Iterative Reconstruction Research Articles

CT image quality and dose optimization by combining tube voltage, dose reduction setting and ASIR-V (explorative study using VCT phantom)

Utilization of ASIR-V software to improve CT scan images with lower exposure factor settings has enormous potential to produce CT scan images with minimal dose and optimal image quality. Otherwise, the excessive use of iterative reconstruction may lead to poor image quality. The purpose of this study was to determine the differences in radiation dose and image quality in the combination of tube voltage, dose reduction and ASIR-V settings and giving recommendation out of it. This type of research is quasi-experimental with a pretest posttest design. VCT Quality Assurance phantom scanned with abdominal CT parameters with the combination of tube voltage variations and dose reduction settings then reconstructed using ASIR-V. Image quality data including noise, LCD and HCR obtained were analyzed by using the paired t-test statistical test. The lowest dose (2.01 mGy) resulted from the combination of tube voltage setting 80 kV, 60% dose reduction, and the dose reduction in the treatment group was in the range of 49% - 87%. The lowest noise was produced by a combination of tube voltage settings of 80 kV, 60% dose reduction, and 100% ASIR-V and noise reduction in the treatment group in the range of 15% -68%. There are significant differences in low contrast detectability of image obtained from 15 combination of tube voltage settings, and dose reduction setting after ASIR-V reconstruction on CT scans. Meanwhile, there are significant differences of extreme contrast spatial resolution in 13 combinations of the tube voltage and dose reduction setting after ASIR-V reconstruction showed. Decreasing the tube voltage and increasing the dose reduction value results in a lesser radiation dose accompanied by a decrease in image quality, while the application of ASIR-V is proven to improve the quality of CT scan images including noise and low contrast detectability, in the other hand the excessive use of ASIR-V may also decrease high contrast spatial resolution of the image. The combination of image quality that is closest to the image quality of the control group is a combination of tube voltage settings of 120 kV, 60% dose reduction and 60% ASIR-V which produces a radiation dose of 6.37 mGy.

Synthetic hematocrit from virtual non-contrast images for myocardial extracellular volume evaluation with photon-counting detector CT.

To assess the accuracy of a synthetic hematocrit derived from virtual non-contrast (VNC) and virtual non-iodine images (VNI) for myocardial extracellular volume (ECV) computation with photon-counting detector computed tomography (PCD-CT). Consecutive patients undergoing PCD-CT including a coronary CT angiography (CCTA) and a late enhancement (LE) scan and having a blood hematocrit were retrospectively included. In the first 75 patients (derivation cohort), CCTA and LE scans were reconstructed as VNI at 60, 70, and 80 keV and as VNC with quantum iterative reconstruction (QIR) strengths 2, 3, and 4. Blood pool attenuation (BPmean) was correlated to blood hematocrit. In the next 50 patients (validation cohort), synthetic hematocrit was calculated using BPmean. Myocardial ECV was computed using the synthetic hematocrit and compared with the ECV using the blood hematocrit as a reference. In the derivation cohort (49 men, mean age 79 ± 8 years), a correlation between BPmean and blood hematocrit ranged from poor for VNI of CCTA at 80 keV, QIR2 (R2 = 0.12) to moderate for VNI of LE at 60 keV, QIR4; 70 keV, QIR3 and 4; and VNC of LE, QIR3 and 4 (all, R2 = 0.58). In the validation cohort (29 men, age 75 ± 14 years), synthetic hematocrit was calculated from VNC of the LE scan, QIR3. Median ECV was 26.9% (interquartile range (IQR), 25.5%, 28.8%) using the blood hematocrit and 26.8% (IQR, 25.4%, 29.7%) using synthetic hematocrit (VNC, QIR3; mean difference, -0.2%; limits of agreement, -2.4%, 2.0%; p = 0.33). Synthetic hematocrit calculated from VNC images enables an accurate computation of myocardial ECV with PCD-CT. Virtual non-contrast images from cardiac late enhancement scans with photon-counting detector CT allow the calculation of a synthetic hematocrit, which enables accurate computation of myocardial extracellular volume. Blood hematocrit is mandatory for conventional myocardial extracellular volume computation. Synthetic hematocrit can be calculated from virtual non-iodine and non-contrast photon-counting detector CT images. Synthetic hematocrit from virtual non-contrast images enables computation of the myocardial extracellular volume.

Joint-learning-based coded aperture compressive temporal imaging

Coded aperture compressive temporal imaging (CACTI) is a recently developed imaging technique based on the theory of compressed sensing. It uses an optical imaging system to sample a high-speed dynamic scene (a set of consecutive video frames), integrates the sampled data in time according to masks (sensing matrix), and thus obtains compressive measurements. Considerable effort has been devoted to the sampling strategy and the ill-posed inverse process of reconstructing a three-dimensional (3D) high-speed dynamic scene from two-dimensional (2D) compressive measurements. The importance of the reconstruction algorithm and the optimization mask is evident. In this paper, a flexible, efficient, and superior quality Landweber iterative method is proposed for video reconstruction through jointly learning the optimal binary mask strategy, relaxation strategy, and regularization strategy. To solve the sparse representation problem in iteration, multiple denoisers are introduced to obtain more regularization prior information. By combining the mathematical structure of the Landweber iterative reconstruction method with deep learning, the challenging parameter selection procedure is successfully tackled. Extensive experimental results demonstrate the superiority of the proposed method.

Comparison of image quality between Deep learning image reconstruction and Iterative reconstruction technique for CT Brain- a pilot study.

Non-contrast Computed Tomography (NCCT) plays a pivotal role in assessing central nervous system disorders and is a crucial diagnostic method. Iterative reconstruction (IR) methods have enhanced image quality (IQ) but may result in a blotchy appearance and decreased resolution for subtle contrasts. The deep-learning image reconstruction (DLIR) algorithm, which integrates a convolutional neural network (CNN) into the reconstruction process, generates high-quality images with minimal noise. Hence, the objective of this study was to assess the IQ of the Precise Image (DLIR) and the IR technique (iDose 4) for the NCCT brain. This is a prospective study. Thirty patients who underwent NCCT brain were included. The images were reconstructed using DLIR-standard and iDose 4. Qualitative IQ analysis parameters, such as overall image quality (OQ), subjective image noise (SIN), and artifacts, were measured. Quantitative IQ analysis parameters such as Computed Tomography (CT) attenuation (HU), image noise (IN), posterior fossa index (PFI), signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) in the basal ganglia (BG) and centrum-semiovale (CSO) were measured. Paired t-tests were performed for qualitative and quantitative IQ analyses between the iDose 4 and DLIR-standard. Kappa statistics were used to assess inter-observer agreement for qualitative analysis. Quantitative IQ analysis showed significant differences (p<0.05) in IN, SNR, and CNR between the iDose 4 and DLIR-standard at the BG and CSO levels. IN was reduced (41.8-47.6%), SNR (65-82%), and CNR (68-78.8%) were increased with DLIR-standard. PFI was reduced (27.08%) the DLIR-standard. Qualitative IQ analysis showed significant differences (p<0.05) in OQ, SIN, and artifacts between the DLIR standard and iDose 4. The DLIR standard showed higher qualitative IQ scores than the iDose 4. DLIR standard yielded superior quantitative and qualitative IQ compared to the IR technique (iDose4). The DLIR-standard significantly reduced the IN and artifacts compared to iDose 4 in the NCCT brain.

TomoPyUI: a user-friendly tool for rapid tomography alignment and reconstruction.

The management and processing of synchrotron and neutron computed tomography data can be a complex, labor-intensive and unstructured process. Users devote substantial time to both manually processing their data (i.e. organizing data/metadata, applying image filters etc.) and waiting for the computation of iterative alignment and reconstruction algorithms to finish. In this work, we present a solution to these problems: TomoPyUI, a user interface for the well known tomography data processing package TomoPy. This highly visual Python software package guides the user through the tomography processing pipeline from data import, preprocessing, alignment and finally to 3D volume reconstruction. The TomoPyUI systematic intermediate data and metadata storage system improves organization, and the inspection and manipulation tools (built within the application) help to avoid interrupted workflows. Notably, TomoPyUI operates entirely within a Jupyter environment. Herein, we provide a summary of these key features of TomoPyUI, along with an overview of the tomography processing pipeline, a discussion of the landscape of existing tomography processing software and the purpose of TomoPyUI, and a demonstration of its capabilities for real tomography data collected at SSRL beamline 6-2c.

Effect of Model-Based Iterative Reconstruction on Image Quality of Chest Computed Tomography for COVID-19 Pneumonia.

This study aimed to compare the image quality of chest computed tomography (CT) scans for COVID-19 pneumonia using forward-projected model-based iterative reconstruction solution-LUNG (FIRST-LUNG) with filtered back projection (FBP) and hybrid iterative reconstruction (HIR). The CT images of 44 inpatients diagnosed with COVID-19 pneumonia between December 2022 and June 2023 were retrospectively analyzed. The CT images were reconstructed using FBP, HIR, and FIRST-LUNG-MILD/STANDARD/STRONG. The CT values and noise of the lumen of the main trachea and erector spine muscle were measured for each group. Signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were calculated. Subjective evaluations included overall image quality, noise, streak artifact, visualization of normal lung structures, and abnormal CT features. One-way analysis of variance was used to compare the objective and subjective indicators among the five groups. The task-based transfer function was derived for three distinct contrasts representing anatomical structures, lower-contrast lesion, and higher-contrast lesion. The results of the study demonstrated significant differences in image noise, SNR, and CNR among the five groups (P < 0.001). The FBP images exhibited the highest levels of noise and the lowest SNR and CNR among the five groups (P < 0.001). When compared to the FBP and HIR groups, the noise was lower in the FIRST-LUNG-MILD/STANDARD/STRONG group, while the SNR and CNR were higher (P < 0.001). The subjective overall image quality score of FIRST-LUNG-MILD/STANDARD was significantly better than FBP and FIRST-LUNG-STRONG (P < 0.001). FIRST-LUNG-MILD was superior to FBP, HIR, FIRST-LUNG-STANDARD, and FIRST-LUNG-STRONG in visualizing proximal and peripheral bronchovascular and subpleural vessels (P < 0.05). Additionally, FIRST-LUNG-MILD achieved the best scores in evaluating abnormal lung structure (P < 0.001). The overall interobserver agreement was substantial (intraclass correlation coefficient = 0.891). The task-based transfer function 50% values of FIRST reconstructions are consistently higher compared to FBP and HIR. The FIRST-LUNG-MILD/STANDARD algorithm can enhance the image quality of chest CT in patients with COVID-19 pneumonia, while preserving important details of the lesions, better than the FBP and HIR algorithms. After evaluating various COVID-19 pneumonia lesions and considering the improvement in image quality, we recommend using the FIRST-LUNG-MILD reconstruction for diagnosing COVID-19 pneumonia.

A preliminary study of super-resolution deep learning reconstruction with cardiac option for evaluation of endovascular-treated intracranial aneurysms.

To investigate the usefulness of super-resolution deep learning reconstruction (SR-DLR) with cardiac option in the assessment of image quality in patients with stent-assisted coil embolization, coil embolization, and flow-diverting stent placement compared with other image reconstructions. This single-centre retrospective study included 50 patients (mean age, 59 years; range, 44-81 years; 13 men) who were treated with stent-assisted coil embolization, coil embolization, and flow-diverting stent placement between January and July 2023. The images were reconstructed using filtered back projection (FBP), hybrid iterative reconstruction (IR), and SR-DLR. The objective image analysis included image noise in the Hounsfield unit (HU), signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and full width at half maximum (FWHM). Subjectively, two radiologists evaluated the overall image quality for the visualization of the flow-diverting stent, coil, and stent. The image noise in HU in SR-DLR was 6.99 ± 1.49, which was significantly lower than that in images reconstructed with FBP (12.32 ± 3.01) and hybrid IR (8.63 ± 2.12) (P < .001). Both the mean SNR and CNR were significantly higher in SR-DLR than in FBP and hybrid IR (P < .001 and P < .001). The FWHMs for the stent (P < .004), flow-diverting stent (P < .001), and coil (P < .001) were significantly lower in SR-DLR than in FBP and hybrid IR. The subjective visual scores were significantly higher in SR-DLR than in other image reconstructions (P < .001). SR-DLR with cardiac option is useful for follow-up imaging in stent-assisted coil embolization and flow-diverting stent placement in terms of lower image noise, higher SNR and CNR, superior subjective image analysis, and less blooming artifact than other image reconstructions. SR-DLR with cardiac option allows better visualization of the peripheral and smaller cerebral arteries. SR-DLR with cardiac option can be beneficial for CT imaging of stent-assisted coil embolization and flow-diverting stent.

Impact of reconstruction parameters on the accuracy of myocardial extracellular volume quantification on a first-generation, photon-counting detector CT

BackgroundThe potential role of cardiac computed tomography (CT) has increasingly been demonstrated for the assessment of diffuse myocardial fibrosis through the quantification of extracellular volume (ECV). Photon-counting detector (PCD)-CT technology may deliver more accurate ECV quantification compared to energy-integrating detector CT. We evaluated the impact of reconstruction settings on the accuracy of ECV quantification using PCD-CT, with magnetic resonance imaging (MRI)-based ECV as reference.MethodsIn this post hoc analysis, 27 patients (aged 53.1 ± 17.2 years (mean ± standard deviation); 14 women) underwent same-day cardiac PCD-CT and MRI. Late iodine CT scans were reconstructed with different quantum iterative reconstruction levels (QIR 1−4), slice thicknesses (0.4−8 mm), and virtual monoenergetic imaging levels (VMI, 40−90 keV); ECV was quantified for each reconstruction setting. Repeated measures ANOVA and t-test for pairwise comparisons, Bland–Altman plots, and Lin’s concordance correlation coefficient (CCC) were used.ResultsECV values did not differ significantly among QIR levels (p = 1.000). A significant difference was observed throughout different slice thicknesses, with 0.4 mm yielding the highest agreement with MRI-based ECV (CCC = 0.944); 45-keV VMI reconstructions showed the lowest mean bias (0.6, 95% confidence interval 0.1–1.4) compared to MRI. Using the most optimal reconstruction settings (QIR4. slice thickness 0.4 mm, VMI 45 keV), a 63% reduction in mean bias and a 6% increase in concordance with MRI-based ECV were achieved compared to standard settings (QIR3, slice thickness 1.5 mm; VMI 65 keV).ConclusionsThe selection of appropriate reconstruction parameters improved the agreement between PCD-CT and MRI-based ECV.Relevance statementTailoring PCD-CT reconstruction parameters optimizes ECV quantification compared to MRI, potentially improving its clinical utility.Key points• CT is increasingly promising for myocardial tissue characterization, assessing focal and diffuse fibrosis via late iodine enhancement and ECV quantification, respectively.• PCD-CT offers superior performance over conventional CT, potentially improving ECV quantification and its agreement with MRI-based ECV.• Tailoring PCD-CT reconstruction parameters optimizes ECV quantification compared to MRI, potentially improving its clinical utility.Graphical

Fat suppression using frequency-sweep RF saturation and iterative reconstruction.

To introduce an alternative idea for fat suppression that is suited both for low-field applications where conventional fat-suppression approaches become ineffective due to narrow spectral separation and for applications with strong B0 homogeneities. Separation of fat and water is achieved by sweeping the frequency of RF saturation pulses during continuous radial acquisition and calculating frequency-resolved images using regularized iterative reconstruction. Voxel-wise signal-response curves are extracted that reflect tissue's response to RF saturation at different frequencies and allow the classification into fat or water. This information is then utilized to generate water-only composite images. The principle is demonstrated in free-breathing abdominal and neck examinations using stack-of-stars 3D balanced SSFP (bSSFP) and gradient-recalled echo (GRE) sequences at 0.55 and 3T. Moreover, a potential extension toward quantitative fat/water separation is described. Experiments with a proton density fat fraction (PDFF) phantom validated the reliability of fat/water separation using signal-response curves. As demonstrated for abdominal imaging at 0.55T, the approach resulted in more uniform fat suppression without loss of water signal and in improved CSF-to-fat signal ratio. Moreover, the approach provided consistent fat suppression in 3T neck exams where conventional spectrally-selective fat saturation failed due to strong local B0 inhomogeneities. The feasibility of simultaneous fat/water quantification has been demonstrated in a PDFF phantom. The proposed principle achieves reliable fat suppression in low-field applications and adapts to high-field applications with strong B0 inhomogeneity. Moreover, the principle potentially provides a basis for developing an alternative approach for PDFF quantification.

Evaluation of Single-Photon Emission Computed Tomography Myocardial Perfusion Detection Capability through Physical Descriptors

A comprehensive validation of data acquired by different myocardial perfusion imaging (MPI) systems was performed to evaluate contrast, self-attenuation properties, and perfusion detection capability. An anthropomorphic phantom with a myocardial insert and perfusion defect was used to simulate 99mTc-tetrofosmin distribution. Different MPI systems were evaluated: a SPECT system with iterative reconstruction algorithms and resolution recovery (IRR) with/without scatter correction (SPECT-IRR-SC and SPECT-IRR), and a cardio-centric IQ SPECT/CT system with IRR, with/without scatter and attenuation corrections (IQ-IRR-SC-AC and IQ-IRR). The image quality was assessed through physical descriptors: the contrast between the left ventricular (LV) wall and LV inner chamber (CLV/LVIC), intrinsic contrast (IC), and net contrast (NC). CLV/LVIC was found to be superior for IQ-IRR-SC-AC. The IC results showed non-uniformity of the signal intensity in the LV wall for the SPECT systems. The lowest IC values were obtained for IQ-IRR-SC-AC, except for septal position, where an underestimation of the signal intensity was revealed. The NC was found to be the highest for IQ-IRR-SC-AC and SPECT-IRR-SC. Additionally, for IQ-IRR-SC-AC, the NC increased in posterior and septal positions compared to IQ-IRR, enabling better perfusion detection capability over short-axis images. IQ-IRR showed performances comparable to SPECT-IRR. The characterization and evaluation perfusion detection capability of the MPI systems enabled the investigation of the systems’ performance and limitations.

Super-resolution deep-learning reconstruction for cardiac CT: impact of radiation dose and focal spot size on task-based image quality.

This study aimed to evaluate the impact of radiation dose and focal spot size on the image quality of super-resolution deep-learning reconstruction (SR-DLR) in comparison with iterative reconstruction (IR) and normal-resolution DLR (NR-DLR) algorithms for cardiac CT. Catphan-700 phantom was scanned on a 320-row scanner at six radiation doses (small and large focal spots at 1.4-4.3 and 5.8-8.8mGy, respectively). Images were reconstructed using hybrid-IR, model-based-IR, NR-DLR, and SR-DLR algorithms. Noise properties were evaluated through plotting noise power spectrum (NPS). Spatial resolution was quantified with task-based transfer function (TTF); Polystyrene, Delrin, and Bone-50% inserts were used for low-, intermediate, and high-contrast spatial resolution. The detectability index (d') was calculated. Image noise, noise texture, edge sharpness of low- and intermediate-contrast objects, delineation of fine high-contrast objects, and overall quality of four reconstructions were visually ranked. Results indicated that among four reconstructions, SR-DLR yielded the lowest noise magnitude and NPS peak, as well as the highest average NPS frequency, TTF50%, d' values, and visual rank at each radiation dose. For all reconstructions, the intermediate- to high-contrast spatial resolution was maximized at 4.3mGy, while the lowest noise magnitude and highest d' were attained at 8.8mGy. SR-DLR at 4.3mGy exhibited superior noise performance, intermediate- to high-contrast spatial resolution, d' values, and visual rank compared to the other reconstructions at 8.8mGy. Therefore, SR-DLR may yield superior diagnostic image quality and facilitate radiation dose reduction compared to the other reconstructions, particularly when combined with small focal spot scanning.

Statistical image reconstruction with beam-hardening compensation for X-ray CT by a calibration step (2DIterBH).

The beam-hardening effect due to the polychromatic nature of the X-ray spectra results in two main artifacts in CT images: cupping in homogeneous areas and dark bands between dense parts in heterogeneous samples. Post-processing methods have been proposed in the literature to compensate for these artifacts, but these methods may introduce additional noise in low-dose acquisitions. Iterative methods are an alternative to compensate noise and beam-hardening artifacts simultaneously. However, they usually rely on the knowledge of the spectrum or the selection of empirical parameters. We propose an iterative reconstruction method with beam hardening compensation for small animal scanners that is robust against low-dose acquisitions and that does not require knowledge of the spectrum, overcoming the limitations of current beam-hardening correction algorithms. The proposed method includes an empirical characterization of the beam-hardening function based on a simple phantom in a polychromatic statistical reconstruction method. Evaluation was carried out on simulated data with different noise levels and step angles and on limited-view rodent data acquired with the ARGUS/CT system. Results in small animal studies showed a proper correction of the beam-hardening artifacts in the whole sample, independently of the quantity of bone present on each slice. The proposed approach also reduced noise in the low-dose acquisitions and reduced streaks in the limited-view acquisitions. Using an empirical model for the beam-hardening effect, obtained through calibration, in an iterative reconstruction method enables a robust correction of beam-hardening artifacts in low-dose small animal studies independently of the bone distribution.

Speckle-free coherent imaging through deep turbulence.

We develop and validate a model-based iterative reconstruction framework for digitally correcting coherent images corrupted by deep turbulence. In general, this framework is applicable to coherent-imaging approaches that gain access to the complex-optical field; however, we demonstrate our approach with multi-shot digital holography data. To test our image correction framework, we generate calibrated deep-turbulence conditions from our laboratory testbed. Using the resulting data, we demonstrate groundbreaking performance in terms of speckle-free image correction in deep-turbulence conditions.

Improving diagnostic precision in amyloid brain PET imaging through data-driven motion correction

BackgroundHead motion during brain positron emission tomography (PET)/computed tomography (CT) imaging degrades image quality, resulting in reduced reading accuracy. We evaluated the performance of a head motion correction algorithm using 18F-flutemetamol (FMM) brain PET/CT images.MethodsFMM brain PET/CT images were retrospectively included, and PET images were reconstructed using a motion correction algorithm: (1) motion estimation through 3D time-domain signal analysis, signal smoothing, and calculation of motion-free intervals using a Merging Adjacent Clustering method; (2) estimation of 3D motion transformations using the Summing Tree Structural algorithm; and (3) calculation of the final motion-corrected images using the 3D motion transformations during the iterative reconstruction process. All conventional and motion-corrected PET images were visually reviewed by two readers. Image quality was evaluated using a 3-point scale, and the presence of amyloid deposition was interpreted as negative, positive, or equivocal. For quantitative analysis, we calculated the uptake ratio (UR) of 5 specific brain regions, with the cerebellar cortex as a reference region. The results of the conventional and motion-corrected PET images were statistically compared.ResultsIn total, 108 sets of FMM brain PET images from 108 patients (34 men and 74 women; median age, 78 years) were included. After motion correction, image quality significantly improved (p < 0.001), and there were no images of poor quality. In the visual analysis of amyloid deposition, higher interobserver agreements were observed in motion-corrected PET images for all specific regions. In the quantitative analysis, the UR difference between the conventional and motion-corrected PET images was significantly higher in the group with head motion than in the group without head motion (p = 0.016).ConclusionsThe motion correction algorithm provided better image quality and higher interobserver agreement. Therefore, we suggest that this algorithm be adopted as a routine post-processing protocol in amyloid brain PET/CT imaging and applied to brain PET scans with other radiotracers.

Performance of cone-beam computed tomography imaging during megavoltage beam irradiation under phase-gated conditions

PurposeTarget positions should be acquired during beam delivery for accurate lung stereotactic body radiotherapy. We aimed to perform kilovoltage (kV) imaging during beam irradiation (intra-irradiation imaging) under phase-gated conditions and evaluate its performance. MethodsCatphan 504 and QUASAR respiratory motion phantoms were used to evaluate image quality and target detectability, respectively. TrueBeam STx linac and the Developer Mode was used. The imaging parameters were 125 kVp and 1.2 mAs/projection. Flattened megavoltage (MV) X-ray beam energies 6, 10 and 15 MV and un-flattened beam energies 6 and 10 MV were used with field sizes of 5 × 5 and 15 × 15 cm2 and various frame rates for intra-irradiation imaging. In addition, using a QUASAR phantom, intra-irradiation imaging was performed during intensity-modulated plan delivery. The root-mean-square error (RMSE) of the CT-number for the inserted rods, image noise, visual assessment, and contrast-to-noise ratio (CNR) were evaluated. ResultsThe RMSEs of intra-irradiation cone-beam computed tomography (CBCT) images under gated conditions were 50–230 Hounsfield Unit (HU) (static < 30 HU). The noise of the intra-irradiation CBCT images under gated conditions was 15–35 HU, whereas that of the standard CBCT images was 8.8–27.2 HU. Lower frame rates exhibited large RMSEs and noise; however, the iterative reconstruction algorithm (IR) was effective at improving these values. Approximately 7 fps with the IR showed an equivalent CNR of 15 fps without the IR. The target was visible on all the gated intra-irradiation CBCT images. ConclusionSeveral image quality improvements are required; however, intra-irradiated CBCT images showed good visual target detection.

Iterative algorithm computational spectrometer based on a single-hidden-layer neural network.

Computational spectrometers have great application prospects in hyperspectral detection, and fast and high-precision in situ measurement is an important development trend. The computational spectrometer based on iterative algorithms has low requirements for computational resources and is easy to achieve hardware integration and in situ measurement. However, iterative algorithms are difficult to achieve high reconstruction accuracy due to the ill-posed nature of problems. Neural networks have powerful learning capabilities and can achieve high-precision spectral reconstruction. However, solely relying on neural network algorithms for reconstruction requires higher storage space and computing power from hardware devices, which makes it difficult to integrate large-scale neural network models into embedded systems. We propose using neural networks to alleviate the effect of the problem ill-posedness on the reconstruction results of iterative algorithms, so as to improve the reconstruction accuracy of the iterative algorithm computational spectrometers. First, spectral reconstruction was performed with iterative algorithms using a public spectral dataset. Then, a single-hidden-layer neural network was trained to establish a fitting relationship between the iterative algorithm spectral reconstruction results and the original spectrum. Finally, simulation and experimental results show that the proposed application of neural networks to alleviate the ill-posed problem of the iterative algorithm spectral reconstruction can effectively improve the reconstruction accuracy of iterative algorithm computational spectrometers with low computational resources. The research results may have good potential in achieving fast and high-precision in situ measurements of computational spectrometers.

Robin coefficient determination problem in a fractional parabolic differential equation

This article discusses the identification of an unknown Robin coefficient in a fractional parabolic equation using a noisy measurement of the ultimate solution over time. The problem is quite complex, involving a nonlocal, nonlinear, and ill‐posed operator. To solve this problem, the article proposes a regularized optimization approach that minimizes a least‐squares cost function. The article also examines the various conceptual and real‐world challenges associated with this problem. The article demonstrates the presence of a singular and stable solution for the optimization problem. It utilizes the Morozov discrepancy principle and the conjugate gradient method to streamline the iterative reconstruction process. The proposed method is accurate and efficient, as several numerical examples demonstrate.

Reconstruction of inhomogeneous media by an iteration algorithm with a learned projector

This paper is concerned with the inverse problem of reconstructing an inhomogeneous medium from the acoustic far-field data at a fixed frequency in two dimensions. This inverse problem is severely ill-posed (and also strongly nonlinear), and certain regularization strategy is thus needed. However, it is difficult to select an appropriate regularization strategy which should enforce some a priori information of the unknown scatterer. To address this issue, we plan to use a deep learning approach to learn some a priori information of the unknown scatterer from certain ground truth data, which is then combined with a traditional iteration method to solve the inverse problem. Specifically, we propose a deep learning-based iterative reconstruction algorithm for the inverse problem, based on a repeated application of a deep neural network and the iteratively regularized Gauss–Newton method (IRGNM). Our deep neural network (called the learned projector in this paper) mainly focuses on learning the a priori information of the shape of the unknown contrast with a normalization technique in the training processes and is trained to act like a projector which is helpful for projecting the solution into some feasible region. Extensive numerical experiments show that our reconstruction algorithm provides good reconstruction results even for the high contrast case and has a satisfactory generalization ability.

Intensity-based iterative reconstruction with cross-channel regularization for grating interferometry breast CT

This work demonstrates the successful reconstruction of phase contrast images under challenging acquisition conditions in grating interferometry breast CT (GI-BCT) with an algorithm that adds a novel regularization functional to the existing iterative-based intensity reconstruction (IBIR) algorithm. The addition of a cross-channel regularizer allows to leverage the absorption channel’s convergence to promote that of the phase channel, which otherwise struggles to converge. We demonstrate convergence of phase contrast images on both simulations and real data. This work sets a step towards a clinically compatible reconstruction procedure using cross-channel regularization for the generation of standalone phase-contrast images of breasts.

Computed Tomography Effective Dose and Image Quality in Deep Learning Image Reconstruction in Intensive Care Patients Compared to Iterative Algorithms.

Deep learning image reconstruction (DLIR) algorithms employ convolutional neural networks (CNNs) for CT image reconstruction to produce CT images with a very low noise level, even at a low radiation dose. The aim of this study was to assess whether the DLIR algorithm reduces the CT effective dose (ED) and improves CT image quality in comparison with filtered back projection (FBP) and iterative reconstruction (IR) algorithms in intensive care unit (ICU) patients. We identified all consecutive patients referred to the ICU of a single hospital who underwent at least two consecutive chest and/or abdominal contrast-enhanced CT scans within a time period of 30 days using DLIR and subsequently the FBP or IR algorithm (Advanced Modeled Iterative Reconstruction [ADMIRE] model-based algorithm or Adaptive Iterative Dose Reduction 3D [AIDR 3D] hybrid algorithm) for CT image reconstruction. The radiation ED, noise level, and signal-to-noise ratio (SNR) were compared between the different CT scanners. The non-parametric Wilcoxon test was used for statistical comparison. Statistical significance was set at p < 0.05. A total of 83 patients (mean age, 59 ± 15 years [standard deviation]; 56 men) were included. DLIR vs. FBP reduced the ED (18.45 ± 13.16 mSv vs. 22.06 ± 9.55 mSv, p < 0.05), while DLIR vs. FBP and vs. ADMIRE and AIDR 3D IR algorithms reduced image noise (8.45 ± 3.24 vs. 14.85 ± 2.73 vs. 14.77 ± 32.77 and 11.17 ± 32.77, p < 0.05) and increased the SNR (11.53 ± 9.28 vs. 3.99 ± 1.23 vs. 5.84 ± 2.74 and 3.58 ± 2.74, p < 0.05). CT scanners employing DLIR improved the SNR compared to CT scanners using FBP or IR algorithms in ICU patients despite maintaining a reduced ED.