Spectrum Estimation-Guided Iterative Reconstruction Algorithm for Dual Energy CT

Penumbra-effect induced spectral mixing in x-ray computed tomography: a multi-ray spectrum estimation model and subsampled weighting algorithm

Objective.With the development of spectral CT, various spectral imaging technologies have been proposed. Among these, filter-based spectral imaging methods have been greatly advanced in recent years, such as split filters used in clinical diagnose, spectral modulators studied for spectral imaging and scatter correction. However, due to the finite size of the focal spot of x-ray source, spectral filters cause spectral mixing in the penumbra region. Traditional spectrum estimation methods fail to account for it, resulting in reduced spectral accuracy. To address this challenge, we develop a multi-ray spectrum estimation model and propose an Adaptive Subsampled WeIghting of Filter Thickness (A-SWIFT) method.Approach.First, we estimate the unfiltered spectrum using traditional methods. Next, we model the final spectra as a weighted summation of spectra attenuated by multiple filters. The weights and equivalent lengths are obtained by x-ray transmission measurements taken with altered spectra using different kVp or flat filters. Finally, the spectra are approximated by using the multi-ray model. To mimic the penumbra effect, we used a spectral modulator (0.2 mm Mo, 0.6 mm Mo), a split filter (0.07 mm Au, 0.7 mm Sn), and the abdominal images of an XCAT phantom in simulations; in experiments, we used spectral modulators made by molybdenum or copper along with a pure water phantom, a Gammex multi-energy CT phantom and a Kyoto chest phantom for validation.Main results.Simulation results show that the mean energy bias in the penumbra region decreased from 7.43 keV using the previous Spectral Compensation for Modulator (SCFM) method to 0.72 keV using the A-SWIFT method for the split filter, and from 1.98 keV to 0.61 keV for the spectral modulator. In physics experiments, for the pure water phantom with a molybdenum modulator, the average error of the mean values (ERMSE) in selected regions of interests decreased from 77 to 7 Hounsfield units (HU) using the A-SWIFT method compared with SCFM method; for the Gammex phantom,ERMSEin iodine images was 0.2 mg ml-1using A-SWIFT method, and 1.5 mg ml-1using SCFM method; for the chest phantom with an added 5 mg ml-1iodine cylinder, the estimated material density of the iodine inserts was 5.0 mg ml-1using A-SWIFT method, and 5.9 mg ml-1using SCFM method.Significance.Based on a multi-ray spectrum estimation model, the A-SWIFT method provides an accurate and robust spectrum estimation in the penumbra region, contributing to enhanced spectral imaging performance of CT systems utilizing spectral filters.

Improved noise reduction in photon-counting detector CT using prior knowledge-aware iterative denoising neural network

Purpose

We aim to reduce image noise in high-resolution (HR) virtual monoenergetic images (VMIs) from photon-counting detector (PCD) CT scans by developing a prior knowledge-aware iterative denoising neural network (PKAID-Net) that efficiently exploits the unique noise characteristics of VMIs at different energy (keV) levels.

Approach

PKAID-Net offers two major features: first, it utilizes a lower-noise VMI (e.g., 70 keV) as a prior input; second, it iteratively constructs a refined training dataset to improve the neural network's denoising performance. In each iteration, the denoised image from the previous module serves as an updated target image, which is included in the dataset for the subsequent training iteration. Our study includes 10 patient coronary CT angiography exams acquired on a clinical dual-source PCD-CT (NAEOTOM Alpha, Siemens Healthineers). The HR VMIs were reconstructed at 50, 70, and 100 keV, using a sharp vascular kernel (Bv68) and thin (0.6 mm) slice thickness (0.3 mm increment). PKAID-Net's performance was evaluated in terms of image noise, spatial detail preservation, and quantitative accuracy.

Results

PKAID-Net achieved a noise reduction of 96% compared to filtered back projection and 65% relative to iterative reconstruction, all while preserving spatial and spectral fidelity and maintaining a natural noise texture. The iterative refinement of PCD-CT data during the training process substantially enhanced the robustness of deep learning-based denoising compared to the original method, which resulted in some spatial detail loss.

Conclusions

The PKAID-Net provides substantial noise reduction while maintaining spatial and spectral fidelity of the HR VMIs from PCD-CT.

Advanced mathematical modeling for preciseestimation of CT energy spectrum using a calibration phantom

PURPOSE

This research aims to develop an advanced mathematical model using a CT calibration phantom to accurately estimate the CT energy spectrum in clinical settings, enhancing imaging quality and patient dose management.

METHODS

Data were collected from a CT scanner using a CT calibration phantom at various energy levels (80, 100, 120, and 135 kVp). The data was optimized to refine the energy spectrum model, followed by cross-validation with Monte Carlo simulations.

RESULTS

The developed model demonstrated high precision in estimating the CT energy spectrum at all tested energy levels, with R-squared values above 0.9738 and an R-squared value of 0.9829 at 100 kVp. The model also showed low Normalized Root Mean Square Deviation (NRMSD) ranging from 0.6698 % to 1.8745 %. The Mean Energy Difference (ΔE) between the estimated and simulated spectrum consistently remained under 0.01 keV. These results were comparable to recent studies, which reported higher NRMSD and ΔE.

CONCLUSIONS

This study presents a significantly improved model for estimating the CT energy spectrum, offering greater accuracy than existing models. Its strengths include high precision and the use of standard equipment and algorithmic values. While the current use of 13 plugs is adequate, incorporating plugs with varied densities could enhance accuracy. This model has potential for improving imaging quality and optimizing patient dosing in clinical applications. Future trends may include extending energy spectrum estimation to megavoltage domains and integrating technologies like EPID and MVCT for better dose distribution prediction in high-energy photon beam therapy.

Prior image-based generative adversarial learning for multi-material decomposition in photon counting computed tomography

BACKGROUND

Photon counting detector computed tomography (PCD-CT) is a novel promising technique providing higher spatial resolution, lower radiation dose and greater energy spectrum differentiation, which create more possibilities to improve image quality. Multi-material decomposition is an attractive application for PCD-CT to identify complicated materials and provide accurate quantitative analysis. However, limited by the finite photon counting rate in each energy window of photon counting detector, the noise problem hinders the decomposition of high-quality basis material images.

METHODS

To address this issue, an end-to-end multi-material decomposition network based on prior images is proposed in this paper. First, the reconstructed images corresponding to the full spectrum with less noise are introduced as prior information to improve the overall signal-to-noise ratio of the data. Then, a generative adversarial network is designed to mine the relationship between reconstructed images and basis material images based on the information interaction of material decomposition. Furthermore, a weighted edge loss is introduced to adapt to the structural differences of different basis material images.

RESULTS

To verify the performance of the proposed method, simulation and real studies are carried out. In simulation study of structured fibro-glandular tissue model, the results show that the proposed method decreased the root mean square error by 67 % and 26 % on adipose, 66 % and 28 % on fibroglandular, 52 % and 8 % on calcification, compared to butterfly network and dual interactive Wasserstein generative adversarial network.

CONCLUSION

Experimentally, the proposed method shows certain advantages over other methods on noise suppression effect, detail retention ability and decomposition accuracy.

An indirect estimation of x-ray spectrum via convolutional neural network and transmission measurement

Objective.In this work, we aim to propose an accurate and robust spectrum estimation method by synergistically combining x-ray imaging physics with a convolutional neural network (CNN).Approach.The approach relies on transmission measurements, and the estimated spectrum is formulated as a convolutional summation of a few model spectra generated using Monte Carlo simulation. The difference between the actual and estimated projections is utilized as the loss function to train the network. We contrasted this approach with the weighted sums of model spectra approach previously proposed. Comprehensive studies were performed to demonstrate the robustness and accuracy of the proposed approach in various scenarios.Main results.The results show the desirable accuracy of the CNN-based method for spectrum estimation. The ME and NRMSE were -0.021 keV and 3.04% for 80 kVp, and 0.006 keV and 4.44% for 100 kVp, superior to the previous approach. The robustness test and experimental study also demonstrated superior performances. The CNN-based approach yielded remarkably consistent results in phantoms with various material combinations, and the CNN-based approach was robust concerning spectrum generators and calibration phantoms.Significance. We proposed a method for estimating the real spectrum by integrating a deep learning model with real imaging physics. The results demonstrated that this method was accurate and robust in estimating the spectrum, and it is potentially helpful for broad x-ray imaging tasks.

Constrained one-step material decomposition reconstruction of head CT data from a silicon photon-counting prototype

BACKGROUND

Spectral CT material decomposition provides quantitative information but is challenged by the instability of the inversion into basis materials. We have previously proposed the constrained One-Step Spectral CT Image Reconstruction (cOSSCIR) algorithm to stabilize the material decomposition inversion by directly estimating basis material images from spectral CT data. cOSSCIR was previously investigated on phantom data.

PURPOSE

This study investigates the performance of cOSSCIR using head CT datasets acquired on a clinical photon-counting CT (PCCT) prototype. This is the first investigation of cOSSCIR for large-scale, anatomically complex, clinical PCCT data. The cOSSCIR decomposition is preceded by a spectrum estimation and nonlinear counts correction calibration step to address nonideal detector effects.

METHODS

Head CT data were acquired on an early prototype clinical PCCT system using an edge-on silicon detector with eight energy bins. Calibration data of a step wedge phantom were also acquired and used to train a spectral model to account for the source spectrum and detector spectral response, and also to train a nonlinear counts correction model to account for pulse pileup effects. The cOSSCIR algorithm optimized the bone and adipose basis images directly from the photon counts data, while placing a grouped total variation (TV) constraint on the basis images. For comparison, basis images were also reconstructed by a two-step projection-domain approach of Maximum Likelihood Estimation (MLE) for decomposing basis sinograms, followed by filtered backprojection (MLE + FBP) or a TV minimization algorithm (MLE + TVmin ) to reconstruct basis images. We hypothesize that the cOSSCIR approach will provide a more stable inversion into basis images compared to two-step approaches. To investigate this hypothesis, the noise standard deviation in bone and soft-tissue regions of interest (ROIs) in the reconstructed images were compared between cOSSCIR and the two-step methods for a range of regularization constraint settings.

RESULTS

cOSSCIR reduced the noise standard deviation in the basis images by a factor of two to six compared to that of MLE + TVmin , when both algorithms were constrained to produce images with the same TV. The cOSSCIR images demonstrated qualitatively improved spatial resolution and depiction of fine anatomical detail. The MLE + TVmin algorithm resulted in lower noise standard deviation than cOSSCIR for the virtual monoenergetic images (VMIs) at higher energy levels and constraint settings, while the cOSSCIR VMIs resulted in lower noise standard deviation at lower energy levels and overall higher qualitative spatial resolution. There were no statistically significant differences in the mean values within the bone region of images reconstructed by the studied algorithms. There were statistically significant differences in the mean values within the soft-tissue region of the reconstructed images, with cOSSCIR producing mean values closer to the expected values.

CONCLUSIONS

The cOSSCIR algorithm, combined with our previously proposed spectral model estimation and nonlinear counts correction method, successfully estimated bone and adipose basis images from high resolution, large-scale patient data from a clinical PCCT prototype. The cOSSCIR basis images were able to depict fine anatomical details with a factor of two to six reduction in noise standard deviation compared to that of the MLE + TVmin two-step approach.

Pie-Net: Prior-information-enabled deep learning noise reduction for coronary CT angiography acquired with a photon counting detector CT

BACKGROUND

Photon-counting-detector CT (PCD-CT) enables the production of virtual monoenergetic images (VMIs) at a high spatial resolution (HR) via simultaneous acquisition of multi-energy data. However, noise levels in these HR VMIs are markedly increased.

PURPOSE

To develop a deep learning technique that utilizes a lower noise VMI as prior information to reduce image noise in HR, PCD-CT coronary CT angiography (CTA).

METHODS

Coronary CTA exams of 10 patients were acquired using PCD-CT (NAEOTOM Alpha, Siemens Healthineers). A prior-information-enabled neural network (Pie-Net) was developed, treating one lower-noise VMI (e.g., 70 keV) as a prior input and one noisy VMI (e.g., 50 keV or 100 keV) as another. For data preprocessing, noisy VMIs were reconstructed by filtered back-projection (FBP) and iterative reconstruction (IR), which were then subtracted to generate "noise-only" images. Spatial decoupling was applied to the noise-only images to mitigate overfitting and improve randomization. Thicker slice averaging was used for the IR and prior images. The final training inputs for the convolutional neural network (CNN) inside the Pie-Net consisted of thicker-slice signal images with the reinsertion of spatially decoupled noise-only images and the thicker-slice prior images. The CNN training labels consisted of the corresponding thicker-slice label images without noise insertion. Pie-Net's performance was evaluated in terms of image noise, spatial detail preservation, and quantitative accuracy, and compared to a U-net-based method that did not include prior information.

RESULTS

Pie-Net provided strong noise reduction, by 95 ± 1% relative to FBP and by 60 ± 8% relative to IR. For HR VMIs at different keV (e.g., 50 keV or 100 keV), Pie-Net maintained spatial and spectral fidelity. The inclusion of prior information from the PCD-CT data in the spectral domain was able to improve a robust deep learning-based denoising performance compared to the U-net-based method, which caused some loss of spatial detail and introduced some artifacts.

CONCLUSION

The proposed Pie-Net achieved substantial noise reduction while preserving HR VMI's spatial and spectral properties.

Joint Reconstruction and Spectrum Refinement for Photon-Counting-Detector Spectral CT

Photon-counting detector CT (PCD-CT) is a revolutionary technology in decades in the field of CT. Its potential benefits in lowering noise, dose reduction, and material-specific imaging enable completely new clinical applications. Spectral reconstruction of basis material maps requires knowledge of the x-ray spectrum and the spectral response calibration of the detector. However, spectrum estimation errors caused by inaccurate energy threshold calibration will degrade the accuracy of the reconstructions. Existing spectrum estimation methods are not adequately modeled for bias in energy threshold position. Besides, directly solving a big number of variables of the pixel-wise effective spectra for PCD is an ill-conditioned problem so that stable solution is hardly achievable. In this paper, we assumed the effective spectra variation across the detector mainly comes from the calibration error in the energy threshold positions as well as the intrinsic threshold distribution. We propose a joint reconstruction and spectrum refinement algorithm (JoSR) that introduces an innovative spectrum model based on non-negative matrix factorization (NMF) to significantly reduce the dimension of unknowns so that makes the problem well-conditioned. The polychromatic spectral imaging model and the basis material decomposition method together form an optimization objective. The proximal regularized block coordinate descent algorithm is adopted to deal with the non-convex optimization problem to ensure convergence. Simulation studies and experiments on a laboratory PCD-CT system validated the proposed JoSR method. The results demonstrate its advantages on image quality and quantitative accuracy over other state-of-the-art methods in the field.

Exploring Dual-Energy CT Spectral Information for Machine Learning-Driven Lesion Diagnosis in Pre-Log Domain

In this study, we proposed a computer-aided diagnosis (CADx) framework under dual-energy spectral CT (DECT), which operates directly on the transmission data in the pre-log domain, called CADxDE, to explore the spectral information for lesion diagnosis. The CADxDE includes material identification and machine learning (ML) based CADx. Benefits from DECT's capability of performing virtual monoenergetic imaging with the identified materials, the responses of different tissue types (e.g., muscle, water, and fat) in lesions at each energy can be explored by ML for CADx. Without losing essential factors in the DECT scan, a pre-log domain model-based iterative reconstruction is adopted to obtain decomposed material images, which are then used to generate the virtual monoenergetic images (VMIs) at selected n energies. While these VMIs have the same anatomy, their contrast distribution patterns contain rich information along with the n energies for tissue characterization. Thus, a corresponding ML-based CADx is developed to exploit the energy-enhanced tissue features for differentiating malignant from benign lesions. Specifically, an original image-driven multi-channel three-dimensional convolutional neural network (CNN) and extracted lesion feature-based ML CADx methods are developed to show the feasibility of CADxDE. Results from three pathologically proven clinical datasets showed 4.01% to 14.25% higher AUC (area under the receiver operating characteristic curve) scores than the scores of both the conventional DECT data (high and low energy spectrum separately) and the conventional CT data. The mean gain >9.13% in AUC scores indicated that the energy spectral-enhanced tissue features from CADxDE have great potential to improve lesion diagnosis performance.

Multislice input for 2D and 3D residual convolutional neural network noise reduction in CT

Purpose

Deep convolutional neural network (CNN)-based methods are increasingly used for reducing image noise in computed tomography (CT). Current attempts at CNN denoising are based on 2D or 3D CNN models with a single- or multiple-slice input. Our work aims to investigate if the multiple-slice input improves the denoising performance compared with the single-slice input and if a 3D network architecture is better than a 2D version at utilizing the multislice input.

Approach

Two categories of network architectures can be used for the multislice input. First, multislice images can be stacked channel-wise as the multichannel input to a 2D CNN model. Second, multislice images can be employed as the 3D volumetric input to a 3D CNN model, in which the 3D convolution layers are adopted. We make performance comparisons among 2D CNN models with one, three, and seven input slices and two versions of 3D CNN models with seven input slices and one or three output slices. Evaluation was performed on liver CT images using three quantitative metrics with full-dose images as reference. Visual assessment was made by an experienced radiologist.

Results

When the input channels of the 2D CNN model increases from one to three to seven, a trend of improved performance was observed. Comparing the three models with the seven-slice input, the 3D CNN model with a one-slice output outperforms the other models in terms of noise texture and homogeneity in liver parenchyma as well as subjective visualization of vessels.

Conclusions

We conclude the that multislice input is an effective strategy for improving performance for 2D deep CNN denoising models. The pure 3D CNN model tends to have a better performance than the other models in terms of continuity across axial slices, but the difference was not significant compared with the 2D CNN model with the same number of slices as the input.

CT Image Features Based on the Reconstruction Algorithm for Continuous Blood Purification Combined with Nursing Intervention in the Treatment of Severe Acute Pancreatitis

The aim of the study was to explore the CT images of the iterative reconstruction algorithm to evaluate the curative effect of continuous blood purification combined with nursing intervention in the treatment of severe acute pancreatitis (SAP). A total of 100 patients with SAP treated by the bedside continuous venous hemofiltration purification method in a hospital were selected. The control group (n = 50) was given a routine treatment, and the observation group (n = 50) was treated with the continuous blood filtration mode for blood purification based on the routine treatment. In the CT image scanning of periodontitis patients, the iterative reconstruction algorithm was introduced to reduce image noise, and the CT values under the algorithm were statistically analyzed. The results showed that IL-1, IL-6, and IL-8 after treatment were significantly lower than those before treatment (P < 0.05). The symptoms effectively improved with continuous blood purification combined with nursing intervention in patients with SAP. After the use of the iterative reconstruction algorithm, the image quality, image information, and image MSE significantly improved. The image noise with 50% dose reduction was the lowest, but the reconstruction algorithm improved the low contrast resolution (P < 0.05). CT images based on the reconstruction algorithm can clearly display the lesion characteristics of the patients, and the reconstruction algorithm is feasible to improve the spatial resolution of CT images.

Effect of Interventional Therapy on Iliac Venous Compression Syndrome Evaluated and Diagnosed by Artificial Intelligence Algorithm-Based Ultrasound Images

In order to explore the efficacy of using artificial intelligence (AI) algorithm-based ultrasound images to diagnose iliac vein compression syndrome (IVCS) and assist clinicians in the diagnosis of diseases, the characteristics of vein imaging in patients with IVCS were summarized. After ultrasound image acquisition, the image data were preprocessed to construct a deep learning model to realize the position detection of venous compression and the recognition of benign and malignant lesions. In addition, a dataset was built for model evaluation. The data came from patients with thrombotic chronic venous disease (CVD) and deep vein thrombosis (DVT) in hospital. The image feature group of IVCS extracted by cavity convolution was the artificial intelligence algorithm imaging group, and the ultrasound images were directly taken as the control group without processing. Digital subtraction angiography (DSA) was performed to check the patient's veins one week in advance. Then, the patients were rolled into the AI algorithm imaging group and control group, and the correlation between May-Thurner syndrome (MTS) and AI algorithm imaging was analyzed based on DSA and ultrasound results. Satisfaction of intestinal venous stenosis (or occlusion) or formation of collateral circulation was used as a diagnostic index for MTS. Ultrasound showed that the AI algorithm imaging group had a higher percentage of good treatment effects than that of the control group. The call-up rate of the DMRF-convolutional neural network (CNN), precision, and accuracy were all superior to those of the control group. In addition, the degree of venous swelling of patients in the artificial intelligence algorithm imaging group was weak, the degree of pain relief was high after treatment, and the difference between the artificial intelligence algorithm imaging group and control group was statistically considerable (p < 0.005). Through grouped experiments, it was found that the construction of the AI imaging model was effective for the detection and recognition of lower extremity vein lesions in ultrasound images. To sum up, the ultrasound image evaluation and analysis using AI algorithm during MTS treatment was accurate and efficient, which laid a good foundation for future research, diagnosis, and treatment.

An X-ray spectrum estimation method from transmission measurement combined with scatter correction

PURPOSE

Conventional x-ray spectrum estimation methods from transmission measurement often lead to inaccurate results when extensive x-ray scatter is present in the measured projection. This study aims to apply the weighted L1-norm scatter correction algorithm in spectrum estimation for reducing residual differences between the estimated and true spectrum.

METHOD

The scatter correction algorithm is based on a simple radiographic scattering model where the intensity of scattered x-ray is directly estimated from a transmission measurement. Then, the scatter-corrected measurement is used for the spectrum estimation method that consists of deciding the weights of predefined spectra and representing the spectrum as a linear combination of the predefined spectra with the weights. The performances of the estimation method combined with scatter correction are evaluated on both simulated and experimental data.

RESULTS

The results show that the estimated spectra using the scatter-corrected projection nearly match the true spectra. The normalized-root-mean-square-error and the mean energy difference between the estimated spectra and corresponding true spectra are reduced from 5.8% and 1.33 keV without the scatter correction to 3.2% and 0.73 keV with the scatter correction for both simulation and experimental data, respectively.

CONCLUSIONS

The proposed method is more accurate for the acquisition of x-ray spectrum than the estimation method without scatter correction and the spectrum can be successfully estimated even the materials of the filters and their thicknesses are unknown. The proposed method has the potential to be used in several diagnostic x-ray imaging applications.

Spectral CT imaging method based on blind separation of polychromatic projections with Poisson prior

The linear reconstruction of narrow-energy-width projections can suppress hardening artifacts in conventional computed tomography (CT). We develop a spectral CT blind separation algorithm for obtaining narrow-energy-width projections under a blind scenario where the incident spectra are unknown. The algorithm relies on an X-ray multispectral forward model. Based on the Poisson statistical properties of measurements, a constrained optimization problem is established and solved by a block coordinate descent algorithm that alternates between nonnegative matrix factorization and Gauss-Newton algorithm. Experiments indicate that the decomposed projections conform to the characteristics of narrow-energy-width projections. The new algorithm improves the accuracy of obtaining narrow-energy-width projections.