDR) algorithm for limited-angle CT. First, we used the ADMM algorithm to decompose a regularization reconstruction model. Then, we utilized a deep convolutional neural network (CNN) to replace a part of the ADMM algorithm to reduce artifacts and avoid the choice of the regularization term and the regularization parameter. Furthermore, we conducted some numerical experiments to evaluate the feasibility and the advantages of the proposed algorithm. The results showed that the proposed algorithm had a better performance than several state-of-the-art algorithms; with respect to structure preservation and artifact reduction.

Rapid compositional mapping of knee cartilage with compressed sensing MRI

More than a decade after the introduction of compressed sensing (CS) in MRI, researchers are still working on ways to translate it into different research and clinical applications. The greatest advantage of CS in MRI is the reduced amount of k-space data needed to reconstruct images, which can be exploited to reduce scan time or to improve spatial resolution and volumetric coverage. Efficient data acquisition using CS is extremely important for compositional mapping of the musculoskeletal system in general and knee cartilage mapping techniques in particular. High-resolution quantitative information about tissue biochemical composition could be obtained in just a few minutes using CS MRI. However, in order to make this goal a reality, some issues still need to be addressed. In this article we review the current state of the art of CS methods for rapid compositional mapping of knee cartilage. Specifically, data acquisition strategies, image reconstruction algorithms, and data fitting models are discussed. Different CS studies for T2 and T1ρ mapping of knee cartilage are reviewed, with illustrative results. Future directions, opportunities, and challenges of rapid compositional mapping techniques are also discussed. Level of Evidence: 4 Technical Efficacy: Stage 6 J. Magn. Reson. Imaging 2018;47:1185-1198.

Improving Tomographic Reconstruction from Limited Data Using Mixed-Scale Dense Convolutional Neural Networks

In many applications of tomography, the acquired data are limited in one or more ways due to unavoidable experimental constraints. In such cases, popular direct reconstruction algorithms tend to produce inaccurate images, and more accurate iterative algorithms often have prohibitively high computational costs. Using machine learning to improve the image quality of direct algorithms is a recently proposed alternative, for which promising results have been shown. However, previous attempts have focused on using encoder–decoder networks, which have several disadvantages when applied to large tomographic images, preventing wide application in practice. Here, we propose the use of the Mixed-Scale Dense convolutional neural network architecture, which was specifically designed to avoid these disadvantages, to improve tomographic reconstruction from limited data. Results are shown for various types of data limitations and object types, for both simulated data and large-scale real-world experimental data. The results are compared with popular tomographic reconstruction algorithms and machine learning algorithms, showing that Mixed-Scale Dense networks are able to significantly improve reconstruction quality even with severely limited data, and produce more accurate results than existing algorithms.

Limited-view CT Reconstruction Based on Autoencoder-like Generative Adversarial Networks with Joint Loss

Limiting the scan views of X-ray computed tomography (CT) can make radiation dose reduced efficiently and consequently weaken the damage of ionizing radiation. However, it will degrade the reconstructed CT images. In this paper, we proposed to predict the missing projections and improve the reconstructed CT images by constructing an autoencoder-like generative adversarial network (GAN) with joint loss function. In the generator network, we train an autoencoder-like convolutional neural network (CNN) to generate the missing projections given a sinogram of the limited-view CT projections. For the discriminator network, a CNN is used to classify an input sinogram as real or synthetic one. To produce more realistic images, the joint loss function which includes not only reconstruction loss, but the adversarial loss is employed. While reconstruction loss can capture the overall structure of the missing projections, the latter can pick a particular mode from the distribution and make the results much sharper. After the missing projections have been estimated, we reconstruct the CT images from the completed projections by utilizing conventional filtered back-projection (FBP) method. The experiments prove the capability of our method to achieve a considerable improvement in limited-view CT reconstruction.

Artificial Neural Network Enhanced Bayesian PET Image Reconstruction

In positron emission tomography (PET) image reconstruction, the Bayesian framework with various regularization terms has been implemented to constrain the radio tracer distribution. Varying the regularizing weight of a maximum a posteriori (MAP) algorithm specifies a lower bound of the tradeoff between variance and spatial resolution measured from the reconstructed images. The purpose of this paper is to build a patch-based image enhancement scheme to reduce the size of the unachievable region below the bound and thus to quantitatively improve the Bayesian PET imaging. We cast the proposed enhancement as a regression problem which models a highly nonlinear and spatial-varying mapping between the reconstructed image patches and an enhanced image patch. An artificial neural network model named multilayer perceptron (MLP) with backpropagation was used to solve this regression problem through learning from examples. Using the BrainWeb phantoms, we simulated brain PET data at different count levels of different subjects with and without lesions. The MLP was trained using the image patches reconstructed with a MAP algorithm of different regularization parameters for one normal subject at a certain count level. To evaluate the performance of the trained MLP, reconstructed images from other simulations and two patient brain PET imaging data sets were processed. In every testing cases, we demonstrate that the MLP enhancement technique improves the noise and bias tradeoff compared with the MAP reconstruction using different regularizing weights thus decreasing the size of the unachievable region defined by the MAP algorithm in the variance/resolution plane.

Deep Convolutional Neural Network for Inverse Problems in Imaging

In this paper, we propose a novel deep convolutional neural network (CNN)-based algorithm for solving ill-posed inverse problems. Regularized iterative algorithms have emerged as the standard approach to ill-posed inverse problems in the past few decades. These methods produce excellent results, but can be challenging to deploy in practice due to factors including the high computational cost of the forward and adjoint operators and the difficulty of hyperparameter selection. The starting point of this paper is the observation that unrolled iterative methods have the form of a CNN (filtering followed by pointwise nonlinearity) when the normal operator (H*H, where H* is the adjoint of the forward imaging operator, H) of the forward model is a convolution. Based on this observation, we propose using direct inversion followed by a CNN to solve normal-convolutional inverse problems. The direct inversion encapsulates the physical model of the system, but leads to artifacts when the problem is ill posed; the CNN combines multiresolution decomposition and residual learning in order to learn to remove these artifacts while preserving image structure. We demonstrate the performance of the proposed network in sparse-view reconstruction (down to 50 views) on parallel beam X-ray computed tomography in synthetic phantoms as well as in real experimental sinograms. The proposed network outperforms total variation-regularized iterative reconstruction for the more realistic phantoms and requires less than a second to reconstruct a 512 × 512 image on the GPU.