SPULTRA: Low-Dose CT Image Reconstruction With Joint Statistical and Learned Image Models

Existence, uniqueness, and efficiency of numerically unbiased attenuation pathlength estimators for photon counting detectors at low count rates

BACKGROUND

The first step in computed tomography (CT) reconstruction is to estimate attenuation pathlength. Usually, this is done with a logarithm transformation, which is the direct solution to the Beer-Lambert Law. At low signals, however, the logarithm estimator is biased. Bias arises both from the curvature of the logarithm and from the possibility of detecting zero counts, so a data substitution strategy may be employed to avoid the singularity of the logarithm. Recent progress has been made by Li et al. [IEEE Trans Med Img 42:6, 2023] to modify the logarithm estimator to eliminate curvature bias, but the optimal strategy for mitigating bias from the singularity remains unknown.

PURPOSE

The purpose of this study was to use numerical techniques to construct unbiased attenuation pathlength estimators that are alternatives to the logarithm estimator, and to study the uniqueness and optimality of possible solutions, assuming a photon counting detector.

METHODS

Formally, an attenuation pathlength estimator is a mapping from integer detector counts to real pathlength values. We constrain our focus to only the small signal inputs that are problematic for the logarithm estimator, which we define as inputs of <100 counts, and we consider estimators that use only a single input and that are not informed by adjacent measurements (e.g., adaptive smoothing). The set of all possible pathlength estimators can then be represented as points in a 100-dimensional vector space. Within this vector space, we use optimization to select the estimator that (1) minimizes mean squared error and (2) is unbiased. We define "unbiased" as satisfying the numerical condition that the maximum bias be less than 0.001 across a continuum of 1000 object thicknesses that span the desired operating range. Because the objective function is convex and the constraints are affine, optimization is tractable and guaranteed to converge to the global minimum. We further examine the nullspace of the constraint matrix to understand the uniqueness of possible solutions, and we compare the results to the Cramér-Rao bound of the variance.

RESULTS

We first show that an unbiased attenuation pathlength estimator does not exist if very low mean detector signals (equivalently, very thick objects) are permitted. It is necessary to select a minimum mean detector signal for which unbiased behavior is desired. If we select two counts, the optimal estimator is similar to Li's estimator. If we select one count, the optimal estimator becomes non-monotonic. The oscillations cause the unbiased estimator to be noise amplifying. The nullspace of the constraint matrix is high-dimensional, so that unbiased solutions are not unique. The Cramér-Rao bound of the variance matches well with the expectedI - 0.5 ${{I}^{ - 0.5}}$ scaling law and cannot be attained.

CONCLUSION

If arbitrarily thick objects are permitted, an unbiased attenuation pathlength estimator does not exist. If the maximum thickness is restricted, an unbiased estimator exists but is not unique. An optimal estimator can be selected that minimizes variance, but a bias-variance tradeoff exists where a larger domain of unbiased behavior requires increased variance.

Sparse-view CT reconstruction based on group-based sparse representation using weighted guided image filtering

OBJECTIVES

In the past, guided image filtering (GIF)-based methods often utilized total variation (TV)-based methods to reconstruct guidance images. And they failed to reconstruct the intricate details of complex clinical images accurately. To address these problems, we propose a new sparse-view CT reconstruction method based on group-based sparse representation using weighted guided image filtering.

METHODS

In each iteration of the proposed algorithm, the result constrained by the group-based sparse representation (GSR) is used as the guidance image. Then, the weighted guided image filtering (WGIF) was used to transfer the important features from the guidance image to the reconstruction of the SART method.

RESULTS

Three representative slices were tested under 64 projection views, and the proposed method yielded the best visual effect. For the shoulder case, the PSNR can achieve 48.82, which is far superior to other methods.

CONCLUSIONS

The experimental results demonstrate that our method is more effective in preserving structures, suppressing noise, and reducing artifacts compared to other methods.

Machine Learned Texture Prior From Full-Dose CT Database via Multi-Modality Feature Selection for Bayesian Reconstruction of Low-Dose CT

In our earlier study, we proposed a regional Markov random field type tissue-specific texture prior from previous full-dose computed tomography (FdCT) scan for current low-dose CT (LdCT) imaging, which showed clinical benefits through task-based evaluation. Nevertheless, two assumptions were made for early study. One assumption is that the center pixel has a linear relationship with its nearby neighbors and the other is previous FdCT scans of the same subject are available. To eliminate the two assumptions, we proposed a database assisted end-to-end LdCT reconstruction framework which includes a deep learning texture prior model and a multi-modality feature based candidate selection model. A convolutional neural network-based texture prior is proposed to eliminate the linear relationship assumption. And for scenarios in which the concerned subject has no previous FdCT scans, we propose to select one proper prior candidate from the FdCT database using multi-modality features. Features from three modalities are used including the subjects' physiological factors, the CT scan protocol, and a novel feature named Lung Mark which is deliberately proposed to reflect the z-axial property of human anatomy. Moreover, a majority vote strategy is designed to overcome the noise effect from LdCT scans. Experimental results showed the effectiveness of Lung Mark. The selection model has accuracy of 84% testing on 1,470 images from 49 subjects. The learned texture prior from FdCT database provided reconstruction comparable to the subjects having corresponding FdCT. This study demonstrated the feasibility of bringing clinically relevant textures from available FdCT database to perform Bayesian reconstruction of any current LdCT scan.

Multi-layer clustering-based residual sparsifying transform for low-dose CT image reconstruction

PURPOSE

The recently proposed sparsifying transform (ST) models incur low computational cost and have been applied to medical imaging. Meanwhile, deep models with nested network structure reveal great potential for learning features in different layers. In this study, we propose a network-structured ST learning approach for X-ray computed tomography (CT), which we refer to as multi-layer clustering-based residual sparsifying transform (MCST) learning. The proposed MCST scheme learns multiple different unitary transforms in each layer by dividing each layer's input into several classes. We apply the MCST model to low-dose CT (LDCT) reconstruction by deploying the learned MCST model into the regularizer in penalized weighted least squares (PWLS) reconstruction.

METHODS

The proposed MCST model combines a multi-layer sparse representation structure with multiple clusters for the features in each layer that are modeled by a rich collection of transforms. We train the MCST model in an unsupervised manner via a block coordinate descent (BCD) algorithm. Since our method is patch-based, the training can be performed with a limited set of images. For CT image reconstruction, we devise a novel algorithm called PWLS-MCST by integrating the pre-learned MCST signal model with PWLS optimization.

RESULTS

We conducted LDCT reconstruction experiments on XCAT phantom data, Numerical Mayo Clinical CT dataset and "LDCT image and projection dataset" (Clinical LDCT dataset). We trained the MCST model with two (or three) layers and with five clusters in each layer. The learned transforms in the same layer showed rich features while additional information is extracted from representation residuals. Our simulation results and clinical results demonstrate that PWLS-MCST achieves better image reconstruction quality than the conventional filtered back-projection (FBP) method and PWLS with edge-preserving (EP) regularizer. It also outperformed recent advanced methods like PWLS with a learned multi-layer residual sparsifying transform (MARS) prior and PWLS with a union of learned transforms (ULTRA), especially for displaying clear edges and preserving subtle details.

CONCLUSIONS

In this work, a multi-layer sparse signal model with a nested network structure is proposed. We refer this novel model as the MCST model that exploits multi-layer residual maps to sparsify the underlying image and clusters the inputs in each layer for accurate sparsification. We presented a new PWLS framework with a learned MCST regularizer for LDCT reconstruction. Experimental results show that the proposed PWLS-MCST provides clearer reconstructions than several baseline methods. The code for PWLS-MCST is released at https://github.com/Xikai97/PWLS-MCST.

A total variation prior unrolling approach for computed tomography reconstruction

BACKGROUND

With the rapid development of deep learning technology, deep neural networks can effectively enhance the performance of computed tomography (CT) reconstructions. One kind of commonly used method to construct CT reconstruction networks is to unroll the conventional iterative reconstruction (IR) methods to convolutional neural networks (CNNs). However, most unrolling methods primarily unroll the fidelity term of IR methods to CNNs, without unrolling the prior terms. The prior terms are always directly replaced by neural networks.

PURPOSE

In conventional IR methods, the prior terms play a vital role in improving the visual quality of reconstructed images. Unrolling the hand-crafted prior terms to CNNs may provide a more specialized unrolling approach to further improve the performance of CT reconstruction. In this work, a primal-dual network (PD-Net) was proposed by unrolling both the data fidelity term and the total variation (TV) prior term, which effectively preserves the image edges and textures in the reconstructed images.

METHODS

By further deriving the Chambolle-Pock (CP) algorithm instance for CT reconstruction, we discovered that the TV prior updates the reconstructed images with its divergences in each iteration of the solution process. Based on this discovery, CNNs were applied to yield the divergences of the feature maps for the reconstructed image generated in each iteration. Additionally, a loss function was applied to the predicted divergences of the reconstructed image to guarantee that the CNNs' results were the divergences of the corresponding feature maps in the iteration. In this manner, the proposed CNNs seem to play the same roles in the PD-Net as the TV prior in the IR methods. Thus, the TV prior in the CP algorithm instance can be directly unrolled to CNNs.

RESULTS

The datasets from the Low-Dose CT Image and Projection Data and the Piglet dataset were employed to assess the effectiveness of our proposed PD-Net. Compared with conventional CT reconstruction methods, our proposed method effectively preserves the structural and textural information in reference to ground truth.

CONCLUSIONS

The experimental results show that our proposed PD-Net framework is feasible for the implementation of CT reconstruction tasks. Owing to the promising results yielded by our proposed neural network, this study is intended to inspire further development of unrolling approaches by enabling the direct unrolling of hand-crafted prior terms to CNNs.

A CT image feature space (CTIS) loss for restoration with deep learning-based methods

Objective. Deep learning-based methods have been widely used in medical imaging field such as detection, segmentation and image restoration. For supervised learning methods in CT image restoration, different loss functions will lead to different image qualities which may affect clinical diagnosis. In this paper, to compare commonly used loss functions and give a better alternative, we studied a widely generalizable framework for loss functions which are defined in the feature space extracted by neural networks. Approach. For the purpose of incorporating prior knowledge, a CT image feature space (CTIS) loss was proposed, which learned the feature space from high quality CT images by an autoencoder. In the absence of high-quality CT images, an alternate loss function, random-weight (RaW) loss in the feature space of images (LoFS) was proposed. For RaW-LoFS, the feature space is defined by neural networks with random weights. Main results. In experimental studies, we used post reconstruction deep learning-based methods in the 2016 AAPM low dose CT grand challenge. Compared with perceptual loss that is widely used, our loss functions performed better both quantitatively and qualitatively. In addition, three senior radiologists were invited for subjective assessments between CTIS loss and RaW-LoFS. According to their judgements, the results of CTIS loss achieved better visual quality. Furtherly, by analyzing each channel of CTIS loss, we also proposed partially constrained CTIS loss. Significance. Our loss functions achieved favorable image quality. This framework can be easily adapted to other tasks and fields.

Reconstruction of three-dimensional tomographic patient models for radiation dose modulation in CT from two scout views using deep learning

BACKGROUND

A tomographic patient model is essential for radiation dose modulation in x-ray computed tomography (CT). Currently, two-view scout images (also known as topograms) are used to estimate patient models with relatively uniform attenuation coefficients. These patient models do not account for the detailed anatomical variations of human subjects, and thus, may limit the accuracy of intraview or organ-specific dose modulations in emerging CT technologies.

PURPOSE

The purpose of this work was to show that 3D tomographic patient models can be generated from two-view scout images using deep learning strategies, and the reconstructed 3D patient models indeed enable accurate prescriptions of fluence-field modulated or organ-specific dose delivery in the subsequent CT scans.

METHODS

CT images and the corresponding two-view scout images were retrospectively collected from 4214 individual CT exams. The collected data were curated for the training of a deep neural network architecture termed ScoutCT-NET to generate 3D tomographic attenuation models from two-view scout images. The trained network was validated using a cohort of 55 136 images from 212 individual patients. To evaluate the accuracy of the reconstructed 3D patient models, radiation delivery plans were generated using ScoutCT-NET 3D patient models and compared with plans prescribed based on true CT images (gold standard) for both fluence-field-modulated CT and organ-specific CT. Radiation dose distributions were estimated using Monte Carlo simulations and were quantitatively evaluated using the Gamma analysis method. Modulated dose profiles were compared against state-of-the-art tube current modulation schemes. Impacts of ScoutCT-NET patient model-based dose modulation schemes on universal-purpose CT acquisitions and organ-specific acquisitions were also compared in terms of overall image appearance, noise magnitude, and noise uniformity.

RESULTS

The results demonstrate that (1) The end-to-end trained ScoutCT-NET can be used to generate 3D patient attenuation models and demonstrate empirical generalizability. (2) The 3D patient models can be used to accurately estimate the spatial distribution of radiation dose delivered by standard helical CTs prior to the actual CT acquisition; compared to the gold-standard dose distribution, 95.0% of the voxels in the ScoutCT-NET based dose maps have acceptable gamma values for 5 mm distance-to-agreement and 10% dose difference. (3) The 3D patient models also enabled accurate prescription of fluence-field modulated CT to generate a more uniform noise distribution across the patient body compared to tube current-modulated CT. (4) ScoutCT-NET 3D patient models enabled accurate prescription of organ-specific CT to boost image quality for a given body region-of-interest under a given radiation dose constraint.

CONCLUSION

3D tomographic attenuation models generated by ScoutCT-NET from two-view scout images can be used to prescribe fluence-field-modulated or organ-specific CT scans with high accuracy for the overall objective of radiation dose reduction or image quality improvement for a given imaging task.

Unified Supervised-Unsupervised (SUPER) Learning for X-Ray CT Image Reconstruction

Traditional model-based image reconstruction (MBIR) methods combine forward and noise models with simple object priors. Recent machine learning methods for image reconstruction typically involve supervised learning or unsupervised learning, both of which have their advantages and disadvantages. In this work, we propose a unified supervised-unsupervised (SUPER) learning framework for X-ray computed tomography (CT) image reconstruction. The proposed learning formulation combines both unsupervised learning-based priors (or even simple analytical priors) together with (supervised) deep network-based priors in a unified MBIR framework based on a fixed point iteration analysis. The proposed training algorithm is also an approximate scheme for a bilevel supervised training optimization problem, wherein the network-based regularizer in the lower-level MBIR problem is optimized using an upper-level reconstruction loss. The training problem is optimized by alternating between updating the network weights and iteratively updating the reconstructions based on those weights. We demonstrate the learned SUPER models' efficacy for low-dose CT image reconstruction, for which we use the NIH AAPM Mayo Clinic Low Dose CT Grand Challenge dataset for training and testing. In our experiments, we studied different combinations of supervised deep network priors and unsupervised learning-based or analytical priors. Both numerical and visual results show the superiority of the proposed unified SUPER methods over standalone supervised learning-based methods, iterative MBIR methods, and variations of SUPER obtained via ablation studies. We also show that the proposed algorithm converges rapidly in practice.

Downsampled Imaging Geometric Modeling for Accurate CT Reconstruction via Deep Learning

X-ray computed tomography (CT) is widely used clinically to diagnose a variety of diseases by reconstructing the tomographic images of a living subject using penetrating X-rays. For accurate CT image reconstruction, a precise imaging geometric model for the radiation attenuation process is usually required to solve the inversion problem of CT scanning, which encodes the subject into a set of intermediate representations in different angular positions. Here, we show that accurate CT image reconstruction can be subsequently achieved by downsampled imaging geometric modeling via deep-learning techniques. Specifically, we first propose a downsampled imaging geometric modeling approach for the data acquisition process and then incorporate it into a hierarchical neural network, which simultaneously combines both geometric modeling knowledge of the CT imaging system and prior knowledge gained from a data-driven training process for accurate CT image reconstruction. The proposed neural network is denoted as DSigNet, i.e., downsampled-imaging-geometry-based network for CT image reconstruction. We demonstrate the feasibility of the proposed DSigNet for accurate CT image reconstruction with clinical patient data. In addition to improving the CT image quality, the proposed DSigNet might help reduce the computational complexity and accelerate the reconstruction speed for modern CT imaging systems.

Multilayer residual sparsifying transform (MARS) model for low-dose CT image reconstruction

PURPOSE

Signal models based on sparse representations have received considerable attention in recent years. On the other hand, deep models consisting of a cascade of functional layers, commonly known as deep neural networks, have been highly successful for the task of object classification and have been recently introduced to image reconstruction. In this work, we develop a new image reconstruction approach based on a novel multilayer model learned in an unsupervised manner by combining both sparse representations and deep models. The proposed framework extends the classical sparsifying transform model for images to a Multilayer residual sparsifying transform (MARS) model, wherein the transform domain data are jointly sparsified over layers. We investigate the application of MARS models learned from limited regular-dose images for low-dose CT reconstruction using penalized weighted least squares (PWLS) optimization.

METHODS

We propose new formulations for multilayer transform learning and image reconstruction. We derive an efficient block coordinate descent algorithm to learn the transforms across layers, in an unsupervised manner from limited regular-dose images. The learned model is then incorporated into the low-dose image reconstruction phase.

RESULTS

Low-dose CT experimental results with both the XCAT phantom and Mayo Clinic data show that the MARS model outperforms conventional methods such as filtered back-projection and PWLS methods based on the edge-preserving (EP) regularizer in terms of two numerical metrics (RMSE and SSIM) and noise suppression. Compared with the single-layer learned transform (ST) model, the MARS model performs better in maintaining some subtle details.

CONCLUSIONS

This work presents a novel data-driven regularization framework for CT image reconstruction that exploits learned multilayer or cascaded residual sparsifying transforms. The image model is learned in an unsupervised manner from limited images. Our experimental results demonstrate the promising performance of the proposed multilayer scheme over single-layer learned sparsifying transforms. Learned MARS models also offer better image quality than typical nonadaptive PWLS methods.

A dual-domain deep learning-based reconstruction method for fully 3D sparse data helical CT

Helical CT has been widely used in clinical diagnosis. In this work, we focus on a new prototype of helical CT, equipped with sparsely spaced multidetector and multi-slit collimator (MSC) in the axis direction. This type of system can not only lower radiation dose, and suppress scattering by MSC, but also cuts down the manufacturing cost of the detector. The major problem to overcome with such a system, however, is that of insufficient data for reconstruction. Hence, we propose a deep learning-based function optimization method for this ill-posed inverse problem. By incorporating a Radon inverse operator, and disentangling each slice, we significantly simplify the complexity of our network for 3D reconstruction. The network is composed of three subnetworks. Firstly, a convolutional neural network (CNN) in the projection domain is constructed to estimate missing projection data, and to convert helical projection data to 2D fan-beam projection data. This is follwed by the deployment of an analytical linear operator to transfer the data from the projection domain to the image domain. Finally, an additional CNN in the image domain is added for further image refinement. These three steps work collectively, and can be trained end to end. The overall network is trained on a simulated CT dataset based on eight patients from the American Association of Physicists in Medicine (AAPM) Low Dose CT Grand Challenge. We evaluate the trained network on both simulated datasets and clinical datasets. Extensive experimental studies have yielded very encouraging results, based on both visual examination and quantitative evaluation. These results demonstrate the effectiveness of our method and its potential for clinical usage. The proposed method provides us with a new solution for a fully 3D ill-posed problem.

Characterization of tissue-specific pre-log Bayesian CT reconstruction by texture-dose relationship

PURPOSE

Tissue textures have been recognized as biomarkers for various clinical tasks. In computed tomography (CT) image reconstruction, it is important but challenging to preserve the texture when lowering x-ray exposure from full- toward low-/ultra-low dose level. Therefore, this paper aims to explore the texture-dose relationship within one tissue-specific pre-log Bayesian CT reconstruction algorithm.

METHODS

To enhance the texture in ultra-low dose CT (ULdCT) reconstruction, this paper presents a Bayesian type algorithm. A shifted Poisson model is adapted to describe the statistical properties of pre-log data, and a tissue-specific Markov random field prior (MRFt) is used to incorporate tissue texture from previous full-dose CT, thus called SP-MRFt algorithm. Utilizing the SP-MRFt algorithm, we investigated tissue texture degradation as a function of x-ray dose levels from full dose (100 mAs/120 kVp) to ultralow dose (1 mAs/120 kVp) by using quantitative texture-based evaluation metrics.

RESULTS

Experimental results show the SP-MRFt algorithm outperforms conventional filtered back projection (FBP) and post-log domain penalized weighted least square MRFt (PWLS-MRFt) in terms of noise suppression and texture preservation. Comparable results are also obtained with shifted Poisson model with 7 × 7 Huber MRF weights (SP-Huber7). The investigation on texture-dose relationship shows that the quantified texture measures drop monotonically as dose level decreases, and interestingly a turning point is observed on the texture-dose response curve.

CONCLUSIONS

This important observation implies that there exists a minimum dose level, at which a given CT scanner (hardware configuration and image reconstruction software) can achieve without compromising clinical tasks. Moreover, the experiment results show that the variance of electronic noise has higher impact than the mean to the texture-dose relationship.

Image Reconstruction: From Sparsity to Data-adaptive Methods and Machine Learning

The field of medical image reconstruction has seen roughly four types of methods. The first type tended to be analytical methods, such as filtered back-projection (FBP) for X-ray computed tomography (CT) and the inverse Fourier transform for magnetic resonance imaging (MRI), based on simple mathematical models for the imaging systems. These methods are typically fast, but have suboptimal properties such as poor resolution-noise trade-off for CT. A second type is iterative reconstruction methods based on more complete models for the imaging system physics and, where appropriate, models for the sensor statistics. These iterative methods improved image quality by reducing noise and artifacts. The FDA-approved methods among these have been based on relatively simple regularization models. A third type of methods has been designed to accommodate modified data acquisition methods, such as reduced sampling in MRI and CT to reduce scan time or radiation dose. These methods typically involve mathematical image models involving assumptions such as sparsity or low-rank. A fourth type of methods replaces mathematically designed models of signals and systems with data-driven or adaptive models inspired by the field of machine learning. This paper focuses on the two most recent trends in medical image reconstruction: methods based on sparsity or low-rank models, and data-driven methods based on machine learning techniques.