Low-dose CT reconstruction via L1 dictionary learning regularization using iteratively reweighted least-squares

Parallel processing model for low-dose computed tomography image denoising

Low-dose computed tomography (LDCT) has gained increasing attention owing to its crucial role in reducing radiation exposure in patients. However, LDCT-reconstructed images often suffer from significant noise and artifacts, negatively impacting the radiologists' ability to accurately diagnose. To address this issue, many studies have focused on denoising LDCT images using deep learning (DL) methods. However, these DL-based denoising methods have been hindered by the highly variable feature distribution of LDCT data from different imaging sources, which adversely affects the performance of current denoising models. In this study, we propose a parallel processing model, the multi-encoder deep feature transformation network (MDFTN), which is designed to enhance the performance of LDCT imaging for multisource data. Unlike traditional network structures, which rely on continual learning to process multitask data, the approach can simultaneously handle LDCT images within a unified framework from various imaging sources. The proposed MDFTN consists of multiple encoders and decoders along with a deep feature transformation module (DFTM). During forward propagation in network training, each encoder extracts diverse features from its respective data source in parallel and the DFTM compresses these features into a shared feature space. Subsequently, each decoder performs an inverse operation for multisource loss estimation. Through collaborative training, the proposed MDFTN leverages the complementary advantages of multisource data distribution to enhance its adaptability and generalization. Numerous experiments were conducted on two public datasets and one local dataset, which demonstrated that the proposed network model can simultaneously process multisource data while effectively suppressing noise and preserving fine structures. The source code is available at https://github.com/123456789ey/MDFTN .

Systematic Review on Learning-based Spectral CT

Spectral computed tomography (CT) has recently emerged as an advanced version of medical CT and significantly improves conventional (single-energy) CT. Spectral CT has two main forms: dual-energy computed tomography (DECT) and photon-counting computed tomography (PCCT), which offer image improvement, material decomposition, and feature quantification relative to conventional CT. However, the inherent challenges of spectral CT, evidenced by data and image artifacts, remain a bottleneck for clinical applications. To address these problems, machine learning techniques have been widely applied to spectral CT. In this review, we present the state-of-the-art data-driven techniques for spectral CT.

Feature shared multi-decoder network using complementary learning for Photon counting CT ring artifact suppression

BACKGROUND

Photon-counting computed tomography (Photon counting CT) utilizes photon-counting detectors to precisely count incident photons and measure their energy. These detectors, compared to traditional energy integration detectors, provide better image contrast and material differentiation. However, Photon counting CT tends to show more noticeable ring artifacts due to limited photon counts and detector response variations, unlike conventional spiral CT.

OBJECTIVE

To comprehensively address this issue, we propose a novel feature shared multi-decoder network (FSMDN) that utilizes complementary learning to suppress ring artifacts in Photon counting CT images.

METHODS

Specifically, we employ a feature-sharing encoder to extract context and ring artifact features, facilitating effective feature sharing. These shared features are also independently processed by separate decoders dedicated to the context and ring artifact channels, working in parallel. Through complementary learning, this approach achieves superior performance in terms of artifact suppression while preserving tissue details.

RESULTS

We conducted numerous experiments on Photon counting CT images with three-intensity ring artifacts. Both qualitative and quantitative results demonstrate that our network model performs exceptionally well in correcting ring artifacts at different levels while exhibiting superior stability and robustness compared to the comparison methods.

CONCLUSIONS

In this paper, we have introduced a novel deep learning network designed to mitigate ring artifacts in Photon counting CT images. The results illustrate the viability and efficacy of our proposed network model as a new deep learning-based method for suppressing ring artifacts.

A self-supervised guided knowledge distillation framework for unpaired low-dose CT image denoising

Low-dose computed tomography (LDCT) can significantly reduce the damage of X-ray to the human body, but the reduction of CT dose will produce images with severe noise and artifacts, which will affect the diagnosis of doctors. Recently, deep learning has attracted more and more attention from researchers. However, most of the denoising networks applied to deep learning-based LDCT imaging are supervised methods, which require paired data for network training. In a realistic imaging scenario, obtaining well-aligned image pairs is challenging due to the error in the table re-positioning and the patient's physiological movement during data acquisition. In contrast, the unpaired learning method can overcome the drawbacks of supervised learning, making it more feasible to collect unpaired training data in most real-world imaging applications. In this study, we develop a novel unpaired learning framework, Self-Supervised Guided Knowledge Distillation (SGKD), which enables the guidance of supervised learning using the results generated by self-supervised learning. The proposed SGKD scheme contains two stages of network training. First, we can achieve the LDCT image quality improvement by the designed self-supervised cycle network. Meanwhile, it can also produce two complementary training datasets from the unpaired LDCT and NDCT images. Second, a knowledge distillation strategy with the above two datasets is exploited to further improve the LDCT image denoising performance. To evaluate the effectiveness and feasibility of the proposed method, extensive experiments were performed on the simulated AAPM challenging and real-world clinical LDCT datasets. The qualitative and quantitative results show that the proposed SGKD achieves better performance in terms of noise suppression and detail preservation compared with some state-of-the-art network models.

CCN-CL: A content-noise complementary network with contrastive learning for low-dose computed tomography denoising

In recent years, low-dose computed tomography (LDCT) has played an increasingly important role in the diagnosis CT to reduce the potential adverse effects of x-ray radiation on patients while maintaining the same diagnostic image quality. Current deep learning-based denoising methods applied to LDCT imaging only use normal dose CT (NDCT) images as positive examples to guide the denoising process. Recent studies on contrastive learning have proved that the original images as negative examples can also be helpful for network learning. Therefore, this paper proposes a novel content-noise complementary network with contrastive learning for an LDCT denoising task. First, to better train our proposed network, a contrastive learning loss, taking the NDCT image as a positive example and the original LDCT image as a negative example to guide the network learning is added. Furthermore, we also design a network structure that combines content-noise complementary learning strategy, attention mechanism, and deformable convolution for better network performance. In an evaluation study, we compare the performance of our designed network with some of the state-of-the-art methods in the 2016 NIH-AAPM-Mayo Clinic Low Dose CT Grand Challenge dataset. The quantitative and qualitative evaluation results demonstrate the feasibility and effectiveness of applying our proposed CCN-CL network model as a new deep learning-based LDCT denoising method.

Two-stage deep learning network-based few-view image reconstruction for parallel-beam projection tomography

BACKGROUND

Projection tomography (PT) is a very important and valuable method for fast volumetric imaging with isotropic spatial resolution. Sparse-view or limited-angle reconstruction-based PT can greatly reduce data acquisition time, lower radiation doses, and simplify sample fixation modes. However, few techniques can currently achieve image reconstruction based on few-view projection data, which is especially important for in vivo PT in living organisms.

METHODS

A 2-stage deep learning network (TSDLN)-based framework was proposed for parallel-beam PT reconstructions using few-view projections. The framework is composed of a reconstruction network (R-net) and a correction network (C-net). The R-net is a generative adversarial network (GAN) used to complete image information with direct back-projection (BP) of a sparse signal, bringing the reconstructed image close to reconstruction results obtained from fully projected data. The C-net is a U-net array that denoises the compensation result to obtain a high-quality reconstructed image.

RESULTS

The accuracy and feasibility of the proposed TSDLN-based framework in few-view projection-based reconstruction were first evaluated with simulations, using images from the DeepLesion public dataset. The framework exhibited better reconstruction performance than traditional analytic reconstruction algorithms and iterative algorithms, especially in cases using sparse-view projection images. For example, with as few as two projections, the TSDLN-based framework reconstructed high-quality images very close to the original image, with structural similarities greater than 0.8. By using previously acquired optical PT (OPT) data in the TSDLN-based framework trained on computed tomography (CT) data, we further exemplified the migration capabilities of the TSDLN-based framework. The results showed that when the number of projections was reduced to 5, the contours and distribution information of the samples in question could still be seen in the reconstructed images.

CONCLUSIONS

The simulations and experimental results showed that the TSDLN-based framework has strong reconstruction abilities using few-view projection images, and has great potential in the application of in vivo PT.

Low-dose cone-beam computed tomography reconstruction through a fast three-dimensional compressed sensing method based on the three-dimensional pseudo-polar fourier transform

Background:

Reconstruction of high quality two dimensional images from fan beam computed tomography (CT) with a limited number of projections is already feasible through Fourier based iterative reconstruction method. However, this article is focused on a more complicated reconstruction of three dimensional (3D) images in a sparse view cone beam computed tomography (CBCT) by utilizing Compressive Sensing (CS) based on 3D pseudo polar Fourier transform (PPFT).

Method:

In comparison with the prevalent Cartesian grid, PPFT re gridding is potent to remove rebinning and interpolation errors. Furthermore, using PPFT based radon transform as the measurement matrix, reduced the computational complexity.

Results:

In order to show the computational efficiency of the proposed method, we compare it with an algebraic reconstruction technique and a CS type algorithm. We observed convergence in <20 iterations in our algorithm while others would need at least 50 iterations for reconstructing a qualified phantom image. Furthermore, using a fast composite splitting algorithm solver in each iteration makes it a fast CBCT reconstruction algorithm. The algorithm will minimize a linear combination of three terms corresponding to a least square data fitting, Hessian (HS) Penalty and l1 norm wavelet regularization. We named it PP-based compressed sensing-HS-W. In the reconstruction range of 120 projections around the 360° rotation, the image quality is visually similar to reconstructed images by Feldkamp-Davis-Kress algorithm using 720 projections. This represents a high dose reduction.

Conclusion:

The main achievements of this work are to reduce the radiation dose without degrading the image quality. Its ability in removing the staircase effect, preserving edges and regions with smooth intensity transition, and producing high-resolution, low-noise reconstruction results in low-dose level are also shown.

Superiorization versus regularization: A comparison of algorithms for solving image reconstruction problems with applications in computed tomography

PURPOSE

A system matrix can be built in order to account for the refractions in an optical computed tomography (CT) system. In order to utilize this system matrix, iterative methods are employed to solve the image reconstruction problem. The purpose of this study is to compare potential iterative algorithms to solve this image reconstruction problem. Comparisons examine both solution time and the quality of the reconstructed image. While our work is motivated by optical CT, the results can be extended more generally to CT.

METHODS

A collection of 21 algorithms for solving the image reconstruction problem were evaluated. Specifically, algorithms using (i) superiorization techniques and (ii) regularization to avoid overfitting were compared. Multiple test problems are investigated using 18 different image phantoms, parallel-beam and fan-beam system matrices, and varying noise levels. Comparison of the algorithms is done using performance profiles on three different performance measures.

RESULTS

The results for both the synthetic and clinical test problems show that there is not one single algorithm outperforming all others, but instead a set of top algorithms that give the best values on the performance profiles. When qualitative analyses such as reliance on stopping conditions, number of input parameters, and run time are also considered, FISTA-TV shows slight advantages over the other top algorithms.

CONCLUSIONS

There is a set of top algorithms that all show good results in the performance profiles with a mix of superiorized and regularized model algorithms. As to which of these top algorithms outperforms the rest is undetermined and further research needs to be investigated.

Tomographic absorption spectroscopy based on dictionary learning

Tomographic absorption spectroscopy (TAS) has an advantage over other optical imaging methods for practical combustor diagnostics: optical access is needed in a single plane only, and the access can be limited. However, practical TAS often suffers from limited projection data. In these cases, priors such as smoothness and sparseness can be incorporated to mitigate the ill-posedness of the inversion problem. This work investigates use of dictionary learning (DL) to effectively extract useful a priori information from the existing dataset and incorporate it in the reconstruction process to improve accuracy. We developed two DL algorithms; our numerical results suggest that they can outperform classical Tikhonov reconstruction under moderate noise conditions. Further testing with experimental data indicates that they can effectively suppress reconstruction artifacts and obtain more physically plausible solutions compared with the inverse Radon transform.

Limited View Tomographic Reconstruction Using a Cascaded Residual Dense Spatial-Channel Attention Network With Projection Data Fidelity Layer

Limited view tomographic reconstruction aims to reconstruct a tomographic image from a limited number of projection views arising from sparse view or limited angle acquisitions that reduce radiation dose or shorten scanning time. However, such a reconstruction suffers from severe artifacts due to the incompleteness of sinogram. To derive quality reconstruction, previous methods use UNet-like neural architectures to directly predict the full view reconstruction from limited view data; but these methods leave the deep network architecture issue largely intact and cannot guarantee the consistency between the sinogram of the reconstructed image and the acquired sinogram, leading to a non-ideal reconstruction. In this work, we propose a cascaded residual dense spatial-channel attention network consisting of residual dense spatial-channel attention networks and projection data fidelity layers. We evaluate our methods on two datasets. Our experimental results on AAPM Low Dose CT Grand Challenge datasets demonstrate that our algorithm achieves a consistent and substantial improvement over the existing neural network methods on both limited angle reconstruction and sparse view reconstruction. In addition, our experimental results on Deep Lesion datasets demonstrate that our method is able to generate high-quality reconstruction for 8 major lesion types.

Accelerating vasculature imaging in tumor using mesoscopic fluorescence molecular tomography via a hybrid reconstruction strategy

Mesoscopic fluorescent molecular tomography (MFMT) enables to image fluorescent molecular probes beyond the typical depth limits of microscopic imaging and with enhanced resolution compared to macroscopic imaging. However, MFMT is a scattering-based inverse problem that is an ill-posed inverse problem and hence, requires relative complex iterative solvers coupled with regularization strategies. Inspired by the potential of deep learning in performing image formation tasks from raw measurements, this work proposes a hybrid approach to solve the MFMT inverse problem. This methodology combines a convolutional symmetric network and a conventional iterative algorithm to accelerate the reconstruction procedure. By the proposed deep neural network, the principal components of the sensitivity matrix are extracted and the accompanying noise in measurements is suppressed, which helps to accelerate the reconstruction and improve the accuracy of results. We apply the proposed method to reconstruct in silico and vascular tree models. The results demonstrate that reconstruction accuracy and speed are highly improved due to the reduction of redundant entries of the sensitivity matrix and noise suppression.

Reduced iteration image reconstruction of incomplete projection CT using regularization strategy through Lp norm dictionary learning

BACKGROUND

For sparse and limited angle projection Computed Tomography (CT), the reconstructed image usually suffers from considerable artifacts due to undersampled data.

OBJECTIVE

To improve image reconstruction quality of sparse and limited angle projection CT, this study tested a novel reconstruction algorithm based on Dictionary Learning (DL) from sparse and limited projections.

METHODS

The study used signal sparse representation and feature extraction to render the DL technology, which is constrained by L2 and Lp norms, respectively. A Lp Norm Dictionary Learning term is suitable for regular term of objective function for CT image reconstruction. This is helpful for solving the objective function by combining algorithm of ART. Based on these features, the new algorithm of ART-DL-Lp is proposed for CT image reconstruction. The alternate solving strategy of the algorithm of "ART first, then adaptive DL" is provided in sequence. The impact on reconstruction results of ART-DL-Lp at different p values (0 < p < 1) is also considered.

RESULTS

For non-ideal projections with noise, the digital experiments show that ART-DL-Lp data were superior to those of ART, SART, and ART-DL-L2. Accordingly, the objective evaluation metrics for non-ideal situation of RMSE, MAE, PSNR, Residuals and SSIM are all better than those of contrasted three algorithms. The metrics curves of ART-DL-Lp algorithm are recorded as the best. In both incomplete projection situations, smaller p-value of ART-DL-Lp algorithm induces more close reconstructed images to the original form and better five objective evaluation metrics.

CONCLUSIONS

Overall, the reconstruction efficiency of the proposed ART-DL-Lp for CT imaging using the noisy incomplete projections outperforms ART, SART and ART-DL-L2 algorithms. For ART-DL-Lp algorithm, lower p-values result in better reconstruction performance.

Spectral Angiography Material Decomposition Using an Empirical Forward Model and a Dictionary-Based Regularization

By resolving the energy of the incident X-ray photons, spectral X-ray imaging with photon counting detectors offers additional material-specific information compared to conventional X-ray imaging. This additional information can be used to improve clinical diagnosis for various applications. However, spectral imaging still faces several challenges. Amplified noise and a reduced signal-to-noise ratio on the decomposed basis material images remain a major problem, especially for low-dose applications. Furthermore, it is challenging to construct an accurate model of the spectral measurement acquisition process. In this paper, we present a novel algorithm for projection-based material decomposition. It uses an empirical polynomial model that is tuned by calibration measurements. We combine this method with a statistical model of the measured photon counts and a dictionary-based joint regularization approach. We focused on spectral coronary angiography as a potential clinical application of projection-based material decomposition with photon counting detectors. Numerical and real experiments show that spectral angiography with realistic dose levels and gadolinium contrast agent concentrations are feasible using the proposed decomposition algorithm and currently available photon-counting detector technology.

Smoothed l0 Norm Regularization for Sparse-View X-Ray CT Reconstruction

Low-dose computed tomography (CT) reconstruction is a challenging problem in medical imaging. To complement the standard filtered back-projection (FBP) reconstruction, sparse regularization reconstruction gains more and more research attention, as it promises to reduce radiation dose, suppress artifacts, and improve noise properties. In this work, we present an iterative reconstruction approach using improved smoothed l₀ (SL0) norm regularization which is used to approximate l₀ norm by a family of continuous functions to fully exploit the sparseness of the image gradient. Due to the excellent sparse representation of the reconstruction signal, the desired tissue details are preserved in the resulting images. To evaluate the performance of the proposed SL0 regularization method, we reconstruct the simulated dataset acquired from the Shepp-Logan phantom and clinical head slice image. Additional experimental verification is also performed with two real datasets from scanned animal experiment. Compared to the referenced FBP reconstruction and the total variation (TV) regularization reconstruction, the results clearly reveal that the presented method has characteristic strengths. In particular, it improves reconstruction quality via reducing noise while preserving anatomical features.