Search

Objective. Deep learning reconstruction (DLR) algorithms exhibit object-dependent resolution and noise performance. Thus, traditional geometric CT phantoms cannot fully capture the clinical imaging performance of DLR. This study uses a patient-derived 3D-printed PixelPrint lung phantom to evaluate a commercial DLR algorithm across a wide range of radiation dose levels. Method. The lung phantom used in this study is based on a patient chest CT scan containing ground glass opacities and was fabricated using PixelPrint 3D-printing technology. The phantom was placed inside two different size extension rings to mimic a small- and medium-sized patient and was scanned on a conventional CT scanner at exposures between 0.5 and 20 mGy. Each scan was reconstructed using filtered back projection (FBP), iterative reconstruction, and DLR at five levels of denoising. Image noise, contrast to noise ratio (CNR), root mean squared error, structural similarity index (SSIM), and multi-scale SSIM (MS SSIM) were calculated for each image. Results. DLR demonstrated superior performance compared to FBP and iterative reconstruction for all measured metrics in both phantom sizes, with better performance for more aggressive denoising levels. DLR was estimated to reduce dose by 25%–83% in the small phantom and by 50%–83% in the medium phantom without decreasing image quality for any of the metrics measured in this study. These dose reduction estimates are more conservative compared to the estimates obtained when only considering noise and CNR. Conclusion. DLR has the capability of producing diagnostic image quality at up to 83% lower radiation dose, which can improve the clinical utility and viability of lower dose CT scans. Furthermore, the PixelPrint phantom used in this study offers an improved testing environment with more realistic tissue structures compared to traditional CT phantoms, allowing for structure-based image quality evaluation beyond noise and contrast-based assessments. [ABSTRACT FROM AUTHOR]

Purpose. Fast kV-switching (FKS) and dual-layer flat-panel detector (DL-FPD) technologies have been actively studied as promising dual-energy spectral imaging solutions for FPD-based cone-beam computed tomography (CT). However, cone-beam CT (CBCT) spectral imaging is known to face challenges in obtaining accurate and robust material discrimination performance. That is because the energy separation by either FKS or DL-FPD, alone, is still limited, along with apparently unpaired signal levels in the effective low- and high-energy projections in real applications, not to mention the x-ray scatter in cone-beam scan which will make the material decomposition almost impossible if no correction is applied. To further improve CBCT spectral imaging capability, this work aims to promote a source-detector joint multi-energy spectral imaging solution which takes advantages of both FKS and DL-FPD, and to conduct a feasibility study on the first tabletop CBCT system with the joint spectral imaging capability developed. Methods. For CBCT, development of multi-energy spectral imaging can be jointly realized by using an x-ray source with a generator whose kilo-voltages can alternate in tens of Hertz (i.e. FKS), and a DL-FPD whose top- and bottom-layer projections corresponds to different effective energy levels. Thanks to the complimentary characteristics inherent in FKS and DL-FPD, the overall energy separation will be significantly better when compared with FKS or DL-FPD alone, and the x-ray photon detection efficiency will be also improved when compared with FKS alone. In this work, a noise performance analysis using the Cramér–Rao lower bound (CRLB) method is conducted. The CRLB for basis material after a projection-domain material decomposition is derived, followed by a set of numerical calculations of CRLBs, for the FKS, the DL-FPD and the joint solution, respectively. To compensate for the slightly angular mismatch between low- and high- projections in FKS, a dual-domain projection completion scheme is implemented. Afterwards material decomposition from the complete projection data is carried out by using the maximum-likelihood method, followed by reconstruction of basis material and virtual monochromatic images (VMI). In this work, the first FKS and DL-FPD jointly enabled multi-energy tabletop CBCT system, to the best of our knowledge, has been developed in our laboratory. To evaluate its spectral imaging performance, a set of physics experiments are conducted, where the multi-energy and head phantoms are scanned using the 80/105/130 kVp switching pairs and projection data are collected using a prototype DL-FPD, whose both top and bottom layer of panels are composed of 550 μ m of cesium iodine (CsI) scintillators with no intermediate metal filter in-between. Results. The numerical simulations show that the joint spectral imaging solution can lead to a significant improvement in energy separation and lower noise levels in most of material decomposition cases. The physics experiments confirmed the feasibility and superiority of the joint spectral imaging, whose CNRs in the selected regions of interest of the multi-energy phantom were boosted by an average improvement of 21.9%, 20.4% for water basis images and 32.8%, 62.8% for iodine images when compared with that of the FKS and DL-FPD, respectively. For the head phantom case, the joint spectral imaging can effectively reduce the streaking artifacts as well, and the standard deviation in the selected regions of interest are reduced by an average decrement of 19.5% and 8.1% for VMI when compared with that of the FKS and DL-FPD, respectively. Conclusions. A feasibility study of the joint spectral imaging solution for CBCT by utilizing both the FKS and DL-FPD was conducted, with the first tabletop CBCT system having such a capability being developed, which exhibits improved CNR and is more effective in avoiding streaking artifacts as expected. [ABSTRACT FROM AUTHOR]

Objective. We introduce a robust image reconstruction algorithm named residual-guided Golub–Kahan iterative reconstruction technique (RGIRT) designed for sparse-view computed tomography (CT), which aims at high-fidelity image reconstruction from a limited number of projection views. Approach. RGIRT utilizes an inner-outer dual iteration framework, with a flexible least square QR (FLSQR) algorithm implemented in the inner iteration and a restarted iterative scheme applied in the outer iteration. The inner FLSQR employs a flexible Golub–Kahan bidiagonalization method to reduce the size of the inverse problem, and a weighted generalized cross-validation method to adaptively estimate the regularization hyper-parameter. The inner iteration efficiently yields the intermediate reconstruction result, while the outer iteration minimizes the residual and refines the solution by using the result obtained from the inner iteration. Main results. The reconstruction performance of RGIRT is evaluated and compared to other reference methods (FBPConvNet, SART-TV, and FLSQR) using projection data from both numerical phantoms and real experimental Micro-CT data. The experimental findings, from testing various numbers of projection views and different noise levels, underscore the robustness of RGIRT. Meanwhile, theoretical analysis confirms the convergence of residual for our approach. Significance. We propose a robust iterative reconstruction algorithm for x-ray CT scans with sparse views, thereby shortening scanning time and mitigating excessive ionizing radiation exposure to small animals. [ABSTRACT FROM AUTHOR]

The x-ray radiation dose in computed tomography (CT) examination has been a major concern for patients. Lowing the tube current and exposure time in data acquisition is a straightforward and cost-effective strategy to reduce the x-ray radiation dose. However, this will inevitably increase the noise fluctuations in measured projection data, and the corresponding CT image quality will be severely degraded if noise suppression is not performed during image reconstruction. To reconstruct high-quality low-dose CT image, we present a spatial-radon domain total generalized variation (SRDTGV) regularization for statistical iterative reconstruction based on penalized weighted least-squares (PWLS) principle, which is called PWLS-SRDTGV for simplicity. The presented PWLS-SRDTGV model can simultaneously reconstruct high-quality CT image in space domain and its corresponding projection in radon domain. An efficient split Bregman algorithm was applied to minimize the cost function of the proposed reconstruction model. Qualitative and quantitative studies were performed to evaluate the effectiveness of the PWLS-SRDTGV image reconstruction algorithm using a digital 3D XCAT phantom and an anthropomorphic torso phantom. The experimental results demonstrate that PWLS-SRDTGV algorithm achieves notable gains in noise reduction, streak artifact suppression, and edge preservation compared with competing reconstruction approaches. [ABSTRACT FROM AUTHOR]

Objective. Limited-angle computed tomography (CT) presents a challenge due to its ill-posed nature. In such scenarios, analytical reconstruction methods often exhibit severe artifacts. To tackle this inverse problem, several supervised deep learning-based approaches have been proposed. However, they are constrained by limitations such as generalization issue and the difficulty of acquiring a large amount of paired CT images. Approach. In this work, we propose an iterative neural reconstruction framework designed for limited-angle CT. By leveraging a coordinate-based neural representation, we formulate tomographic reconstruction as a convex optimization problem involving a deep neural network. We then employ differentiable projection layer to optimize this network by minimizing the discrepancy between the predicted and measured projection data. In addition, we introduce a prior-based weight initialization method to ensure the network starts optimization with an informed initial guess. This strategic initialization significantly improves the quality of iterative reconstruction by stabilizing the divergent behavior in ill-posed neural fields. Our method operates in a self-supervised manner, thereby eliminating the need for extensive data. Main results. The proposed method outperforms other iterative and learning-based methods. Experimental results on XCAT and Mayo Clinic datasets demonstrate the effectiveness of our approach in restoring anatomical features as well as structures. This finding was substantiated by visual inspections and quantitative evaluations using NRMSE, PSNR, and SSIM. Moreover, we conduct a comprehensive investigation into the divergent behavior of iterative neural reconstruction, thus revealing its suboptimal convergence when starting from scratch. In contrast, our method consistently produced accurate images by incorporating an initial estimate as informed initialization. Significance. This work showcases the feasibility to reconstruct high-fidelity CT images from limited-angle x-ray projections. The proposed methodology introduces a novel data-free approach to enhance medical imaging, holding promise across various clinical applications. [ABSTRACT FROM AUTHOR]

Objective. 3D cine-magnetic resonance imaging (cine-MRI) can capture images of the human body volume with high spatial and temporal resolutions to study anatomical dynamics. However, the reconstruction of 3D cine-MRI is challenged by highly under-sampled k-space data in each dynamic (cine) frame, due to the slow speed of MR signal acquisition. We proposed a machine learning-based framework, spatial and temporal implicit neural representation learning (STINR-MR), for accurate 3D cine-MRI reconstruction from highly under-sampled data. Approach. STINR-MR used a joint reconstruction and deformable registration approach to achieve a high acceleration factor for cine volumetric imaging. It addressed the ill-posed spatiotemporal reconstruction problem by solving a reference-frame 3D MR image and a corresponding motion model that deforms the reference frame to each cine frame. The reference-frame 3D MR image was reconstructed as a spatial implicit neural representation (INR) network, which learns the mapping from input 3D spatial coordinates to corresponding MR values. The dynamic motion model was constructed via a temporal INR, as well as basis deformation vector fields (DVFs) extracted from prior/onboard 4D-MRIs using principal component analysis. The learned temporal INR encodes input time points and outputs corresponding weighting factors to combine the basis DVFs into time-resolved motion fields that represent cine-frame-specific dynamics. STINR-MR was evaluated using MR data simulated from the 4D extended cardiac-torso (XCAT) digital phantom, as well as two MR datasets acquired clinically from human subjects. Its reconstruction accuracy was also compared with that of the model-based non-rigid motion estimation method (MR-MOTUS) and a deep learning-based method (TEMPEST). Main results. STINR-MR can reconstruct 3D cine-MR images with high temporal (<100 ms) and spatial (3 mm) resolutions. Compared with MR-MOTUS and TEMPEST, STINR-MR consistently reconstructed images with better image quality and fewer artifacts and achieved superior tumor localization accuracy via the solved dynamic DVFs. For the XCAT study, STINR reconstructed the tumors to a mean ± SD center-of-mass error of 0.9 ± 0.4 mm, compared to 3.4 ± 1.0 mm of the MR-MOTUS method. The high-frame-rate reconstruction capability of STINR-MR allows different irregular motion patterns to be accurately captured. Significance. STINR-MR provides a lightweight and efficient framework for accurate 3D cine-MRI reconstruction. It is a 'one-shot' method that does not require external data for pre-training, allowing it to avoid generalizability issues typically encountered in deep learning-based methods. [ABSTRACT FROM AUTHOR]

Objective. X-ray computed tomography employing sparse projection views has emerged as a contemporary technique to mitigate radiation dose. However, due to the inadequate number of projection views, an analytic reconstruction method utilizing filtered backprojection results in severe streaking artifacts. Recently, deep learning (DL) strategies employing image-domain networks have demonstrated remarkable performance in eliminating the streaking artifact caused by analytic reconstruction methods with sparse projection views. Nevertheless, it is difficult to clarify the theoretical justification for applying DL to sparse view computed tomography (CT) reconstruction, and it has been understood as restoration by removing image artifacts, not reconstruction. Approach. By leveraging the theory of deep convolutional framelets (DCF) and the hierarchical decomposition of measurement, this research reveals the constraints of conventional image and projection-domain DL methodologies, subsequently, the research proposes a novel dual-domain DL framework utilizing hierarchical decomposed measurements. Specifically, the research elucidates how the performance of the projection-domain network can be enhanced through a low-rank property of DCF and a bowtie support of hierarchical decomposed measurement in the Fourier domain. Main results. This study demonstrated performance improvement of the proposed framework based on the low-rank property, resulting in superior reconstruction performance compared to conventional analytic and DL methods. Significance. By providing a theoretically justified DL approach for sparse-view CT reconstruction, this study not only offers a superior alternative to existing methods but also opens new avenues for research in medical imaging. It highlights the potential of dual-domain DL frameworks to achieve high-quality reconstructions with lower radiation doses, thereby advancing the field towards safer and more efficient diagnostic techniques. The code is available at https://github.com/hanyoseob/HDD-DL-for-SVCT. [ABSTRACT FROM AUTHOR]

Objective. Computed Tomography (CT) has been widely used in industrial high-resolution non-destructive testing. However, it is difficult to obtain high-resolution images for large-scale objects due to their physical limitations. The objective is to develop an improved super-resolution technique that preserves small structures and details while efficiently capturing high-frequency information. Approach. The study proposes a new deep learning based method called spectrum learning (SPEAR) network for CT images super-resolution. This approach leverages both global information in the image domain and high-frequency information in the frequency domain. The SPEAR network is designed to reconstruct high-resolution images from low-resolution inputs by considering not only the main body of the images but also the small structures and other details. The symmetric property of the spectrum is exploited to reduce weight parameters in the frequency domain. Additionally, a spectrum loss is introduced to enforce the preservation of both high-frequency components and global information. Main results. The network is trained using pairs of low-resolution and high-resolution CT images, and it is fine-tuned using additional low-dose and normal-dose CT image pairs. The experimental results demonstrate that the proposed SPEAR network outperforms state-of-the-art networks in terms of image reconstruction quality. The approach successfully preserves high-frequency information and small structures, leading to better results compared to existing methods. The network's ability to generate high-resolution images from low-resolution inputs, even in cases of low-dose CT images, showcases its effectiveness in maintaining image quality. Significance. The proposed SPEAR network's ability to simultaneously capture global information and high-frequency details addresses the limitations of existing methods, resulting in more accurate and informative image reconstructions. This advancement can have substantial implications for various industries and medical diagnoses relying on accurate imaging. [ABSTRACT FROM AUTHOR]

Objective. Incorporating computed tomography (CT) reconstruction operators into differentiable pipelines has proven beneficial in many applications. Such approaches usually focus on the projection data and keep the acquisition geometry fixed. However, precise knowledge of the acquisition geometry is essential for high quality reconstruction results. In this paper, the differentiable formulation of fan-beam CT reconstruction is extended to the acquisition geometry. Approach. The CT fan-beam reconstruction is analytically derived with respect to the acquisition geometry. This allows to propagate gradient information from a loss function on the reconstructed image into the geometry parameters. As a proof-of-concept experiment, this idea is applied to rigid motion compensation. The cost function is parameterized by a trained neural network which regresses an image quality metric from the motion-affected reconstruction alone. Main results. The algorithm improves the structural similarity index measure (SSIM) from 0.848 for the initial motion-affected reconstruction to 0.946 after compensation. It also generalizes to real fan-beam sinograms which are rebinned from a helical trajectory where the SSIM increases from 0.639 to 0.742. Significance. Using the proposed method, we are the first to optimize an autofocus-inspired algorithm based on analytical gradients. Next to motion compensation, we see further use cases of our differentiable method for scanner calibration or hybrid techniques employing deep models. [ABSTRACT FROM AUTHOR]

Objective. Fluorescence molecular tomography (FMT) is an optical imaging modality that provides high sensitivity and low cost, which can offer the three-dimensional distribution of biomarkers by detecting the fluorescently labeled probe noninvasively. In the field of preclinical cancer diagnosis and treatment, FMT has gained significant traction. Nonetheless, the current FMT reconstruction results suffer from unsatisfactory morphology and location accuracy of the fluorescence distribution, primarily due to the light scattering effect and the ill-posed nature of the inverse problem. Approach. To address these challenges, a regularized reconstruction method based on joint smoothly clipped absolute deviation regularization and graph manifold learning (SCAD-GML) for FMT is presented in this paper. The SCAD-GML approach combines the sparsity of the fluorescent sources with the latent manifold structure of fluorescent source distribution to achieve more accurate and sparse reconstruction results. To obtain the reconstruction results efficiently, the non-convex gradient descent iterative method is employed to solve the established objective function. To assess the performance of the proposed SCAD-GML method, a comprehensive evaluation is conducted through numerical simulation experiments as well as in vivo experiments. Main results. The results demonstrate that the SCAD-GML method outperforms other methods in terms of both location and shape recovery of fluorescence biomarkers distribution. Siginificance. These findings indicate that the SCAD-GML method has the potential to advance the application of FMT in in vivo biological research. [ABSTRACT FROM AUTHOR]

Objective. Low-dose CT (LDCT) is an important research topic in the field of CT imaging because of its ability to reduce radiation damage in clinical diagnosis. In recent years, deep learning techniques have been widely applied in LDCT imaging and a large number of denoising methods have been proposed. However, One major challenge of supervised deep learning-based methods is the exactly geometric pairing of datasets with different doses. Therefore, the aim of this study is to develop an unsupervised learning-based LDCT imaging method to address the aforementioned challenges. Approach. In this paper, we propose an unsupervised learning-based dual-domain method for LDCT denoising, which consists of two stages: the first stage is projection domain denoising, in which the unsupervised learning method Noise2Self is applied to denoise the projection data with statistically independent and zero-mean noise. The second stage is an iterative enhancement approach, which combines the prior information obtained from the generative model with an iterative reconstruction algorithm to enhance the details of the reconstructed image. Main results. Experimental results show that our proposed method outperforms the comparison method in terms of denoising effect. Particularly, in terms of SSIM, the denoised results obtained using our method achieve the highest SSIM. Significance. In conclusion, our unsupervised learning-based method can be a promising alternative to the traditional supervised methods for LDCT imaging, especially when the availability of the labeled datasets is limited. [ABSTRACT FROM AUTHOR]

Purpose. Target localization in pulmonary interventions (e.g. transbronchial biopsy of a lung nodule) is challenged by deformable motion and may benefit from fluoroscopic overlay of the target to provide accurate guidance. We present and evaluate a 3D–2D image registration method for fluoroscopic overlay in the presence of tissue deformation using a multi-resolution/multi-scale (MRMS) framework with an objective function that drives registration primarily by soft-tissue image gradients. Methods. The MRMS method registers 3D cone-beam CT to 2D fluoroscopy without gating of respiratory phase by coarse-to-fine resampling and global-to-local rescaling about target regions-of-interest. A variation of the gradient orientation ( GO) similarity metric (denoted G O ′ ) was developed to downweight bone gradients and drive registration via soft-tissue gradients. Performance was evaluated in terms of projection distance error at isocenter (PDEiso). Phantom studies determined nominal algorithm parameters and capture range. Preclinical studies used a freshly deceased, ventilated porcine specimen to evaluate performance in the presence of real tissue deformation and a broad range of 3D–2D image mismatch. Results. Nominal algorithm parameters were identified that provided robust performance over a broad range of motion (0–20 mm), including an adaptive parameter selection technique to accommodate unknown mismatch in respiratory phase. The G O ′ metric yielded median PDEiso = 1.2 mm, compared to 6.2 mm for conventional GO. Preclinical studies with real lung deformation demonstrated median PDEiso = 1.3 mm with MRMS + G O ′ registration, compared to 2.2 mm with a conventional transform. Runtime was 26 s and can be reduced to 2.5 s given a prior registration within ∼5 mm as initialization. Conclusions. MRMS registration via soft-tissue gradients achieved accurate fluoroscopic overlay in the presence of deformable lung motion. By driving registration via soft-tissue image gradients, the method avoided false local minima presented by bones and was robust to a wide range of motion magnitude. [ABSTRACT FROM AUTHOR]

Objective. The aim of this study is to evaluate the performance characteristics of a brain positron emission tomography (PET) scanner composed of four-layer independent read-out time-of-flight depth-of-interaction (TOF-DOI) detectors capable of first interaction position (FIP) detection, using Geant4 application for tomographic emission(GATE). This includes the spatial resolution, sensitivity, count rate capability, and reconstructed image quality. Approach. The proposed TOF-DOI PET detector comprises four layers of a 50 × 50 cerium-doped lutetium–yttrium oxyorthosilicate (LYSO:Ce) scintillator array with 1 mm pitch size, coupled to a 16 × 16 multi-pixel photon counter array with 3.0 mm × 3.0 mm photosensitive segments. Along the direction distant from the center field-of-view (FOV), the scintillator thickness of the four layers is 2.5, 3, 4, and 6 mm. The four layers were simulated with a 150 ps coincidence time resolution and the independent readout make the FIP detection capable. The spatial resolution and imaging performance were compared among the true-FIP, winner-takes-all (WTA) and front-layer FIP (FL-FIP) methods (FL-FIP selects the interaction position located on the front-most interaction layer in all the interaction layers). The National Electrical Manufacturers Association NU 2-2018 procedure was referred and modified to evaluate the performance of proposed scanner. Main results. In detector evaluation, the intrinsic spatial resolutions were 0.52 and 0.76 mm full width at half-maximum (FWHM) at 0° and 30° incident γ -rays in the first layer pair, respectively. The reconstructed spatial resolution by the filter backprojection (FBP) achieved sub-millimeter FWHM on average over the whole FOV. The maximum true count rate was 207.6 kcps at 15 kBq ml−1 and the noise equivalent count rate (NECR_2R) was 54.7 kcps at 6.0 kBq ml−1. Total sensitivity was 45.2 cps kBq−1 and 48.4 cps kBq−1 at the center and 10 cm off-center FOV, respectively. The TOF and DOI reconstructions significantly improved the image quality in the phantom studies. Moreover, the FL-FIP outperformed the conventional WTA method in terms of the spatial resolution and image quality. Significance. The proposed brain PET scanner could achieve sub-millimeter spatial resolution and high image quality with TOF and DOI reconstruction, which is meaningful to the clinical oncology research. Meanwhile, the comparison among the three positioning methods indicated that the FL-FIP decreased the image degradation caused by Compton scatter more than WTA. [ABSTRACT FROM AUTHOR]

Objective. Adaptive radiation therapy (ART) could protect organs at risk (OARs) while maintain high dose coverage to targets. However, there is still a lack of efficient online patient quality assurance (QA) methods, which is an obstacle to large-scale adoption of ART. We aim to develop a clinically relevant online patient QA solution for ART using daily CT scans and EPID-based in vivo dosimetry. Approach. Ten patients with rectal cancer at our center were included. Patients’ daily CT scans and portal images were collected to generate reconstructed 3D dose distributions. Contours of targets and OARs were recontoured on these daily CT scans by a clinician or an auto-segmentation algorithm, then dose-volume indices were calculated, and the percent deviation of these indices to their original plans were determined. This deviation was regarded as the metric for clinically relevant patient QA. The tolerance level was obtained using a 95% confidence interval of the QA metric distribution. These deviations could be further divided into anatomically relevant or delivery relevant indicators for error source analysis. Finally, our QA solution was validated on an additional six clinical patients. Main results. In rectal cancer, the 95% confidence intervals of the QA metric for PTV Î" D 95 (%) were [âˆ'3.11%, 2.35%], and for PTV Î" D 2 (%) were [âˆ'0.78%, 3.23%]. In validation, 68% for PTV Î" D 95 (%), and 79% for PTV Î" D 2 (%) of the 28 fractions are within tolerances of the QA metrics. one patient’s dosimetric impact of anatomical variations during treatment were observed through the source of error analysis. Significance. The online patient QA solution using daily CT scans and EPID-based in vivo dosimetry is clinically feasible. Source of error analysis has the potential for distinguishing sources of error and guiding ART for future treatments. [ABSTRACT FROM AUTHOR]

Objective. Cone-Beam CT (CBCT) often results in severe image artifacts and inaccurate HU values, meaning poor quality CBCT images cannot be directly applied to dose calculation in radiotherapy. To overcome this, we propose a cycle-residual connection with a dilated convolution-consistent generative adversarial network (Cycle-RCDC-GAN). Approach. The cycle-consistent generative adversarial network (Cycle-GAN) was modified using a dilated convolution with different expansion rates to extract richer semantic features from input images. Thirty pelvic patients were used to investigate the effect of synthetic CT (sCT) from CBCT, and 55 head and neck patients were used to explore the generalizability of the model. Three generalizability experiments were performed and compared: the pelvis trained model was applied to the head and neck; the head and neck trained model was applied to the pelvis, and the two datasets were trained together. Main results. The mean absolute error (MAE), the root mean square error (RMSE), peak signal to noise ratio (PSNR), the structural similarity index (SSIM), and spatial nonuniformity (SNU) assessed the quality of the sCT generated from CBCT. Compared with CBCT images, the MAE improved from 28.81 to 18.48, RMSE from 85.66 to 69.50, SNU from 0.34 to 0.30, and PSNR from 31.61 to 33.07, while SSIM improved from 0.981 to 0.989. The sCT objective indicators of Cycle-RCDC-GAN were better than Cycle-GAN’s. The objective metrics for generalizability were also better than Cycle-GAN’s. Significance. Cycle-RCDC-GAN enhances CBCT image quality and has better generalizability than Cycle-GAN, which further promotes the application of CBCT in radiotherapy. [ABSTRACT FROM AUTHOR]

Objective. Machine Learning methods can learn how to reconstruct magnetic resonance images (MRI) and thereby accelerate acquisition, which is of paramount importance to the clinical workflow. Physics-informed networks incorporate the forward model of accelerated MRI reconstruction in the learning process. With increasing network complexity, robustness is not ensured when reconstructing data unseen during training. We aim to embed data consistency (DC) in deep networks while balancing the degree of network complexity. While doing so, we will assess whether either explicit or implicit enforcement of DC in varying network architectures is preferred to optimize performance. Approach. We propose a scheme called Cascades of Independently Recurrent Inference Machines (CIRIM) to assess DC through unrolled optimization. Herein we assess DC both implicitly by gradient descent and explicitly by a designed term. Extensive comparison of the CIRIM to compressed sensing as well as other Machine Learning methods is performed: the End-to-End Variational Network (E2EVN), CascadeNet, KIKINet, LPDNet, RIM, IRIM, and UNet. Models were trained and evaluated on T1-weighted and FLAIR contrast brain data, and T2-weighted knee data. Both 1D and 2D undersampling patterns were evaluated. Robustness was tested by reconstructing 7.5Ă— prospectively undersampled 3D FLAIR MRI data of multiple sclerosis (MS) patients with white matter lesions. Main results. The CIRIM performed best when implicitly enforcing DC, while the E2EVN required an explicit DC formulation. Through its cascades, the CIRIM was able to score higher on structural similarity and PSNR compared to other methods, in particular under heterogeneous imaging conditions. In reconstructing MS patient data, prospectively acquired with a sampling pattern unseen during model training, the CIRIM maintained lesion contrast while efficiently denoising the images. Significance. The CIRIM showed highly promising generalization capabilities maintaining a very fair trade-off between reconstructed image quality and fast reconstruction times, which is crucial in the clinical workflow. [ABSTRACT FROM AUTHOR]

Tomography images are essential for clinical diagnosis and trauma surgery, allowing doctors to understand the internal information of patients in more detail. Since the large amount of x-ray radiation from the continuous imaging during the process of computed tomography scanning can cause serious harm to the human body, reconstructing tomographic images from sparse views becomes a potential solution to this problem. Here we present a deep-learning framework for tomography image reconstruction, namely TIReconNet, which defines image reconstruction as a data-driven supervised learning task that allows a mapping between the 2D projection view and the 3D volume to emerge from corpus. The proposed framework consists of four parts: feature extraction module, shape mapping module, volume generation module and super resolution module. The proposed framework combines 2D and 3D operations, which can generate high-resolution tomographic images with a relatively small amount of computing resources and maintain spatial information. The proposed method is verified on chest digitally reconstructed radiographs, and the reconstructed tomography images have achieved PSNR value of 18.621 ± 1.228 dB and SSIM value of 0.872 ± 0.041 when compared against the ground truth. In conclusion, an innovative convolutional neural network architecture is proposed and validated in this study, which proves that there is the potential to generate a 3D high-resolution tomographic image from a single 2D image using deep learning. This method may actively promote the application of reconstruction technology for radiation reduction, and further exploration of intraoperative guidance in trauma and orthopedics. [ABSTRACT FROM AUTHOR]

Objective. Cone-beam CT (CBCT) in modern pre-clinical small-animal radiation research platforms provides volumetric images for image guidance and experiment planning purposes. In this work, we implemented multi-energy element-resolved (MEER) CBCT using three scans with different kVps on a SmART platform (Precision x-ray Inc.) to determine images of relative electron density (rED) and elemental composition (EC) that are needed for Monte Carlo-based radiation dose calculation. Approach. We performed comprehensive calibration tasks to achieve sufficient accuracy for this quantitative imaging purpose. For geometry calibration, we scanned a ball bearing phantom and used an analytical method together with an optimization approach to derive gantry angle specific geometry parameters. Intensity calibration and correction included the corrections for detector lag, glare, and beam hardening. The corrected CBCT projection images acquired at 30, 40, and 60 kVp in multiple scans were used to reconstruct CBCT images using the Feldkampâ€"Davisâ€"Kress reconstruction algorithm. After that, an optimization problem was solved to determine images of rED and EC. We demonstrated the effectiveness of our CBCT calibration steps by showing improvements in image quality and successful material decomposition in cases with a small animal CT calibration phantom and a plastinated mouse phantom. Main results. It was found that artifacts induced by geometry inaccuracy, detector lag, glare, and beam hardening were visually reduced. CT number mean errors were reduced from 19% to 5%. In the CT calibration phantom case, median errors in H, O, and Ca fractions for all the inserts were below 1%, 2%, and 4% respectively, and median error in rED was less than 5%. Compared to the standard approach deriving material type and rED via CT number conversion, our approach improved Monte Carlo simulation-based dose calculation accuracy in bone regions. Mean dose error was reduced from 47.5% to 10.9%. Significance. The MEER-CBCT implemented on an existing CBCT system of a small animal irradiation platform achieved accurate material decomposition and significantly improved Monte Carlo dose calculation accuracy. [ABSTRACT FROM AUTHOR]

Iterative reconstruction frameworks show predominance in low dose and incomplete data situations. In the iterative reconstruction framework, there are two components, i.e., the fidelity term aims to maintain the structure details of the reconstructed object, and the regularization term uses prior information to suppress the artifacts such as noise. A regularization parameter balances them, aiming to find a good trade-off between noise and resolution. Currently, the regularization parameters are selected as a rule of thumb or some prior knowledge assumption is required, which limits practical uses. Furthermore, the computation cost of regularization parameter selection is also heavy. In this paper, we address this problem by introducing CT image quality assessment (IQA) into the iterative reconstruction framework. Several steps are involved during the study. First, we analyze the CT image statistics using the dual dictionary (DDL) method. Regularities are observed and concluded, revealing the relationship among the regularization parameter, iterations, and CT image quality. Second, with derivation and simplification of DDL procedure, a CT IQA metric named SODVAC is designed. The SODVAC locates the optimal regularization parameter that results in the reconstructed image with distinct structures and with no noise or little noise. Thirdly, we introduce SODVAC into the iterative reconstruction framework and then propose a general image-quality-guided iterative reconstruction (QIR) framework and give a specific framework example (sQIR) by introducing SODVAC into the iterative reconstruction framework. sQIR simultaneously optimizes the reconstructed image and the regularization parameter during the iterations. Results confirm the effectiveness of the proposed method. No prior information is needed and the low computation cost are the advantages of our method compared with existing state-of-the-art L-curve and ZIP selection strategies. [ABSTRACT FROM AUTHOR]

In dual-energy computed tomography (DECT), low- and high-kVp data are collected often over a full-angular range (FAR) of 360°. While there exists strong interest in DECT with low- and high-kVp data acquired over limited-angular ranges (LARs), there remains little investigation of image reconstruction in DECT with LAR data. Objective: we investigate image reconstruction with minimized LAR artifacts from low- and high-kVp data over LARs of ≤180° by using a directional-total-variation (DTV) algorithm. Methods: image reconstruction from LAR data is formulated as a convex optimization problem in which data-ℓ2 is minimized with constraints on image's DTVs along orthogonal axes. We then achieve image reconstruction by applying the DTV algorithm to solve the optimization problem. We conduct numerical studies from data generated over arcs of LARs, ranging from 14° to 180°, and perform visual inspection and quantitative analysis of images reconstructed. Results: monochromatic images of interest obtained with the DTV algorithm from LAR data show substantially reduced artifacts that are observed often in images obtained with existing algorithms. The improved image quality also leads to accurate estimation of physical quantities of interest, such as effective atomic number and iodine contrast concentration. Conclusion: our study reveals that from LAR data of low- and high-kVp, monochromatic images can be obtained that are visually, and physical quantities can be estimated that are quantitatively, comparable to those obtained in FAR DECT. Significance: as LAR DECT is of high practical application interest, the results acquired in the work may engender insights into the design of DECT with LAR scanning configurations of practical application significance. [ABSTRACT FROM AUTHOR]

Proton therapy treatment for lungs remains challenging as images enabling the detection of inter- and intra-fractional motion, which could be used for proton dose adaptation, are not readily available. 4D computed tomography (4DCT) provides high image quality but is rarely available in-room, while in-room 4D cone beam computed tomography (4DCBCT) suffers from image quality limitations stemming mostly from scatter detection. This study investigated the feasibility of using virtual 4D computed tomography (4DvCT) as a prior for a phase-per-phase scatter correction algorithm yielding a 4D scatter corrected cone beam computed tomography image (4DCBCTcor), which can be used for proton dose calculation. 4DCT and 4DCBCT scans of a porcine lung phantom, which generated reproducible ventilation, were acquired with matching breathing patterns. Diffeomorphic Morphons, a deformable image registration algorithm, was used to register the mid-position 4DCT to the mid-position 4DCBCT and yield a 4DvCT. The 4DCBCT was reconstructed using motion-aware reconstruction based on spatial and temporal regularization (MA-ROOSTER). Successively for each phase, digitally reconstructed radiographs of the 4DvCT, simulated without scatter, were exploited to correct scatter in the corresponding CBCT projections. The 4DCBCTcor was then reconstructed with MA-ROOSTER using the corrected CBCT projections and the same settings and deformation vector fields as those already used for reconstructing the 4DCBCT. The 4DCBCTcor and the 4DvCT were evaluated phase-by-phase, performing proton dose calculations and comparison to those of a ground truth 4DCT by means of dose-volume-histograms (DVH) and gamma pass-rates (PR). For accumulated doses, DVH parameters deviated by at most 1.7% in the 4DvCT and 2.0% in the 4DCBCTcor case. The gamma PR for a (2%, 2 mm) criterion with 10% threshold were at least 93.2% (4DvCT) and 94.2% (4DCBCTcor), respectively. The 4DCBCTcor technique enabled accurate proton dose calculation, which indicates the potential for applicability to clinical 4DCBCT scans. [ABSTRACT FROM AUTHOR]

The presence of metallic implants often introduces severe metal artifacts in the x-ray computed tomography (CT) images, which could adversely influence clinical diagnosis or dose calculation in radiation therapy. In this work, we present a novel deep-learning-based approach for metal artifact reduction (MAR). In order to alleviate the need for anatomically identical CT image pairs (i.e. metal artifact-corrupted CT image and metal artifact-free CT image) for network learning, we propose a self-supervised cross-domain learning framework. Specifically, we train a neural network to restore the metal trace region values in the given metal-free sinogram, where the metal trace is identified by the forward projection of metal masks. We then design a novel filtered backward projection (FBP) reconstruction loss to encourage the network to generate more perfect completion results and a residual-learning-based image refinement module to reduce the secondary artifacts in the reconstructed CT images. To preserve the fine structure details and fidelity of the final MAR image, instead of directly adopting convolutional neural network (CNN)-refined images as output, we incorporate the metal trace replacement into our framework and replace the metal-affected projections of the original sinogram with the prior sinogram generated by the forward projection of the CNN output. We then use the FBP algorithms for final MAR image reconstruction. We conduct an extensive evaluation on simulated and real artifact data to show the effectiveness of our design. Our method produces superior MAR results and outperforms other compelling methods. We also demonstrate the potential of our framework for other organ sites. [ABSTRACT FROM AUTHOR]

Simultaneous acquisition of cone beam CT (CBCT) projections using both the kV and MV imagers of an image guided radiotherapy system reduces set-up scan times—a benefit to lung cancer radiation oncology patients—but increases noise in the 3D reconstruction. In this article, we present a kV‐MV scan time reduction technique that uses two noise-reducing measures to achieve superior performance. The first is a high-DQE multi-layer MV imager prototype. The second is a beam hardening correction algorithm which combines poly-energetic modeling with edge-preserving, regularized smoothing of the projections. Performance was tested in real acquisitions of the Catphan 604 and a thorax phantom. Percent noise was quantified from voxel values in a soft tissue volume of interest (VOI) while edge blur was quantified from a VOI straddling a boundary between air and soft material. Comparisons in noise/resolution performance trade-off were made between our proposed approach, a dose-equivalent kV-only scan, and a kV‐MV reconstruction technique previously published by Yin et al (2005 Med. Phys. 32 9). The proposed technique demonstrated lower noise as a function of spatial resolution than the baseline kV‐MV method, notably a 50% noise reduction at typical edge blur levels. Our proposed method also exhibited fainter non-uniformity artifacts and in some cases superior contrast. Overall, we find that the combination of a multi-layer MV imager, acquiring at a LINAC source energy of 2.5 MV, and a denoised beam hardening correction algorithm enables noise, resolution, and dose performance comparable to standard kV-imager only set-up CBCT, but with nearly half the gantry rotation time. [ABSTRACT FROM AUTHOR]

The uncertainty of reconstructed PET images remains difficult to assess and to interpret for the use in diagnostic and quantification tasks. Here we provide (1) an easy-to-use methodology for uncertainty assessment for almost any Bayesian model in PET reconstruction from single datasets and (2) a detailed analysis and interpretation of produced posterior image distributions. We apply a recent posterior bootstrap framework to the PET image reconstruction inverse problem and obtain simple parallelizable algorithms based on random weights and on existing maximum a posteriori (MAP) (posterior maximum) optimization-based algorithms. Posterior distributions are produced, analyzed and interpreted for several common Bayesian models. Their relationship with the distribution of the MAP image estimate over multiple dataset realizations is exposed. The coverage properties of posterior distributions are validated. More insight is obtained for the interpretation of posterior distributions in order to open the way for including uncertainty information into diagnostic and quantification tasks. [ABSTRACT FROM AUTHOR]

Patient movement affects image quality in oral and maxillofacial cone-beam computed tomography imaging. While many efforts are made to minimize the possibility of motion during a scan, relatively little attention has been given to motion correction after acquisition. We propose a novel method which can improve the image quality after an oral and maxillofacial scan. The proposed method is based on our previous work and is a retrospective motion estimation and motion compensation (ME/MC) approach that iteratively estimates and compensates for rigid pose change over time. During motion estimation, image update and motion update are performed alternately in a multi-resolution scheme to obtain the motion. We propose use of a feature-based motion update and patch-based image update in the iterative estimation process, to alleviate the effect of limited scan field of view on estimation. During motion compensation, a fine-resolution image reconstruction was performed with compensation for the estimated motion. The proposed ME/MC method was evaluated with simulations, phantom and patient studies. Two experts in dentomaxillofacial radiology assessed the diagnostic importance of the resulting motion artifact suppression. The quality of the reconstructed images was improved after motion compensation, and most of the image artifacts were eliminated. Quantitative analysis by comparison to a reference image and by calculation of a sharpness metric agreed with the qualitative observation. The results are promising, and further evaluation is required to assess the clinical value of the proposed method. [ABSTRACT FROM AUTHOR]

Fixed-gantry radiation therapy has been proposed as a low-cost alternative to the conventional rotating-gantry radiation therapy, that may help meet the rising global treatment demand. Fixed-gantry systems require gravitational motion compensated reconstruction algorithms to produce cone-beam CT (CBCT) images of sufficient quality for image guidance. The aim of this work was to adapt and investigate five CBCT reconstruction algorithms for fixed-gantry CBCT images. The five algorithms investigated were Feldkamp–Davis–Kress (FDK), prior image constrained compressed sensing (PICCS), gravitational motion compensated FDK (GMCFDK), motion compensated PICCS (MCPICCS) (a novel CBCT reconstruction algorithm) and simultaneous motion estimation and iterative reconstruction (SMEIR). Fixed-gantry and rotating-gantry CBCT scans were acquired of 3 rabbits, with the rotating-gantry scans used as a reference. Projections were sorted into rotation bins, based on the angle of rotation of the rabbit during image acquisition. The algorithms were compared using the structural similarity index measure root mean square error, and reconstruction time. Evaluation of the reconstructed volumes showed that, when compared with the reference rotating-gantry volume, the conventional FDK algorithm did not accurately reconstruct fixed-gantry CBCT scans. Whilst the PICCS reconstruction algorithm reduced some motion artefacts, the motion estimation reconstruction methods (GMCFDK, MCPICCS and SMEIR) were able to greatly reduce the effect of motion artefacts on the reconstructed volumes. This finding was verified quantitatively, with GMCFDK, MCPICCS and SMEIR reconstructions having RMSE 17%–19% lower and SSIM 1% higher than a conventional FDK. However, all motion compensated fixed-gantry CBCT reconstructions had a 56%–61% higher RMSE and 1.5% lower SSIM than FDK reconstructions of conventional rotating-gantry CBCT scans. The results show that motion compensation is required to reduce motion artefacts for fixed-gantry CBCT reconstructions. This paper further demonstrates the feasibility of fixed-gantry CBCT scans, and the ability of CBCT reconstruction algorithms to compensate for motion due to horizontal rotation. [ABSTRACT FROM AUTHOR]

Advances in simultaneous positron emission tomography/magnetic resonance imaging (PET/MRI) technology have led to an active investigation of the anatomy-guided regularized PET image reconstruction algorithm based on MR images. Among the various priors proposed for anatomy-guided regularized PET image reconstruction, Bowsher's method based on second-order smoothing priors sometimes suffers from over-smoothing of detailed structures. Therefore, in this study, we propose a Bowsher prior based on the -norm and an iteratively reweighting scheme to overcome the limitation of the original Bowsher method. In addition, we have derived a closed solution for iterative image reconstruction based on this non-smooth prior. A comparison study between the original and proposed Bowsher priors was conducted using computer simulation and real human data. In the simulation and real data application, small lesions with abnormal PET uptake were better detected by the proposed Bowsher prior methods than the original Bowsher prior. The original Bowsher leads to a decreased PET intensity in small lesions when there is no clear separation between the lesions and surrounding tissue in the anatomical prior. However, the proposed Bowsher prior methods showed better contrast between the tumors and surrounding tissues owing to the intrinsic edge-preserving property of the prior which is attributed to the sparseness induced by -norm, especially in the iterative reweighting scheme. Besides, the proposed methods demonstrated lower bias and less hyper-parameter dependency on PET intensity estimation in the regions with matched anatomical boundaries in PET and MRI. Therefore, these methods will be useful for improving the PET image quality based on the anatomical side information. [ABSTRACT FROM AUTHOR]

In this work, we consider the task of image reconstruction in 2D radial cardiac cine MRI using deep learning (DL)-based regularization. As the regularization is achieved by employing an image-prior predicted by a pre-trained convolutional neural network (CNN), the quality of the image-prior is of essential importance. The achievable performance of any DL-based method is limited by the amount and the quality of the available training data. For fast dynamic processes, obtaining good-quality MR data is challenging because of technical and physiological reasons. In this work, we try to overcome these problems by a transfer-learning approach which is motivated by a previously presented DL-method (XT,YT U-Net). There, instead of training the network on the whole 2D dynamic images, it is trained on 2D spatio-temporal profiles (xt,yt-slices) which show the temporal changes of the imaged object. Therefore, for the training and test data, it is more important that their spatio-temporal profiles share similar local features rather than being images of the same anatomy. This allows us to equip arbitrary data with simulated motion that resembles the cardiac motion and use it as training data. By doing so, it is possible to train a CNN which is applicable to cardiac cine MR data without using ground-truth cine MR images for training. We demonstrate that combining XT,YT U-Net with the proposed transfer-learning strategy delivers comparable performance to CNNs trained on cardiac cine MR images and in some cases even qualitatively surpasses these. Additionally, the transfer-learning strategy was investigated for a 2D and 3D U-Net. The images processed by the the CNNs were used as image-priors in the CNN-regularized iterative reconstruction. The XT,YT U-Net yielded visibly better results than the 2D U-Net and slightly better results than the 3D U-Net when used in combination with the presented transfer learning-strategy. [ABSTRACT FROM AUTHOR]

In this paper we present OMEGA, an open-source software, for efficient and fast image reconstruction in positron emission tomography (PET). OMEGA uses the scripting language of MATLAB and GNU Octave allowing reconstruction of PET data with a MATLAB or GNU Octave interface. The goal of OMEGA is to allow easy and fast reconstruction of any PET data, and to provide a computationally efficient, easy-access platform for development of new PET algorithms with built-in forward and backward projection operations available to the user as a MATLAB/Octave class. OMEGA also includes direct support for GATE simulated data, facilitating easy evaluation of the new algorithms using Monte Carlo simulated PET data. OMEGA supports parallel computing by utilizing OpenMP for CPU implementations and OpenCL for GPU allowing any hardware to be used. OMEGA includes built-in function for the computation of normalization correction and allows several other corrections to be applied such as attenuation, randoms or scatter. OMEGA includes several different maximum-likelihood and maximum a posteriori (MAP) algorithms with several different priors. The user can also input their own priors to the built-in MAP functions. The image reconstruction in OMEGA can be computed either by using an explicitly computed system matrix or with a matrix-free formalism, where the latter can be accelerated with OpenCL. We provide an overview on the software and present some examples utilizing the different features of the software. [ABSTRACT FROM AUTHOR]

Accurate spatial dose delivery in radiotherapy is frequently complicated due to changes in the patient's internal anatomy during and in-between therapy segments. The recent introduction of hybrid MRI radiotherapy systems allows unequaled soft-tissue visualization during radiation delivery and can be used for dose reconstruction to quantify the impact of motion. To this end, knowledge of anatomical deformations obtained from continuous monitoring during treatment has to be combined with information on the spatio-temporal dose delivery to perform motion-compensated dose accumulation (MCDA). Here, the influence of the choice of deformable image registration algorithm, dose warping strategy, and magnetic resonance image resolution and signal-to-noise-ratio on the resulting MCDA is investigated. For a quantitative investigation, four 4D MRI-datasets representing typical patient observed motion patterns are generated using finite element modeling and serve as a gold standard. Energy delivery is simulated intra-fractionally in the deformed image space and, subsequently, MCDA-processed. Finally, the results are substantiated by comparing MCDA strategies on clinically acquired patient data. It is shown that MCDA is needed for correct quantitative dose reconstruction. For prostate treatments, using the energy per mass transfer dose warping strategy has the largest influence on decreasing dose estimation errors. [ABSTRACT FROM AUTHOR]

Image-guided therapies in the abdomen and pelvis are often hindered by motion artifacts in cone-beam CT (CBCT) arising from complex, non-periodic, deformable organ motion during long scan times (5–30 s). We propose a deformable image-based motion compensation method to address these challenges and improve CBCT guidance. Motion compensation is achieved by selecting a set of small regions of interest in the uncompensated image to minimize a cost function consisting of an autofocus objective and spatiotemporal regularization penalties. Motion trajectories are estimated using an iterative optimization algorithm (CMA-ES) and used to interpolate a 4D spatiotemporal motion vector field. The motion-compensated image is reconstructed using a modified filtered backprojection approach. Being image-based, the method does not require additional input besides the raw CBCT projection data and system geometry that are used for image reconstruction. Experimental studies investigated: (1) various autofocus objective functions, analyzed using a digital phantom with a range of sinusoidal motion magnitude (4, 8, 12, 16, 20 mm); (2) spatiotemporal regularization, studied using a CT dataset from The Cancer Imaging Archive with deformable sinusoidal motion of variable magnitude (10, 15, 20, 25 mm); and (3) performance in complex anatomy, evaluated in cadavers undergoing simple and complex motion imaged on a CBCT-capable mobile C-arm system (Cios Spin 3D, Siemens Healthineers, Forchheim, Germany). Gradient entropy was found to be the best autofocus objective for soft-tissue CBCT, increasing structural similarity (SSIM) by 42%–92% over the range of motion magnitudes investigated. The optimal temporal regularization strength was found to vary widely (0.5–5 mm−2) over the range of motion magnitudes investigated, whereas optimal spatial regularization strength was relatively constant (0.1). In cadaver studies, deformable motion compensation was shown to improve local SSIM by ∼17% for simple motion and ∼21% for complex motion and provided strong visual improvement of motion artifacts (reduction of blurring and streaks and improved visibility of soft-tissue edges). The studies demonstrate the robustness of deformable motion compensation to a range of motion magnitudes, frequencies, and other factors (e.g. truncation and scatter). [ABSTRACT FROM AUTHOR]

Purpose. To investigate the impact of 4D-CBCT image quality on radiomic analysis and the efficacy of using deep learning based image enhancement to improve the accuracy of radiomic features of 4D-CBCT. Material and Methods. In this study, 4D-CT data from 16 lung cancer patients were obtained. Digitally reconstructed radiographs (DRRs) were simulated from the 4D-CT, and then used to reconstruct 4D CBCT using the conventional FDK (Feldkamp et al 1984 J. Opt. Soc. Am. A 1 612–9) algorithm. Different projection numbers (i.e. 72, 120, 144, 180) and projection angle distributions (i.e. evenly distributed and unevenly distributed using angles from real 4D-CBCT scans) were simulated to generate the corresponding 4D-CBCT. A deep learning model (TecoGAN) was trained on 10 patients and validated on 3 patients to enhance the 4D-CBCT image quality to match with the corresponding ground-truth 4D-CT. The remaining 3 patients with different tumor sizes were used for testing. The radiomic features in 6 different categories, including histogram, GLCM, GLRLM, GLSZM, NGTDM, and wavelet, were extracted from the gross tumor volumes of each phase of original 4D-CBCT, enhanced 4D-CBCT, and 4D-CT. The radiomic features in 4D-CT were used as the ground-truth to evaluate the errors of the radiomic features in the original 4D-CBCT and enhanced 4D-CBCT. Errors in the original 4D-CBCT demonstrated the impact of image quality on radiomic features. Comparison between errors in the original 4D-CBCT and enhanced 4D-CBCT demonstrated the efficacy of using deep learning to improve the radiomic feature accuracy. Results. 4D-CBCT image quality can substantially affect the accuracy of the radiomic features, and the degree of impact is feature-dependent. The deep learning model was able to enhance the anatomical details and edge information in the 4D-CBCT as well as removing other image artifacts. This enhancement of image quality resulted in reduced errors for most radiomic features. The average reduction of radiomics errors for 3 patients are 20.0%, 31.4%, 36.7%, 50.0%, 33.6% and 11.3% for histogram, GLCM, GLRLM, GLSZM, NGTDM and Wavelet features. And the error reduction was more significant for patients with larger tumors. The findings were consistent across different respiratory phases, projection numbers, and angle distributions. Conclusions. The study demonstrated that 4D-CBCT image quality has a significant impact on the radiomic analysis. The deep learning-based augmentation technique proved to be an effective approach to enhance 4D-CBCT image quality to improve the accuracy of radiomic analysis. [ABSTRACT FROM AUTHOR]

Three-dimensional cone-beam imaging has become valuable in interventional radiology. Currently, this tool, referred to as C-arm CT, employs a circular short-scan for data acquisition, which limits the axial volume coverage and yields unavoidable cone-beam artifacts. To improve flexibility in axial coverage and image quality, there is a critical need for novel data acquisition geometries and related image reconstruction algorithms. For this purpose, we previously introduced the extended line-ellipse-line trajectory, which allows complete scanning of arbitrary volume lengths in the axial direction together with adjustable axial beam collimation, from narrow to wide depending on the targeted application. A first implementation of this trajectory on a state-of-the-art robotic angiography system is reported here. More specifically, an assessment of the quality of this first implementation is presented. The assessment is in terms of geometric fidelity and repeatability, complemented with a first visual inspection of how well the implementation enables imaging an anthropomorphic head phantom. The geometric fidelity analysis shows that the ideal trajectory is closely emulated, with only minor deviations that have no impact on data completeness and clinical practicality. Also, mean backprojection errors over short-term repetitions are shown to be below the detector pixel size at field-of-view center for most views, which indicates repeatability is satisfactory for clinical utilization. These repeatability observations are further supported by values of the Structural Similarity Index Metric above 94% for reconstructions of the FORBILD head phantom from computer-simulated data based on repeated data acquisition geometries. Last, the real data experiment with the anthropomorphic head phantom shows that the high contrast features of the phantom are well reconstructed without distortions as well as without breaks or other disturbing transition zones, which was not obvious given the complexity of the data acquisition geometry and the major variations in axial coverage that occur over the scan. [ABSTRACT FROM AUTHOR]

Artifacts caused by patient breathing and movement during PET data acquisition affect image quality. Respiratory gating is commonly used to gate the list-mode PET data into multiple bins over a respiratory cycle. Non-rigid registration of respiratory-gated PET images can reduce motion artifacts and preserve count statistics, but it is time consuming. In this work, we propose an unsupervised non-rigid image registration framework using deep learning for motion correction. Our network uses a differentiable spatial transformer layer to warp the moving image to the fixed image and uses a stacked structure for deformation field refinement. Estimated deformation fields were incorporated into an iterative image reconstruction algorithm to perform motion compensated PET image reconstruction. We validated the proposed method using simulation and clinical data and implemented an iterative image registration approach for comparison. Motion compensated reconstructions were compared with ungated images. Our simulation study showed that the motion compensated methods can generate images with sharp boundaries and reveal more details in the heart region compared with the ungated image. The resulting normalized root mean square error (NRMS) was 24.3 ± 1.7% for the deep learning based motion correction, 31.1 ± 1.4% for the iterative registration based motion correction, and 41.9 ± 2.0% for ungated reconstruction. The proposed deep learning based motion correction reduced the bias compared with the ungated image without increasing the noise level and outperformed the iterative registration based method. In the real data study, both motion compensated images provided higher lesion contrast and sharper liver boundaries than the ungated image and had lower noise than the reference gate image. The contrast of the proposed method based on the deep neural network was higher than the ungated image and iterative registration method at any matched noise level. [ABSTRACT FROM AUTHOR]

The primary cone-beam computed tomography (CBCT) imaging beam scatters inside the patient and produces a contaminating photon fluence that is registered by the detector. Scattered photons cause artifacts in the image reconstruction, and are partially responsible for the inferior image quality compared to diagnostic fan-beam CT. In this work, a deep convolutional autoencoder (DCAE) and projection-based scatter removal algorithm were constructed for the ImagingRingTM system on rails (IRr), which allows for non-isocentric acquisitions around virtual rotation centers with its independently rotatable source and detector arms. A Monte Carlo model was developed to simulate (i) a non-isocentric training dataset of ≈1200 projection pairs (primary + scatter) from 27 digital head-and-neck cancer patients around five different virtual rotation centers (DCAENONISO), and (ii) an isocentric dataset existing of ≈1200 projection pairs around the physical rotation center (DCAEISO). The scatter removal performance of both DCAE networks was investigated in two digital anthropomorphic phantom simulations and due to superior performance only the DCAENONISO was applied on eight real patient acquisitions. Measures for the quantitative error, the signal-to-noise ratio, and the similarity were evaluated for two simulated digital head-and-neck patients, and the contrast-to-noise ratio (CNR) was investigated between muscle and adipose tissue in the real patient image reconstructions. Image quality metrics were compared between the uncorrected data, the currently implemented heuristic scatter correction data, and the DCAE corrected image reconstruction. The DCAENONISO corrected image reconstructions of two digital patient simulations showed superior image quality metrics compared to the uncorrected and corrected image reconstructions using a heuristic scatter removal. The proposed DCAENONISO scatter correction in this study was successfully demonstrated in real non-isocentric patient CBCT acquisitions and achieved statistically significant higher CNRs compared to the uncorrected or the heuristic corrected image data. This paper presents for the first time a projection-based scatter removal algorithm for isocentric and non-isocentric CBCT imaging using a deep convolutional autoencoder trained on Monte Carlo composed datasets. The algorithm was successfully applied to real patient data. [ABSTRACT FROM AUTHOR]

In this paper we present a generalized Deep Learning-based approach for solving ill-posed large-scale inverse problems occuring in medical image reconstruction. Recently, Deep Learning methods using iterative neural networks (NNs) and cascaded NNs have been reported to achieve state-of-the-art results with respect to various quantitative quality measures as PSNR, NRMSE and SSIM across different imaging modalities. However, the fact that these approaches employ the application of the forward and adjoint operators repeatedly in the network architecture requires the network to process the whole images or volumes at once, which for some applications is computationally infeasible. In this work, we follow a different reconstruction strategy by strictly separating the application of the NN, the regularization of the solution and the consistency with the measured data. The regularization is given in the form of an image prior obtained by the output of a previously trained NN which is used in a Tikhonov regularization framework. By doing so, more complex and sophisticated network architectures can be used for the removal of the artefacts or noise than it is usually the case in iterative NNs. Due to the large scale of the considered problems and the resulting computational complexity of the employed networks, the priors are obtained by processing the images or volumes as patches or slices. We evaluated the method for the cases of 3D cone-beam low dose CT and undersampled 2D radial cine MRI and compared it to a total variation-minimization-based reconstruction algorithm as well as to a method with regularization based on learned overcomplete dictionaries. The proposed method outperformed all the reported methods with respect to all chosen quantitative measures and further accelerates the regularization step in the reconstruction by several orders of magnitude. [ABSTRACT FROM AUTHOR]

Several direct algorithms have been proposed to take into account the non-linear path of protons in the reconstruction of a proton CT (pCT) image. This paper presents a comparison between five of them, in terms of spatial resolution and relative stopping power (RSP) accuracy. Our comparison includes (1) a distance-driven algorithm extending the filtered backprojection to non-linear trajectories (DD), (2) an algorithm reconstructing a pCT image from optimized projections (ML), (3) a backproject-then-filter approach using a 2D cone filter (BTF), (4) a differentiated backprojection algorithm based on the inversion of the Hilbert transform (DBP), and (5) an algorithm using a 2D directional ramp filter (DR). We have simulated a single tracking pCT set-up using Geant4 through GATE, with a proton source and two position, direction and energy detectors upstream and downstream from the object. Tracker uncertainties were added on the position and direction measurements. A Catphan 528 phantom and a spiral phantom were simulated to measure the spatial resolution and a Gammex 467 phantom was used for the RSP accuracy. Each proton's trajectory was estimated using a most likely path (MLP) formalism. The spatial resolution was evaluated using the frequency corresponding to a modulation transfer function of 10% of its peak value and the RSP accuracy using the mean values in the inserts of the Gammex phantom. In terms of spatial resolution, it was shown that, for ideal trackers, the DR and BTF methods offer a slightly better resolution since each proton is directly binned in the image grid according to its MLP. However, all methods but the ML show comparable resolution when using realistic trackers. Regarding the RSP, three algorithms (DR, DD and BTF) show a mean relative error inside the inserts about 0.1%. As the DR and BTF methods are more computationally expensive, the DD—which allows the same spatial resolution in realistic conditions and the same accuracy—and the DBP—which has a fairly good accuracy (<0.2%) and allows reconstruction from truncated data—can be used for a reduced reconstruction time. [ABSTRACT FROM AUTHOR]

We investigated whether a combination of k-space undersampling and variable density averaging enhances image quality for low-SNR MRI acquisitions. We implemented 3D Cartesian k-space prospective undersampling with a variable number of averages for each k-space line. The performance of this compressed sensing with variable-density averaging (CS-VDA) method was evaluated in retrospective analysis of fully sampled phantom MRI measurements, as well as for prospectively accelerated in vivo 3D brain and knee MRI scans. Both phantom and in vivo results showed that acquisitions using the CS-VDA approach resulted in better image quality as compared to full sampling of k-space in the same scan time. Specifically, CS-VDA with a higher number of averages in the center of k-space resulted in the best image quality, apparent from increased anatomical detail with preserved soft-tissue contrast. This novel approach will facilitate improved image quality of inherently low SNR data, such as those with high-resolution or specific contrast-weightings with low SNR efficiency. [ABSTRACT FROM AUTHOR]

Dual-energy computed tomography (DECT) has capability to improve material differentiation, but most scanning schemes require two sets of full-scan measurements at different x-ray spectra, limiting its application to imaging system with incomplete scan. In this study, using one half-scan and a second limited-angle scan, we propose a DECT reconstruction method by exploiting the consistent information of gradient images at high- and low-energy spectra, which relaxes the requirement of data acquisition of DECT. Based on the theory of sampling condition analysis, the complementary support set of gradient images plays an important role in image reconstruction because it constitutes the sufficient and necessary condition for accurate CT reconstruction. For DECT, the gradient images of high- and low-energy CT images ideally share the same complementary support set for the same object. Inspired by this idea, we extract the prior knowledge of complementary support set (Pri-CSS) from the gradient image of the first half-scan CT image to promote the second limited-angle CT reconstruction. Pri-CSS will be incorporated into total variation regularization model in the form of constrains. Alternative direction method is applied to iteratively solve the modified optimization model, thereby deriving the proposed algorithm to recover low-energy CT image from limited-angle measurements. The qualitative and quantitative experiments on digital and real data are performed to validate the proposed method. The results show that the proposed method outperforms its counterparts and achieve high reconstruction quality for the designed scanning configuration. [ABSTRACT FROM AUTHOR]

Incorrect prediction of skin dose in external beam radiotherapy (EBR) can have normal tissue complication such as acute skin desquamation and skin necrosis. The absorbed dose of skin should be evaluated within basal layer, placed between the epidermis and dermis layers. However, current treatment planning systems (TPS) cannot correctly define the skin layer because of the limitation of voxel resolution in computed tomography (CT). Recently, a new tetrahedral-mesh (TM) phantom was developed to evaluate radiation dose realistically. This study aims to develop a technique to evaluate realistic skin dose using the TM phantom in EBR. The TM phantom was modeled with thin skin layers, including the epidermis, basal layer, and dermis from CT images. Using the Geant4 toolkit, the simulation was performed to evaluate the skin dose according to the radiation treatment conditions. The skin dose was evaluated at a surface depth of 50 µm and 2000 µm. The difference in average skin dose between depths was up to 37%, depending on the thickness and region of the skin to be measured. The results indicate that the skin dose has been overestimated when the skin is evaluated using commercial TPS. Although it is not possible with traditional TPS, our skin dose evaluation technique can realistically express the absorbed dose at thin skin layers from a patient-specific phantom. [ABSTRACT FROM AUTHOR]

Objective. There are several x-ray computed tomography (CT) scanning strategies used to reduce radiation dose, such as (1) sparse-view CT, (2) low-dose CT and (3) region-of-interest (ROI) CT (called interior tomography). To further reduce the dose, sparse-view and/or low-dose CT settings can be applied together with interior tomography. Interior tomography has various advantages in terms of reducing the number of detectors and decreasing the x-ray radiation dose. However, a large patient or a small field-of-view (FOV) detector can cause truncated projections, and then the reconstructed images suffer from severe cupping artifacts. In addition, although low-dose CT can reduce the radiation exposure dose, analytic reconstruction algorithms produce image noise. Recently, many researchers have utilized image-domain deep learning (DL) approaches to remove each artifact and demonstrated impressive performances, and the theory of deep convolutional framelets supports the reason for the performance improvement. Approach. In this paper, we found that it is difficult to solve coupled artifacts using an image-domain convolutional neural network (CNN) based on deep convolutional framelets. Significance. To address the coupled problem, we decouple it into two sub-problems: (i) image-domain noise reduction inside the truncated projection to solve low-dose CT problem and (ii) extrapolation of the projection outside the truncated projection to solve the ROI CT problem. The decoupled sub-problems are solved directly with a novel proposed end-to-end learning method using dual-domain CNNs. Main results. We demonstrate that the proposed method outperforms the conventional image-domain DL methods, and a projection-domain CNN shows better performance than the image-domain CNNs commonly used by many researchers. [ABSTRACT FROM AUTHOR]

In the development of prototype systems for positron emission tomography a valid and robust image reconstruction algorithm is required. However, prototypes often employ novel detector and system geometries which may change rapidly under optimization. In addition, developing systems generally produce highly granular, or possibly continuous detection domains which require some level of on-the-fly calculation for retention of measurement precision. In this investigation a new method of on-the-fly system matrix calculation is proposed that provides advantages in application to such list-mode systems in terms of flexibility in system modeling. The new method is easily adaptable to complicated system geometries and available computational resources. Detection uncertainty models are used as random number generators to produce ensembles of possible photon trajectories at image reconstruction time for each datum in the measurement list. However, the result of this approach is that the system matrix elements change at each iteration in a non-repetitive manner. The resulting algorithm is considered the simulation of a one-pass list (SOPL) which is generated and the list traversed during image reconstruction. SOPL alters the system matrix in use at each iteration and so behavior within the maximum likelihood-expectation maximization algorithm was investigated. A two-pixel system and a small two dimensional imaging model are used to illustrate the process and quantify aspects of the algorithm. The two-dimensional imaging system showed that, while incurring a penalty in image resolution, in comparison to a non-random equal-computation counterpart, SOPL provides much enhanced noise properties. In addition, enhancement in system matrix quality is straightforward (by increasing the number of samples in the ensemble) so that the resolution penalty can be recovered when desired while retaining improvement in noise properties. Finally the approach is tested and validated against a standard (highly accurate) system matrix using experimental data from a prototype system--the AX-PET. [ABSTRACT FROM AUTHOR]

Mathematical phantoms are essential for the development and early stage evaluation of image reconstruction algorithms in x-ray computed tomography (CT). This note offers tools for computer simulations using a two-dimensional (2D) phantom that models the central axial slice through the FORBILD head phantom. Introduced in 1999, in response to a need for a more robust test, the FORBILD head phantom is now seen by many as the gold standard. However, the simple Shepp-Logan phantom is still heavily used by researchers working on 2D image reconstruction. Universal acceptance of the FORBILD head phantom may have been prevented by its significantly higher complexity: software that allows computer simulations with the Shepp-Logan phantom is not readily applicable to the FORBILD head phantom. The tools offered here address this problem. They are designed for use with Matlab®, as well as opensource variants, such as FreeMat and Octave, which are all widely used in both academia and industry. To get started, the interested user can simply copy and paste the codes from this PDF document into Matlab® M-files. [ABSTRACT FROM AUTHOR]

Differential phase contrast computed tomography (DPC-CT) is an x-ray imaging method that uses the wave properties of imaging photons as the contrast mechanism. It has been demonstrated that DPC images can be obtained using a conventional x-ray tube and a Talbot-Lau-type interferometer. Due to the limited size of the gratings, current data acquisition systems only offer a limited field of view, and thus are prone to data truncation. As a result, the reconstructed DPC-CT image may suffer from image artifacts and increased inaccuracy in the reconstructed image values. In this paper, we demonstrate that a small region of interest (ROI) within a large object can be accurately and stably reconstructed using fully truncated projection datasets provided that a priori information on electron density is known for a small region inside the ROI. The method reconstructs an image iteratively to satisfy a group of physical conditions by using a projection onto convex set (POCS) approach. In this work, this POCS algorithm is validated using both numerical simulations and physical phantom experimental data. In both cases, the root mean square error is reduced by an order of magnitude with respect to the truncated analytic reconstructions. Truncation artifacts observed in the latter reconstructions are eliminated using the POCS algorithm. [ABSTRACT FROM AUTHOR]

We present a new version of STIR (Software for Tomographic Image Reconstruction), an open source object-oriented library implemented in C++ for 3D positron emission tomography reconstruction. This library has been designed such that it can be used for many algorithms and scanner geometries, while being portable to various computing platforms. This second release enhances its flexibility and modular design and includes additional features such as Compton scatter simulation, an additional iterative reconstruction algorithm and parametric image reconstruction (both indirect and direct). We discuss the new features in this release and present example results. STIR can be downloaded from http://stir.sourceforge.net. [ABSTRACT FROM AUTHOR]

PET scanners with partial-ring geometry have been proposed for various imaging purposes. The incomplete projection data obtained from this design cause undesirable artifacts in the reconstructed images. In this study, we investigated the performance of a deep learning (DL) based method for the recovery of partial-ring PET images. Twenty digital brain phantoms were used in the Monte Carlo simulation toolkit, SimSET, to simulate 15 min full-ring PET scans. Partial-ring PET data were generated from full-ring PET data by removing coincidence events that hit these specific detector blocks. A convolutional neural network based on the residual U-Net architecture was trained to predict full-ring data from partial-ring data in either the projection or image domain. The performance of the proposed DL-based method was evaluated by comparing with the PET images reconstructed using the full-ring projection data in terms of the mean squared error (MSE), structural similarity (SSIM) index and recovery coefficient (RC). The MSE results showed the superiority of the image-domain approach in reduction of 91.7% in contrast to 14.3% for the projection-domain approach. Therefore, the image-domain approach was used to study the influence of the number of detector block removal. The SSIM results were 0.998, 0.996 and 0.993 for 3, 5 and 7 detector block removals, respectively. The activity of gray and white matters could be fully recovered even with 7 detector block removal, while the RCs of two artificially inserted small lesions (3 pixels in diameter) in the testing data were 94%, 89% and 79% for 3, 5, and 7 detector block removals, respectively. Our simulation results suggest that DL has the potential to recover partial-ring PET images. [ABSTRACT FROM AUTHOR]

Radiation exposure and associated radiation risks are major concerns for fetal development for pregnant patients who undergo radiation therapy or diagnostic imaging procedures. In order to accurately estimate the radiation dose to the fetus and assess the uncertainty of fetal position and rotation, three hybrid computational fetus phantoms were constructed using magnetic resonance imaging (MRI) for each fetus model as a starting point to construct a complete anatomically accurate fetus, gravid uterus, and placenta. A total of 27 fetal organs were outlined from radiological images via the Velocity Treatment Planning System. The DICOM-Structure set was imported to Rhinoceros software for further reconstruction of 3D fetus phantom model sets. All fetal organ masses were compared with ICRP-89 reference data. Our fetal model series corresponds to 20, 31, and 35 weeks of pregnancy, thus covering the second and third trimester. Fetal positions and locations were carefully adapted to represent the real fetus locations inside the uterus for each trimester of pregnancy. The new series of hybrid computational fetus models together with pregnant female models can be used in evaluating fetal radiation doses in diagnostic imaging and radiotherapy procedures. [ABSTRACT FROM AUTHOR]

Clinical translation of optoacoustic imaging is fostered by the rapid technical advances in imaging performance as well as the growing number of clinicians recognizing the immense diagnostic potential of this technology. Clinical optoacoustic systems are available in multiple configurations, including hand-held and endoscopic probes as well as raster-scan approaches. The hardware design must be adapted to the accessible portion of the imaged region and other application-specific requirements pertaining the achievable depth, field of view or spatio-temporal resolution. Equally important is the adequate choice of the signal and image processing approach, which is largely responsible for the resulting imaging performance. Thus, new image reconstruction algorithms are constantly evolving in parallel to the newly-developed set-ups. This review focuses on recent progress on optoacoustic image formation algorithms and processing methods in the clinical setting. Major reconstruction challenges include real-time image rendering in two and three dimensions, efficient hybridization with other imaging modalitites as well as accurate interpretation and quantification of bio-markers, herein discussed in the context of ongoing progress in clinical translation. [ABSTRACT FROM AUTHOR]

Low-dose x-ray CT is a major research area with high clinical impact. Compressed sensing using view-based sparse sampling and sparsity-promoting regularization has shown promise in simulations, but these methods can be difficult to implement on diagnostic clinical CT scanners since the x-ray beam cannot be switched on and off rapidly enough. An alternative to view-based sparse sampling is interrupted-beam sparse sampling. SparseCT is a recently-proposed interrupted-beam scheme that achieves sparse sampling by blocking a portion of the beam using a multislit collimator (MSC). The use of an MSC necessitates a number of modifications to the standard compressed sensing reconstruction pipeline. In particular, we find that SparseCT reconstruction is feasible within a model-based image reconstruction framework that incorporates data fidelity weighting to consider penumbra effects and source jittering to consider the effect of partial source obstruction. Here, we present these modifications and demonstrate their application in simulations and real-world prototype scans. In simulations compared to conventional low-dose acquisitions, SparseCT is able to achieve smaller normalized root-mean square differences and higher structural similarity measures on two reduction factors. In prototype experiments, we successfully apply our reconstruction modifications and maintain image resolution at quarter-dose reduction level. The SparseCT design requires only small hardware modifications to current diagnostic clinical scanners, opening up new possibilities for CT dose reduction. [ABSTRACT FROM AUTHOR]

Mumford–Shah (MS) functional has emerged as a regularization technique in x-ray computed tomography (CT) recently. However, for high-resolution CT applications, the huge size of both projection data and image leads to an implementation difficulty. In this work, we propose an approach to implement and accelerate MS regularization on a multi-GPU platform to resolve the issue of data size and rich onboard memory and computing units. We have established a novel partition scheme of the 3D volume under reconstruction and corresponding multithread parallel acceleration strategy to fully utilize the computing resource of multi-GPUs. Our implementation is highly modularized and can be easily scaled with the configuration of GPUs. Experiment results with simulation data as well as real data demonstrate a superior reconstruction quality in contrast to the total variation regularization approach, especially for the ultra-low-dose case. Moreover, this is the first time that MS regularization is used for 3D reconstruction of huge images up to 30723 voxels within 12 min. [ABSTRACT FROM AUTHOR]