Generalized-equiangular geometry CT: Concept and shift-invariant FBP algorithms.

BACKGROUND: With advanced x-ray source and detector technologies being continuously developed, non-traditional CT geometries have been widely explored. Generalized-Equiangular Geometry CT (GEGCT) architecture, in which an x-ray source might be positioned radially far away from the focus of arced detector array that is equiangularly spaced, is of importance in many novel CT systems and designs. PURPOSE: GEGCT, unfortunately, has no theoretically exact and shift-invariant analytical image reconstruction algorithm in general. In this study, to obtain fast and accurate reconstruction from GEGCT and to promote its system design and optimization, an in-depth investigation on a group of approximate Filtered Back-Projection (FBP) algorithms with a variety of weighting strategies has been conducted. METHODS: The architecture of GEGCT is first presented and characterized by using a normalized-radial-offset distance (NROD). Next, shift-invariant weighted FBP-type algorithms are derived in a unified framework, with pre-filtering, filtering, and post-filtering weights, for both fixed and dynamic NROD configurations. Three viable weighting strategies are then presented including a classic one developed by Besson in the literature and two new ones generated from a curvature fitting and from an empirical formula, where all of the three weights can be expressed as certain functions of NROD. After that, an analysis of reconstruction accuracy is conducted with a wide range of NROD. Finally, the weighted FBP algorithm for GEGCT is extended to a three-dimensional form in the case of cone-beam scan with a cylindrical detector array. RESULTS: Theoretical analysis and numerical study show that weights in the shift-invariant FBP algorithms can guarantee highly accurate reconstruction for GEGCT. A simulation of Shepp-Logan phantom and a GEGCT scan of lung mimicked by using a clinical lung CT dataset both demonstrate that FBP reconstructions with Besson and polynomial weights can achieve excellent image quality, with Peak Signal to Noise Ratio and Structural Similarity being at the same level as that from the standard equiangular fan-beam CT scan. Reconstruction of a cylinder object with multiple contrasts from simulated GEGCT scan with dynamic NROD is also highly consistent with fixed ones when using the Besson and polynomial weights, with root mean square error less than 7 hounsfield units, demonstrating the robustness and flexibility of the presented FBP algorithms. In terms of resolution, the direct FBP methods for GEGCT could achieve 1.35 lp/mm of spatial resolution at 10% modulation transfer functions point, higher than that of the rebinning method which can only reach 1.14 lp/mm. Moreover, 3D reconstructions of a disc phantom reveal that a greater value of NROD for GEGCT will bring less cone beam artifacts as expected. CONCLUSIONS: We propose the concept of GEGCT and investigate the feasibility of using shift-invariant weighted FBP-type algorithms for reconstruction from GEGCT data without rebinning. A comprehensive analysis and phantom studies have been conducted to validate the effectiveness of proposed weighting strategies in a wide range of NROD for GEGCT with fixed and dynamic NROD.

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

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

Deep-Learning-Based Metal Artefact Reduction With Unsupervised Domain Adaptation Regularization for Practical CT Images.

CT metal artefact reduction (MAR) methods based on supervised deep learning are often troubled by domain gap between simulated training dataset and real-application dataset, i.e., methods trained on simulation cannot generalize well to practical data. Unsupervised MAR methods can be trained directly on practical data, but they learn MAR with indirect metrics and often perform unsatisfactorily. To tackle the domain gap problem, we propose a novel MAR method called UDAMAR based on unsupervised domain adaptation (UDA). Specifically, we introduce a UDA regularization loss into a typical image-domain supervised MAR method, which mitigates the domain discrepancy between simulated and practical artefacts by feature-space alignment. Our adversarial-based UDA focuses on a low-level feature space where the domain difference of metal artefacts mainly lies. UDAMAR can simultaneously learn MAR from simulated data with known labels and extract critical information from unlabeled practical data. Experiments on both clinical dental and torso datasets show the superiority of UDAMAR by outperforming its supervised backbone and two state-of-the-art unsupervised methods. We carefully analyze UDAMAR by both experiments on simulated metal artefacts and various ablation studies. On simulation, its close performance to the supervised methods and advantages over the unsupervised methods justify its efficacy. Ablation studies on the influence from the weight of UDA regularization loss, UDA feature layers, and the amount of practical data used for training further demonstrate the robustness of UDAMAR. UDAMAR provides a simple and clean design and is easy to implement. These advantages make it a very feasible solution for practical CT MAR.

Method of sparse-view coded-aperture x-ray diffraction tomography.

Objective.X-ray diffraction (XRD) has been considered as a valuable diagnostic technology providing material specific 'finger-print' information i.e. XRD pattern to distinguish different biological tissues. XRD tomography (XRDT) further obtains spatial-resolved XRD pattern distribution, which has become a frontier biological sample inspection method. Currently, XRD computed tomography (XRD-CT) featured by the conventional CT scan mode with rotation has the best spatial resolution among various XRDT methods, but its scan process takes hours. Meanwhile, snapshot XRDT methods such as coded-aperture XRDT (CA-XRDT) aim at direct imaging without scan movements. With compressed-sensing acquisition applied, CA-XRDT significantly shortens data acquisition time. However, the snapshot acquisition results in a significant drop in spatial resolution. Hence, we need an advanced XRDT method that significantly accelerates XRD-CT acquisition and still maintains an acceptable imaging accuracy for biological sample inspection.Approach.Inspired by the high spatial resolution of XRD-CT from rotational scan and the fast compressed-sensing acquisition in snapshot CA-XRDT (SnapshotCA-XRDT), we proposed a new XRDT imaging method: sparse-view rotational CA-XRDT (RotationCA-XRDT). It takes SnapshotCA-XRDT as a preliminary depth-resolved XRDT method, and combines rotational scan to significantly improve the spatial resolution. A model-based iterative reconstruction (MBIR) method is adopted for RotationCA-XRDT. Moreover, we suggest a refined system model calculation for the RotationCA-XRDT MBIR which is a key factor to improve reconstruction image quality.Main results.We conducted our experimental validation based on Monte-Carlo simulation for a breast sample. The results show that the proposed RotationCA-XRDT method succeeded in producing good images for detecting 2 mm square carcinoma with a 15-view scan. The spatial resolution is significantly improved from current SnapshotCA-XRDT methods. With our refined system model, MBIR can obtain high quality images with little artifacts.Significance.In this work, we proposed a new high spatial resolution XRDT method combining coded-aperture compressed-sensing acquisition and sparse-view scan. The proposed RotationCA-XRDT method obtained significantly better image resolution than current SnapshotCA-XRDT methods in the field. It is of great potential for biological sample XRDT inspection. The proposed RotationCA-XRDT is the fastest millimetre-resolution XRDT method in the field which reduces the scan time from hours to minutes.

Sam's Net: A Self-Augmented Multistage Deep-Learning Network for End-to-End Reconstruction of Limited Angle CT.

Limited angle reconstruction is a typical ill-posed problem in computed tomography (CT). Given incomplete projection data, images reconstructed by conventional analytical algorithms and iterative methods suffer from severe structural distortions and artifacts. In this paper, we proposed a self-augmented multi-stage deep-learning network (Sam's Net) for end-to-end reconstruction of limited angle CT. With the merit of the alternating minimization technique, Sam's Net integrates multi-stage self-constraints into cross-domain optimization to provide additional constraints on the manifold of neural networks. In practice, a sinogram completion network (SCNet) and artifact suppression network (ASNet), together with domain transformation layers constitute the backbone for cross-domain optimization. An online self-augmentation module was designed following the manner defined by alternating minimization, which enables a self-augmented learning procedure and multi-stage inference manner. Besides, a substitution operation was applied as a hard constraint for the solution space based on the data fidelity and a learnable weighting layer was constructed for data consistency refinement. Sam's Net forms a new framework for ill-posed reconstruction problems. In the training phase, the self-augmented procedure guides the optimization into a tightened solution space with enriched diverse data distribution and enhanced data consistency. In the inference phase, multi-stage prediction can improve performance progressively. Extensive experiments with both simulated and practical projections under 90-degree and 120-degree fan-beam configurations validate that Sam's Net can significantly improve the reconstruction quality with high stability and robustness.

Reciprocal-FDK reconstruction for x-ray diffraction computed tomography.

Objective.X-ray diffraction (XRD) technology uses x-ray small-angle scattering signal for material analysis, which is highly sensitive to material inter-molecular structure. To meet the high spatial resolution requirement in applications such as medical imaging, XRD computed tomography (XRDCT) has been proposed to provide XRD intensity with improved spatial resolution from point-wise XRD scan. In XRDCT, 2D spatial tomography corresponds to a 3D reconstruction problem with the third dimension being the XRD spectrum dimension, i.e. the momentum transfer dimension. Current works in the field have studied reconstruction methods for either angular-dispersive XRDCT or energy-dispersive XRDCT for small samples. The approximations used are only suitable for regions near the XRDCT iso-center. A new XRDCT reconstruction method is needed for more general imaging applications.Approach.We derive a new FDK-type reconstruction method (Reciprocal-FDK) for XRDCT without limitation on object size. By introducing a set of reciprocal variables, the XRDCT model is transformed into a classical cone-parallel CT model, which is an extension of a circular-trajectory cone-beam CT model, after which the FDK method is applied for XRDCT reconstruction.Main results.Both analytical simulation and Monte Carlo simulation experiments are conducted to validate the XRDCT reconstruction method. The results show that when compared to existing analytical reconstruction methods, there are improvements in the proposed Reciprocal-FDK method with regard to relative structure reconstruction and XRD pattern peak reconstruction. Since cone-parallel CT does not satisfy the data completeness condition, cone-angle effect affects the reconstruction accuracy of XRDCT. The property of cone-angle effect in XRDCT is also analyzed with ablation studies.Significance.We propose a general analytical reconstruction method for XRDCT without constraint on object size. Reciprocal-FDK provides a complete derivation and theoretical support for XRDCT reconstruction by analogy to the well-studied cone-parallel CT model. In addition, the intrinsic problem with the XRDCT data model and the corresponding reconstruction error are discussed for the first time.

Analytical covariance estimation for iterative CT reconstruction methods.

Covariance of reconstruction images are useful to analyze the magnitude and correlation of noise in the evaluation of systems and reconstruction algorithms. The covariance estimation requires a big number of image samples that are hard to acquire in reality. A covariance propagation method from projection by a few noisy realizations is studied in this work. Based on the property of convergent points of cost funtions, the proposed method is composed of three steps, (1) construct a relationship between the covariance of projection and corresponding reconstruction from cost functions at its convergent point, (2) simplify the covariance relationship constructed in (1) by introducing an approximate gradient of penalties, and (3) obtain an analytical covariance estimation according to the simplified relationship in (2). Three approximation methods for step (2) are studied: the linear approximation of the gradient of penalties (LAM), the Taylor apprximation (TAM), and the mixture of LAM and TAM (MAM). TV and qGGMRF penalized weighted least square methods are experimented on. Results from statistical methods are used as reference. Under the condition of unstable 2nd derivative of penalties such as TV, the covariance image estimated by LAM accords to reference well but of smaller values, while the covarianc estimation by TAM is quite off. Under the conditon of relatively stable 2nd derivative of penalties such as qGGMRF, TAM performs well and LAM is again with a negative bias in magnitude. MAM gives a best performance under both conditions by combining LAM and TAM. Results also show that only one noise realization is enough to obtain reasonable covariance estimation analytically, which is important for practical usage. This work suggests the necessity and a new way to estimate the covariance for non-quadratically penalized reconstructions. Currently, the proposed method is computationally expensive for large size reconstructions.Computational efficiency is our future work to focus.

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

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

Fluence adaptation for contrast-based dose optimization in x-ray phase-contrast imaging.

PURPOSE: X-ray phase-contrast imaging (XPCI) can provide multiple contrasts with great potentials for clinical and industrial applications, including conventional attenuation, phase contrast, and dark field. Grating-based imaging (GBI) and edge-illumination (EI) are two promising types of XPCI as the conventional x-ray sources can be directly utilized. For the GBI and EI systems, the phase-stepping acquisition with multiple exposures at a constant fluence is usually adopted in the literature.This work, however, attempts to challenge such a constant fluence concept during the phase-stepping process and proposes a fluence adaptation mechanism for dose reduction. METHOD: Given the importance of patient radiation dose for clinical applications, numerous studies have tried to reduce patient dose in XPCI by altering imaging system designs, data acquisition, and information retrieval. Recently, analytic multiorder moment analysis has been proposed to improve the computing efficiency. In these algorithms, multiple contrasts can be calculated by summing together the weighted phase-stepping curves (PSCs) with some kernel functions, which suggests us that the raw data at different steps have different contributions for the noise in retrieved contrasts. Therefore, it is possible to improve the noise performance by adjusting the fluence distribution during the phase-stepping process directly. Based on analytic retrieval formulas and the Gaussian noise model for detected signals, we derived an optimal adaptive fluence distribution, which is proportional to the absolute weighting kernel functions and the root of original sample PSCs acquired under the constant fluence. Considering that the original sample PSC might be unavailable, we proposed two practical forms for the GBI and EI systems, which are also able to reduce the contrast noise when comparing with the constant fluence distribution. Since the kernel functions are target contrast-dependent, our proposed fluence adaptation mechanism provides a way of realizing a contrast-based dose optimization while keeping the same noise level. RESULTS: To validate our analyses, simulations and experiments are conducted for the GBI and EI systems. Simulated results demonstrate that the dose reduction ratio between our proposed fluence distributions and the typical constant one can be about 20% for the phase contrast, which is consistent with our theoretical predictions. Although the experimental noise reduction ratios are a little smaller than the theoretical ones, low-dose experiments observe better noise performance by our proposed method. Our simulated results also give out the effective ranges of the parameters of the PSCs, such as the visibility in the GBI, the standard deviation, and the mean value in the EI, providing a guidance for the use of our proposed approach in practice. CONCLUSIONS: In this paper, we propose a fluence adaptation mechanism for contrast-based dose optimization in XPCI, which can be applied to the GBI and EI systems. Our proposed method explores a new direction for dose reduction, and may also be further extended to other types of XPCI systems and information retrieval algorithms.

Fourier-based interpretation and noise analysis of the moments of small-angle x-ray scattering in grating-based x-ray phase contrast imaging.

In grating-based x-ray phase contrast imaging, Fourier component analysis (FCA) is usually recognized as a gold standard to retrieve the contrasts including attenuation, phase and dark-field, since it is well-established on wave optics and is of high computational efficiency. Meanwhile, an alternative approach basing on the particle scattering theory is being developed and can provide similar contrasts with FCA by calculating multi-order moments of deconvolved small-angle x-ray scattering, so called as multi-order moment analysis (MMA). Although originated from quite different physics theories, the high consistency between the contrasts retrieved by FCA and MMA implies us that there may be some intrinsic connections between them, which has not been fully revealed to the best of our knowledge. In this work, we present a Fourier-based interpretation of MMA and conclude that the contrasts retrieved by MMA are actually the weighted compositions of Fourier coefficients, which means MMA delivers similar physical information as FCA. Based on the recognized cosine model, we also provide a truncated analytic MMA method, and its computational efficiency can be hundreds of times faster than the original deconvolution-based MMA method. Moreover, a noise analysis for our proposed truncated method is also conducted to further evaluate its performances. The results of numerical simulation and physical experiments support our analyses and conclusions.

Fourier Properties of Symmetric-Geometry Computed Tomography and Its Linogram Reconstruction With Neural Network.

In this work, we investigate the Fourier properties of a symmetric-geometry computed tomography (SGCT) with linearly distributed source and detector in a stationary configuration. A linkage between the 1D Fourier Transform of a weighted projection from SGCT and the 2D Fourier Transform of a deformed object is established in a simple mathematical form (i.e., the Fourier slice theorem for SGCT). Based on its Fourier slice theorem and its unique data sampling in the Fourier space, a Linogram-based Fourier reconstruction method is derived for SGCT. We demonstrate that the entire Linogram reconstruction process can be embedded as known operators into an end-to-end neural network. As a learning-based approach, the proposed Linogram-Net has capability of improving CT image quality for non-ideal imaging scenarios, a limited-angle SGCT for instance, through combining weights learning in the projection domain and loss minimization in the image domain. Numerical simulations and physical experiments on an SGCT prototype platform showed that our proposed Linogram-based method can achieve accurate reconstruction from a dual-SGCT scan and can greatly reduce computational complexity when compared with the filtered backprojection type reconstruction. The Linogram-Net achieved accurate reconstruction when projection data are complete and significantly suppressed image artifacts from a limited-angle SGCT scan mimicked by using a clinical CT dataset, with the average CT number error in the selected regions of interest reduced from 67.7 Hounsfield Units (HU) to 28.7 HU, and the average normalized mean square error of overall images reduced from 4.21e-3 to 2.65e-3.

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

PURPOSE: Tissue textures have been recognized as biomarkers for various clinical tasks. In computed tomography (CT) image reconstruction, it is important but challenging to preserve the texture when lowering x-ray exposure from full- toward low-/ultra-low dose level. Therefore, this paper aims to explore the texture-dose relationship within one tissue-specific pre-log Bayesian CT reconstruction algorithm. METHODS: To enhance the texture in ultra-low dose CT (ULdCT) reconstruction, this paper presents a Bayesian type algorithm. A shifted Poisson model is adapted to describe the statistical properties of pre-log data, and a tissue-specific Markov random field prior (MRFt) is used to incorporate tissue texture from previous full-dose CT, thus called SP-MRFt algorithm. Utilizing the SP-MRFt algorithm, we investigated tissue texture degradation as a function of x-ray dose levels from full dose (100 mAs/120 kVp) to ultralow dose (1 mAs/120 kVp) by using quantitative texture-based evaluation metrics. RESULTS: Experimental results show the SP-MRFt algorithm outperforms conventional filtered back projection (FBP) and post-log domain penalized weighted least square MRFt (PWLS-MRFt) in terms of noise suppression and texture preservation. Comparable results are also obtained with shifted Poisson model with 7 × 7 Huber MRF weights (SP-Huber7). The investigation on texture-dose relationship shows that the quantified texture measures drop monotonically as dose level decreases, and interestingly a turning point is observed on the texture-dose response curve. CONCLUSIONS: This important observation implies that there exists a minimum dose level, at which a given CT scanner (hardware configuration and image reconstruction software) can achieve without compromising clinical tasks. Moreover, the experiment results show that the variance of electronic noise has higher impact than the mean to the texture-dose relationship.

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

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

Stationary computed tomography with source and detector in linear symmetric geometry: Direct filtered backprojection reconstruction.

PURPOSE: Inverse-geometry computed tomography (IGCT) could have great potential in medical applications and security inspections, and has been actively investigated in recent years. In this work, we explore a special architecture of IGCT in a stationary configuration: symmetric-geometry computed tomography (SGCT), where the x-ray source and detector are linearly distributed in a symmetric design. A direct filtered backprojection (FBP)-type algorithm is developed to analytically reconstruct images from the SGCT projections. METHODS: In our proposed SGCT system, a big number of x-ray source points equally distributed along a straight-line trajectory will sequentially fire in an ultra-fast manner in one side, and an equispaced detector whose total length is comparable to that of the source will continuously collect data in the opposite side, as the object to be scanned moves into the imaging plane. We firstly present the overall design of SGCT. An FBP-type reconstruction algorithm is then derived for this unique imaging configuration. With finite length of x-ray source and detector arrays, projection data from one segment of SGCT scan are insufficient for an exact reconstruction. As a result, in practical applications, dual-SGCT scan whose detector segments are placed perpendicular to each other, is of particular interest and is proposed. Two segments of SGCT together can make sure that the passing rays cover at least 180 degrees for each and every point if carefully designed. In general, however, there exists a data redundancy problem for a dual-SGCT. So a weighting strategy is developed to maximize the use of projection data collected while avoid image artifacts. In addition, we further extend the fan-beam SGCT to cone beam and obtain a Feldkamp-Davis-Kress (FDK)-type reconstruction algorithm. Finally, we conduct a set of experimental studies both in simulation and on a prototype SGCT system and validate our proposed methods. RESULTS: A simulation study using the Shepp-Logan head phantom confirms that CT images can be exactly reconstructed from dual-SGCT scan and that our proposed weighting strategy is able to handle the data redundancy properly. Compared with the rebinning-to-parallel-beam method using the forward projection of an abdominal CT dataset, our proposed method is seen to be less sensitive to data truncation. Our algorithm can achieve 10.64 lp/cm of spatial resolution at 50% modulation transfer functions point, higher than that of the rebinning method which can only reach at 9.42 lp/cm even with extremely fine interpolation. Real experiments of a cylindrical object on a prototype SGCT further prove the effectiveness and practicability of the direct FBP method proposed, with similar level of noise performance to rebinning algorithm. CONCLUSIONS: A new concept of SGCT with linearly distributed source and detector is investigated in this work, in which spinning of sources and detectors is no longer needed during data acquisition, simplifying its system design, development, and manufacturing. A direct FBP-type algorithm is developed for analytical reconstruction from SGCT projection data. Numerical and real experiments validate our method and show that exact CT image can be reconstructed from dual-SGCT scan, where data redundancy problem can be solved by our proposed weighting function.

The trigonometric orthogonality of phase-stepping curves in grating-based x-ray phase-contrast imaging: Integral property and its implications for noise optimization.

PURPOSE: Grating-based x-ray phase-contrast imaging (GPCI) is a promising technique for clinical applications as it can provide two newly emerging imaging modalities (differential phase-contrast and dark-field contrast) in addition to the conventional absorption contrast. As far, phase-stepping strategy is the most commonly used approach in GPCI to indirectly acquire differential phase-contrast and dark-field contrast. It is known that the obtained phase-stepping curves (PSCs) have the cosine property and the convolution property, leading to two types of information retrieval approaches in literature: the Fourier component analysis and the multi-order moment analysis. The purpose of this paper is to derive a new property of PSCs and apply the property to noise optimization for information retrieval. METHODS: Based on the cosine expression of the flat PSC without the sample and the well-established convolution relationship between the flat PSC and the sample PSC, we reveal an important integral property of PSCs: the inner product of PSCs and an arbitrary function contains only zero-order and first-order components in the Fourier series. Furthermore, we apply the property to the direct multi-order moment analysis and propose a set of generalized forms including an optimal one in the presence of noise. RESULTS: To validate the effectiveness of our analysis, we compared the simulated and real experiment results retrieved by the original direct multi-order moment analysis with the ones retrieved by our proposed noise-optimal form. A significant improvement of noise performance by our method is observed and the improvement ratio in differential phase-contrast is consistent with our theoretical calculation (39.2%). CONCLUSIONS: In this paper, we reveal a new integral property of the acquired PSCs with and without samples in GPCI, which can be applied to information retrieval approaches like the direct multi-order moment analysis. Then we optimize these approaches to improve the noise performance, offering great potentials of dose reduction in practical applications.

Metal artifact reduction for practical dental computed tomography by improving interpolation-based reconstruction with deep learning.

PURPOSE: Metal artifact is a quite common problem in diagnostic dental computed tomography (CT) images. Due to the high attenuation of heavy materials such as metal, severe global artifacts can occur in reconstructions. Typical metal artifact reduction (MAR) techniques segment out the metal regions and estimate the corrupted projection data by various interpolation methods. However, interpolations are not accurate and introduce new artifacts or even deform the teeth in the reconstructed image. This work presents a new strategy to take advantage of the power of deep learning for metal artifact reduction. METHOD: The analysis first uses coarse reconstructions from simulated locally interpolated data affected by metal fillings as a starting point. A deep learning network is then trained using the simulated data and applied to practical data. Thus, an easily implemented three-step MAR method is formed: Firstly, use the acquired projection data to create a preliminary image reconstruction with linearly interpolated data for the metal-related projections. Secondly, a deep learning network is used to remove the artifacts from the linear interpolation and recover the nonmetal region information. Thirdly, the method adds the ROI reconstruction of the metal regions. The structures behind the shading artifacts in the direct filtered back-projection (FBP) reconstruction can be partially recovered by interpolation-based MAR (I-MAR) with the network further correcting for interpolation errors. The key to this method is that the linear interpolation reconstruction errors can be easily simulated to train a network and the effectiveness of the network can be easily generalized to I-MAR results in real situations. RESULTS: We trained a network with a simulation dataset and validated the network against a separate simulation dataset. Then, the network was tested using simulation data that did not overlap with the training/validation datasets and real patient datasets. Both tests gave encouraging results with accurate tooth structure recovery and few artifacts. The relative root mean square error and structure similarity index method indexes were significantly improved in the tests. The method was also evaluated by two experienced dentists who gave positive evaluations. CONCLUSIONS: This work presents a strategy to build a transferable learning from simulations to practical systems for metal artifact reduction using a supervised deep learning method. The system transforms the MAR analyses to an interpolation-artifact reduction problem to recover structural details from the coarse interpolation reconstruction. In this way, training data from simulations with ground truth labels can easily model the similar features in real data with I-MAR as the bridge. The network can seamlessly optimize both simulations and real data. The whole method is easily implemented with little computational cost. Test results demonstrated that this is an effective MAR method applicable to practical dental CT systems.

Deep Convolutional Neural Network for Ulcer Recognition in Wireless Capsule Endoscopy: Experimental Feasibility and Optimization.

Wireless capsule endoscopy (WCE) has developed rapidly over the last several years and now enables physicians to examine the gastrointestinal tract without surgical operation. However, a large number of images must be analyzed to obtain a diagnosis. Deep convolutional neural networks (CNNs) have demonstrated impressive performance in different computer vision tasks. Thus, in this work, we aim to explore the feasibility of deep learning for ulcer recognition and optimize a CNN-based ulcer recognition architecture for WCE images. By analyzing the ulcer recognition task and characteristics of classic deep learning networks, we propose a HAnet architecture that uses ResNet-34 as the base network and fuses hyper features from the shallow layer with deep features in deeper layers to provide final diagnostic decisions. 1,416 independent WCE videos are collected for this study. The overall test accuracy of our HAnet is 92.05%, and its sensitivity and specificity are 91.64% and 92.42%, respectively. According to our comparisons of F1, F2, and ROC-AUC, the proposed method performs better than several off-the-shelf CNN models, including VGG, DenseNet, and Inception-ResNet-v2, and classical machine learning methods with handcrafted features for WCE image classification. Overall, this study demonstrates that recognizing ulcers in WCE images via the deep CNN method is feasible and could help reduce the tedious image reading work of physicians. Moreover, our HAnet architecture tailored for this problem gives a fine choice for the design of network structure.

A systematic evaluation and optimization of automatic detection of ulcers in wireless capsule endoscopy on a large dataset using deep convolutional neural networks.

Compared with conventional gastroscopy which is invasive and painful, wireless capsule endoscopy (WCE) can provide noninvasive examination of gastrointestinal (GI) tract. The WCE video can effectively support physicians to reach a diagnostic decision while a huge number of images need to be analyzed (more than 50 000 frames per patient). In this paper, we propose a computer-aided diagnosis method called second glance (secG) detection framework for automatic detection of ulcers based on deep convolutional neural networks that provides both classification confidence and bounding box of lesion area. We evaluated its performance on a large dataset that consists of 1504 patient cases (the largest WCE ulcer dataset to our best knowledge, 1076 cases with ulcers, 428 normal cases). We use 15 781 ulcer frames from 753 ulcer cases and 17 138 normal frames from 300 normal cases for training. Validation dataset consists of 2040 ulcer frames from 108 cases and 2319 frames from 43 normal cases. For test, we use 4917 ulcer frames from 215 ulcer cases and 5007 frames from 85 normal cases. Test results demonstrate the 0.9469 ROC-AUC of the proposed secG detection framework outperforms state-of-the-art detection frameworks including Faster-RCNN (0.9014) and SSD-300 (0.8355), which implies the effectiveness of our method. From the ulcer size analysis, we find the detection of ulcers is highly related to the size. For ulcers with size larger than 1% of the full image size, the sensitivity exceeds 92.00%. For ulcers that are smaller than 1% of the full image size, the sensitivity is around 85.00%. The overall sensitivity, specificity and accuracy are 89.71%, 90.48% and 90.10%, at a threshold value of 0.6706, which implies the potential of the proposed method to suppress oversights and to reduce the burden of physicians.

Fully connected neural network for virtual monochromatic imaging in spectral computed tomography.

Spectral computed tomography (SCT) has advantages in multienergy material decomposition for material discrimination and quantitative image reconstruction. However, due to the nonideal physical effects of photon counting detectors, including charge sharing, pulse pileup and K -escape, it is difficult to obtain precise system models in practical SCT systems. Serious spectral distortion is unavoidable, which introduces error into the decomposition model and affects material decomposition accuracy. Recently, neural networks demonstrated great potential in image segmentation, object detection, natural language processing, etc. By adjusting the interconnection relationship among internal nodes, it provides a way to mine information from data. Considering the difficulty in modeling SCT system spectra and the superiority of data-driven characteristics of neural networks, we proposed a spectral information extraction method for virtual monochromatic attenuation maps using a simple fully connected neural network without knowing spectral information. In our method, virtual monochromatic linear attenuation coefficients can be obtained directly through our neural network, which could contribute to further material recognition. Our method also provides outstanding performance on denoising and artifacts suppression. It can be furnished for SCT systems with different settings of energy bins or thresholds. Various substances available can be used for training. The trained neural network has a good generalization ability according to our results. The testing mean square errors are about 1 × 10 - 05 cm - 2 .

Experimental study to optimize configurations of PCD Spectral CT.

BACKGROUND: High dose efficiency of photon counting detector based spectral CT (PCD-SCT) and its value in some clinical diagnosis have been well acknowledged. However, it has not been widely adopted in practical use for medical diagnosis and security inspection. OBJECTIVE: To evaluate the influence on PCD-SCT from multiple aspects including the number of energy channels, k-edge materials, energy thresholding, basis functions in spectral information decomposition, and the combined optimal setting for these parameters and configurations. METHODS: Basis material decomposition after spatial reconstruction is applied for PCD-SCT. A "one-step" synthesis method, merging decomposition with synthesis, is proposed to obtain virtual monochromatic images. An I-RMSE is computed using the bias part of I-RMSE to describe the difference of a synthesized signal from ground truth and the standard deviation part of I-RMSE to express the noise level. In addition, virtual monochromatic images commonly used in the medical area are also synthesized. Both numerical simulations and practical experiments are conducted for validation. RESULTS: Results indicated that the I-RMSE for matters significantly reduced with an increased number of energy channels compared with dual-energy channel. The maximum reduction is 6% for triple-, 18% for quadruple-and 24% for quintuple-energy, respectively. However, the improvement is not linear, and also slows down after the number of energy channels reaches a certain number. Contrast agents of high concentration can introduce up to 50% error to surrounding matters. Moreover, different energy partitions influence the total error, which demonstrates the necessity of energy threshold optimization. Last, the optimal basis-material combination varies according to targeted imaging matters and the interested monochromatic energies. CONCLUSIONS: Gain from more energy channels could be significant with the increase of energy channel number. Introduction of contrast agents in scanned objects will increase overall error in spectral CT imaging. Energy thresholding optimization is beneficial for information recovery. Moreover, the choice of basis materials could also be important to obtain low noise results. With these studies of the effect from various configurations for PCD-SCT, one may optimize the configuration of PCD-SCT accordingly.