Iterative material decomposition for spectral CT using self-supervised Noise2Noise prior

Image Domain Multi-Material Decomposition Noise Suppression Through Basis Transformation and Selective Filtering

Spectral CT can provide material characterization ability to offer more precise material information for diagnosis purposes. However, the material decomposition process generally leads to amplification of noise which significantly limits the utility of the material basis images. To mitigate such problem, an image domain noise suppression method was proposed in this work. The method performs basis transformation of the material basis images based on a singular value decomposition. The noise variances of the original spectral CT images were incorporated in the matrix to be decomposed to ensure that the transformed basis images are statistically uncorrelated. Due to the difference in noise amplitudes in the transformed basis images, a selective filtering method was proposed with the low-noise transformed basis image as guidance. The method was evaluated using both numerical simulation and real clinical dual-energy CT data. Results demonstrated that compared with existing methods, the proposed method performs better in preserving the spatial resolution and the soft tissue contrast while suppressing the image noise. The proposed method is also computationally efficient and can realize real-time noise suppression for clinical spectral CT images.

Multi-energy CT material decomposition using graph model improved CNN

In spectral CT imaging, the coefficient image of the basis material obtained by the material decomposition technique can estimate the tissue composition, and its accuracy directly affects the disease diagnosis. Although the precision of material decomposition is increased by employing convolutional neural networks (CNN), extracting the non-local features from the CT image is restricted using the traditional CNN convolution operator. A graph model built by multi-scale non-local self-similar patterns is introduced into multi-material decomposition (MMD). We proposed a novel MMD method based on graph edge-conditioned convolution U-net (GECCU-net) to enhance material image quality. The GECCU-net focuses on developing a multi-scale encoder. At the network coding stage, three paths are applied to capture comprehensive image features. The local and non-local feature aggregation (LNFA) blocks are designed to integrate the local and non-local features from different paths. The graph edge-conditioned convolution based on non-Euclidean space excavates the non-local features. A hybrid loss function is defined to accommodate multi-scale input images and avoid over-smoothing of results. The proposed network is compared quantitatively with base CNN models on the simulated and real datasets. The material images generated by GECCU-net have less noise and artifacts while retaining more information on tissue. The Structural SIMilarity (SSIM) of the obtained abdomen and chest water maps reaches 0.9976 and 0.9990, respectively, and the RMSE reduces to 0.1218 and 0.4903 g/cm3. The proposed method can improve MMD performance and has potential applications.

Self-supervised dual-domain balanced dropblock-network for low-dose CT denoising

Objective.Self-supervised learning methods have been successfully applied for low-dose computed tomography (LDCT) denoising, with the advantage of not requiring labeled data. Conventional self-supervised methods operate only in the image domain, ignoring valuable priors in the sinogram domain. Recently proposed dual-domain methods address this limitation but encounter issues with blurring artifacts in the reconstructed image due to the inhomogeneous distribution of noise levels in low-dose sinograms.Approach.To tackle this challenge, this paper proposes SDBDNet, an end-to-end dual-domain self-supervised method for LDCT denoising. With the network designed based on the properties of inhomogeneous noise in low-dose sinograms and the principle of moderate sinogram-domain denoising, SDBDNet achieves effective denoising in dual domains without introducing blurring artifacts. Specifically, we split the sinogram into two subsets based on the positions of detector cells to generate paired training data with high similarity and independent noise. These sub-sinograms are then restored to their original size using 1D interpolation and learning-based correction. To achieve adaptive and moderate smoothing in the sinogram domain, we integrate Dropblock, a type of convolution layer with regularization, into SDBDNet, and set a weighted average between the denoised sinograms and their noisy counterparts, leading to a well-balanced dual-domain approach.Main results.Numerical experiments show that our method outperforms popular non-learning and self-supervised learning methods, demonstrating its effectiveness and superior performance.Significance.While introducing a novel high-performance dual-domain self-supervised LDCT denoising method, this paper also emphasizes and verifies the importance of appropriate sinogram-domain denoising in dual-domain methods, which might inspire future work.

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.

A Locally Weighted Linear Regression Look-Up Table-Based Iterative Reconstruction Method for Dual Spectral CT

OBJECTIVE

Compared with traditional computed tomography (CT), dual spectral CT (DSCT) exhibits superior material distinguishability and thus has broad prospects in industrial and medical fields. In iterative DSCT algorithms, accurately modeling forward-projection functions is crucial, but it is very difficult to analytically provide accurate functions.

METHODS

In this article, we propose a locally weighted linear regression look-up table-based (LWLR-LUT) iterative reconstruction method for DSCT. First, the proposed method uses LWLR to establish LUTs for the forward-projection functions through calibration phantoms, achieving good local information calibration. Second, the reconstructed images can be iteratively obtained through the established LUTs. The proposed method not only does not require knowledge of the X-ray spectra and the attenuation coefficients, but also implicitly accounts for some scattered radiation while fitting locally the forward-projection functions in the calibration space.

RESULTS

Both numerical simulations and real data experiments demonstrate that the proposed method can achieve highly accurate polychromatic forward-projection functions and greatly improve the quality of the images reconstructed from scattering-free and scattering projections.

CONCLUSION

The proposed method is simple and practical, and achieves good material decomposition effects for objects with different complex structures through simple calibration phantoms.

Noise Suppression With Similarity-Based Self-Supervised Deep Learning

Image denoising is a prerequisite for downstream tasks in many fields. Low-dose and photon-counting computed tomography (CT) denoising can optimize diagnostic performance at minimized radiation dose. Supervised deep denoising methods are popular but require paired clean or noisy samples that are often unavailable in practice. Limited by the independent noise assumption, current self-supervised denoising methods cannot process correlated noises as in CT images. Here we propose the first-of-its-kind similarity-based self-supervised deep denoising approach, referred to as Noise2Sim, that works in a nonlocal and nonlinear fashion to suppress not only independent but also correlated noises. Theoretically, Noise2Sim is asymptotically equivalent to supervised learning methods under mild conditions. Experimentally, Nosie2Sim recovers intrinsic features from noisy low-dose CT and photon-counting CT images as effectively as or even better than supervised learning methods on practical datasets visually, quantitatively and statistically. Noise2Sim is a general self-supervised denoising approach and has great potential in diverse applications.

Direct Multi-Material Reconstruction via Iterative Proximal Adaptive Descent for Spectral CT Imaging

Spectral computed tomography (spectral CT) is a promising medical imaging technology because of its ability to provide information on material characterization and quantification. However, with an increasing number of basis materials, the nonlinearity of measurements causes difficulty in decomposition. In addition, noise amplification and beam hardening further reduce image quality. Thus, improving the accuracy of material decomposition while suppressing noise is pivotal for spectral CT imaging. This paper proposes a one-step multi-material reconstruction model as well as an iterative proximal adaptive decent method. In this approach, a proximal step and a descent step with adaptive step size are designed under the forward-backward splitting framework. The convergence analysis of the algorithm is further discussed according to the convexity of the optimization objective function. For simulation experiments with different noise levels, the peak signal-to-noise ratio (PSNR) obtained by the proposed method increases approximately 23 dB, 14 dB, and 4 dB compared to those of other algorithms. Magnified areas of thorax data further demonstrated that the proposed method has a better ability to preserve details in tissues, bones, and lungs. Numerical experiments verify that the proposed method efficiently reconstructed the material maps, and reduced noise and beam hardening artifacts compared with the state-of-the-art methods.

Multi-material spectral photon-counting micro-CT with minimum residual decomposition and self-supervised deep denoising

Spectral micro-CT imaging with direct-detection energy discriminating photon counting detectors having small pixel size (< 100×100 µm²) is mainly hampered by: i) the limited energy resolution of the imaging device due to charge sharing effects and ii) the unavoidable noise amplification in the images resulting from basis material decomposition. In this work, we present a cone-beam micro-CT setup that includes a CdTe photon counting detector implementing a charge summing hardware solution to correct for the charge-sharing issue and an innovative image processing pipeline based on accurate modeling of the spectral response of the imaging system, an improved basis material decomposition (BMD) algorithm named minimum-residual BMD (MR-BMD), and self-supervised deep convolutional denoising. Experimental tomographic projections having a pixel size of 45×45 µm² of a plastinated mouse sample including I, Ba, and Gd small cuvettes were acquired. Results demonstrate the capability of the combined hardware and software tools to sharply discriminate even between materials having their K-Edge separated by a few keV, such as e.g., I and Ba. By evaluating the quality of the reconstructed decomposed images (water, bone, I, Ba, and Gd), the quantitative performances of the spectral system are here assessed and discussed.

An improved iterative neural network for high-quality image-domain material decomposition in dual-energy CT

PURPOSE

Dual-energy computed tomography (DECT) has been widely used in many applications that need material decomposition. Image-domain methods directly decompose material images from high- and low-energy attenuation images, and thus, are susceptible to noise and artifacts on attenuation images. The purpose of this study is to develop an improved iterative neural network (INN) for high-quality image-domain material decomposition in DECT, and to study its properties.

METHODS

We propose a new INN architecture for DECT material decomposition. The proposed INN architecture uses distinct cross-material convolutional neural network (CNN) in image refining modules, and uses image decomposition physics in image reconstruction modules. The distinct cross-material CNN refiners incorporate distinct encoding-decoding filters and cross-material model that captures correlations between different materials. We study the distinct cross-material CNN refiner with patch-based reformulation and tight-frame condition.

RESULTS

Numerical experiments with extended cardiac-torso phantom and clinical data show that the proposed INN significantly improves the image quality over several image-domain material decomposition methods, including a conventional model-based image decomposition (MBID) method using an edge-preserving regularizer, a recent MBID method using pre-learned material-wise sparsifying transforms, and a noniterative deep CNN method. Our study with patch-based reformulations reveals that learned filters of distinct cross-material CNN refiners can approximately satisfy the tight-frame condition.

CONCLUSIONS

The proposed INN architecture achieves high-quality material decompositions using iteration-wise refiners that exploit cross-material properties between different material images with distinct encoding-decoding filters. Our tight-frame study implies that cross-material CNN refiners in the proposed INN architecture are useful for noise suppression and signal restoration. This article is protected by copyright. All rights reserved.

Deep learning for improving the spatial resolution of magnetic particle imaging

Objective.Magnetic particle imaging (MPI) is a new medical, non-destructive, imaging method for visualizing the spatial distribution of superparamagnetic iron oxide nanoparticles. In MPI, spatial resolution is an important indicator of efficiency; traditional techniques for improving the spatial resolution may result in higher costs, lower sensitivity, or reduced contrast.Approach.Therefore, we propose a deep-learning approach to improve the spatial resolution of MPI by fusing a dual-sampling convolutional neural network (FDS-MPI). An end-to-end model is established to generate high-spatial-resolution images from low-spatial-resolution images, avoiding the aforementioned shortcomings.Main results.We evaluate the performance of the proposed FDS-MPI model through simulation and phantom experiments. The results demonstrate that the FDS-MPI model can improve the spatial resolution by a factor of two.Significance.This significant improvement in MPI could facilitate the preclinical application of medical imaging modalities in the future.

Statistical iterative spectral CT imaging method based on blind separation of polychromatic projections

Spectral computed tomography (CT) can provide narrow-energy-width reconstructed images, thereby suppressing beam hardening artifacts and providing rich attenuation information for component characterization. We propose a statistical iterative spectral CT imaging method based on blind separation of polychromatic projections to improve the accuracy of narrow-energy-width image decomposition. For direct inversion in blind scenarios, we introduce the system matrix into the X-ray multispectral forward model to reduce indirect errors. A constrained optimization problem with edge-preserving regularization is established and decomposed into two sub-problems to be alternately solved. Experiments indicate that the novel algorithm obtains more accurate narrow-energy-width images than the state-of-the-art method.

Multi-channel convolutional analysis operator learning for dual-energy CT reconstruction

Objective. Dual-energy computed tomography (DECT) has the potential to improve contrast and reduce artifacts and the ability to perform material decomposition in advanced imaging applications. The increased number of measurements results in a higher radiation dose, and it is therefore essential to reduce either the number of projections for each energy or the source x-ray intensity, but this makes tomographic reconstruction more ill-posed. Approach. We developed the multi-channel convolutional analysis operator learning (MCAOL) method to exploit common spatial features within attenuation images at different energies and we propose an optimization method which jointly reconstructs the attenuation images at low and high energies with mixed norm regularization on the sparse features obtained by pre-trained convolutional filters through the convolutional analysis operator learning (CAOL) algorithm. Main results. Extensive experiments with simulated and real computed tomography data were performed to validate the effectiveness of the proposed methods, and we report increased reconstruction accuracy compared with CAOL and iterative methods with single and joint total variation regularization. Significance. Qualitative and quantitative results on sparse views and low-dose DECT demonstrate that the proposed MCAOL method outperforms both CAOL applied on each energy independently and several existing state-of-the-art model-based iterative reconstruction techniques, thus paving the way for dose reduction.