Spatial-temporal V-Net for automatic segmentation and quantification of right ventricle on gated myocardial perfusion SPECT images.

BACKGROUND: Functional assessment of right ventricle (RV) using gated myocardial perfusion single-photon emission computed tomography (MPS) heavily relies on the precise extraction of right ventricular contours. PURPOSE: In this paper, we present a new deep-learning-based model integrating both the spatial and temporal features in gated MPS images to perform the segmentation of the RV epicardium and endocardium. METHODS: By integrating the spatial features from each cardiac frame of the gated MPS and the temporal features from the sequential cardiac frames of the gated MPS, we developed a Spatial-Temporal V-Net (ST-VNet) for automatic extraction of RV endocardial and epicardial contours. In the ST-VNet, a V-Net is employed to hierarchically extract spatial features, and convolutional long-term short-term memory (ConvLSTM) units are added to the skip-connection pathway to extract the temporal features. The input of the ST-VNet is ECG-gated sequential frames of the MPS images and the output is the probability map of the epicardial or endocardial masks. A Dice similarity coefficient (DSC) loss which penalizes the discrepancy between the model prediction and the manual annotation was adopted to optimize the segmentation model. RESULTS: Our segmentation model was trained and validated on a retrospective dataset with 45 subjects, and the cardiac cycle of each subject was divided into eight gates. The proposed ST-VNet achieved a DSC of 0.8914 and 0.8157 for the RV epicardium and endocardium segmentation, respectively. The mean absolute error, the mean squared error, and the Pearson correlation coefficient of the RV ejection fraction (RVEF) between the manual annotation and the model prediction were 0.0609, 0.0830, and 0.6985. CONCLUSION: Our proposed ST-VNet is an effective model for RV segmentation. It has great promise for clinical use in RV functional assessment.

Importance of GWAS risk loci and clinical data in predicting asthma using machine-learning approaches.

INTRODUCTION: To understand the risk factors of asthma, we combined genome-wide association study (GWAS) risk loci and clinical data in predicting asthma using machine-learning approaches. METHODS: A case-control study with 123 asthmatics and 100 controls was conducted in the Zhuang population in Guangxi. GWAS risk loci were detected using polymerase chain reaction, and clinical data were collected. Machine-learning approaches were used to identify the major factors that contribute to asthma. RESULTS: A total of 14 GWAS risk loci with clinical data were analyzed on the basis of 10 times the 10-fold cross-validation for all machine-learning models. Using GWAS risk loci or clinical data, the best performances exhibited area under the curve (AUC) values of 64.3% and 71.4%, respectively. Combining GWAS risk loci and clinical data, the XGBoost established the best model with an AUC of 79.7%, indicating that the combination of genetics and clinical data can enable improved performance. We then sorted the importance of features and found the top six risk factors for predicting asthma to be rs3117098, rs7775228, family history, rs2305480, rs4833095, and body mass index. CONCLUSION: Asthma-prediction models based on GWAS risk loci and clinical data can accurately predict asthma, and thus provide insights into the disease pathogenesis.

A new method incorporating deep learning with shape priors for left ventricular segmentation in myocardial perfusion SPECT images.

Accurate segmentation of the left ventricle (LV) is crucial for evaluating myocardial perfusion SPECT (MPS) and assessing LV functions. In this study, a novel method combining deep learning with shape priors was developed and validated to extract the LV myocardium and automatically measure LV functional parameters. The method integrates a three-dimensional (3D) V-Net with a shape deformation module that incorporates shape priors generated by a dynamic programming (DP) algorithm to guide its output during training. A retrospective analysis was performed on an MPS dataset comprising 31 subjects without or with mild ischemia, 32 subjects with moderate ischemia, and 12 subjects with severe ischemia. Myocardial contours were manually annotated as the ground truth. A 5-fold stratified cross-validation was used to train and validate the models. The clinical performance was evaluated by measuring LV end-systolic volume (ESV), end-diastolic volume (EDV), left ventricular ejection fraction (LVEF), and scar burden from the extracted myocardial contours. There were excellent agreements between segmentation results by our proposed model and those from the ground truth, with a Dice similarity coefficient (DSC) of 0.9573 ± 0.0244, 0.9821 ± 0.0137, and 0.9903 ± 0.0041, as well as Hausdorff distances (HD) of 6.7529 ± 2.7334 mm, 7.2507 ± 3.1952 mm, and 7.6121 ± 3.0134 mm in extracting the LV endocardium, myocardium, and epicardium, respectively. Furthermore, the correlation coefficients between LVEF, ESV, EDV, stress scar burden, and rest scar burden measured from our model results and the ground truth were 0.92, 0.958, 0.952, 0.972, and 0.958, respectively. The proposed method achieved a high accuracy in extracting LV myocardial contours and assessing LV functions.

A deep learning-based recognition for dangerous objects imaged in X-ray security inspection device.

Several limitations in algorithms and datasets in the field of X-ray security inspection result in the low accuracy of X-ray image inspection. In the literature, there have been rare studies proposed and datasets prepared for the topic of dangerous objects segmentation. In this work, we contribute a purely manual segmentation for labeling the existing X-ray security inspection dataset namely, SIXRay, with the pixel-level semantic information of dangerous objects. We also propose a composition method for X-ray security inspection images to effectively augment the positive samples. This composition method can quickly obtain the positive sample images using affine transformation and HSV features of X-ray images. Furthermore, to improve the recognition accuracy, especially for adjacent and overlapping dangerous objects, we propose to combine the target detection algorithm (i.e., the softer-non maximum suppression, Softer-NMS) with Mask RCNN, which is named as the Softer-Mask RCNN. Compared with the original model (i.e., Mask RCNN), the Softer-Mask RCNN improves by 3.4% in accuracy (mAP), and 6.2% with adding synthetic data. The study result indicates that our proposed method in this work can effectively improve the recognition performance of dangerous objects depicting in the X-ray security inspection images.

Non-convex optimization based optimal bone correction for various beam-hardening artifacts in CT imaging.

Tube of X-ray computed tomography (CT) system emitting a polychromatic spectrum of photons leads to beam hardening artifacts such as cupping and streaks, while the metal implants in the imaged object results in metal artifacts in the reconstructed images. The simultaneous emergence of various beam-hardening artifacts degrades the diagnostic accuracy of CT images in clinics. Thus, it should be deeply investigated for suppressing such artifacts. In this study, data consistency condition is exploited to construct an objective function. Non-convex optimization algorithm is employed to solve the optimal scaling factors. Finally, an optimal bone correction is acquired to simultaneously correct for cupping, streaks and metal artifacts. Experimental result acquired by a realistic computer simulation demonstrates that the proposed method can adaptively determine the optimal scaling factors, and then correct for various beam-hardening artifacts in the reconstructed CT images. Especially, as compared to the nonlinear least squares before variable substitution, the running time of the new CT image reconstruction algorithm decreases 82.36% and residual error reduces 55.95%. As compared to the nonlinear least squares after variable substitution, the running time of the new algorithm decreases 67.54% with the same residual error.

A deep learning-based approach to automatic proximal femur segmentation in quantitative CT images.

Automatic CT segmentation of proximal femur has a great potential for use in orthopedic diseases, especially in the imaging-based assessments of hip fracture risk. In this study, we proposed an approach based on deep learning for the fast and automatic extraction of the periosteal and endosteal contours of proximal femur in order to differentiate cortical and trabecular bone compartments. A three-dimensional (3D) end-to-end fully convolutional neural network (CNN), which can better combine the information among neighbor slices and get more accurate segmentation results by 3D CNN, was developed for our segmentation task. The separation of cortical and trabecular bones derived from the QCT software MIAF-Femur was used as the segmentation reference. Two models with the same network structures were trained, and they achieved a dice similarity coefficient (DSC) of 97.82% and 96.53% for the periosteal and endosteal contours, respectively. Compared with MIAF-Femur, it takes half an hour to segment a case, and our CNN model takes a few minutes. To verify the excellent performance of our model for proximal femoral segmentation, we measured the volumes of different parts of the proximal femur and compared it with the ground truth, and the relative errors of femur volume between predicted result and ground truth are all less than 5%. This approach will be expected helpful to measure the bone mineral densities of cortical and trabecular bones, and to evaluate the bone strength based on FEA.

An Ensemble Hybrid Feature Selection Method for Neuropsychiatric Disorder Classification.

Magnetic resonance imagings (MRIs) are providing increased access to neuropsychiatric disorders that can be made available for advanced data analysis. However, the single type of data limits the ability of psychiatrists to distinguish the subclasses of this disease. In this paper, we propose an ensemble hybrid features selection method for the neuropsychiatric disorder classification. The method consists of a 3D DenseNet and a XGBoost, which are used to select the image features from structural MRI images and the phenotypic feature from phenotypic records, respectively. The hybrid feature is composed of image features and phenotypic features. The proposed method is validated in the Consortium for Neuropsychiatric Phenomics (CNP) dataset, where samples are classified into one of the four classes (healthy controls (HC), attention deficit hyperactivity disorder (ADHD), bipolar disorder (BD), and schizophrenia (SD)). Experimental results show that the hybrid feature can improve the performance of classification methods. The best accuracy of binary and multi-class classification can reach 91.22 and 78.62 percent, respectively. We analyze the importance of phenotypic features and image features in different classification tasks. The importance of the structure MRI images is highlighted by incorporating phenotypic features with image features to generate hybrid features. We also visualize the features of three neuropsychiatric disorders and analyze their locations in the brain region.

A survey on incorporating domain knowledge into deep learning for medical image analysis.

Although deep learning models like CNNs have achieved great success in medical image analysis, the small size of medical datasets remains a major bottleneck in this area. To address this problem, researchers have started looking for external information beyond current available medical datasets. Traditional approaches generally leverage the information from natural images via transfer learning. More recent works utilize the domain knowledge from medical doctors, to create networks that resemble how medical doctors are trained, mimic their diagnostic patterns, or focus on the features or areas they pay particular attention to. In this survey, we summarize the current progress on integrating medical domain knowledge into deep learning models for various tasks, such as disease diagnosis, lesion, organ and abnormality detection, lesion and organ segmentation. For each task, we systematically categorize different kinds of medical domain knowledge that have been utilized and their corresponding integrating methods. We also provide current challenges and directions for future research.

An approach for fully automatic femoral neck-shaft angle evaluation on radiographs.

Femoral neck-shaft angle (NSA) is the angle included by the femoral neck axis (FNA) and the femoral shaft axis (FSA), which is a critical anatomic measurement index for evaluating the biomechanics of the hip joint. Aiming at solving the problem that the physician's manual measurement of the NSA is time consuming and irreproducible, this paper proposes a fully automatic approach for evaluating the femoral NSA on radiographs. We first present an improved deep convolutional generative adversarial network to automatically segment the femoral region of interest on radiographs of the pelvis. Then based on the geometrical characteristic of the femoral shape, the FNA and FSA are fitted, respectively, and thus, the NSA can be evaluated conveniently. The average accuracy of the proposed approach for NSA evaluation is 97.24%, and the average deviation is 2.58° as compared to the measurements manually evaluated by experienced physicians. There is no significant statistical difference (P = 0.808) between the manual and automatic measurements, and Pearson's correlation coefficient is 0.904. It is validated that the proposed approach can provide an effective and reliable tool for automatically evaluating the NSA on radiographs.

An Automatic Classification of the Early Osteonecrosis of Femoral Head with Deep Learning.

BACKGROUND: Osteonecrosis of Femoral Head (ONFH) is a common complication in orthopaedics, wherein femoral structures are usually damaged due to the impairment or interruption of femoral head blood supply. AIM: In this study, an automatic approach for the classification of the early ONFH with deep learning has been proposed. METHODS: All femoral CT slices according to their spatial locations with the Convolutional Neural Network (CNN) are first classified. Therefore, all CT slices are divided into upper, middle or lower segments of femur head. Then the femur head areas can be segmented with the Conditional Generative Adversarial Network (CGAN) for each part. The Convolutional Autoencoder is employed to reduce dimensions and extract features of femur head, and finally K-means clustering is used for an unsupervised classification of the early ONFH. RESULTS: To invalidate the effectiveness of the proposed approach, the experiments on the dataset with 120 patients are carried out. The experimental results show that the segmentation accuracy is higher than 95%. The Convolutional Autoencoder can reduce the dimension of data, the Peak Signal- to-Noise Ratios (PSNRs) are better than 34dB for inputs and outputs. Meanwhile, there is a great intra-category similarity, and a significant inter-category difference. CONCLUSION: The research on the classification of the early ONFH has a valuable clinical merit, and hopefully it can assist physicians to apply more individualized treatment for patient.

Clustering of morphological fracture lines for identifying intertrochanteric fracture classification with Hausdorff distance-based K-means approach.

OBJECTIVES: The aim of this study was to develop a systematic three-dimensional (3D) classification of intertrochanteric fractures by clustering the morphological features of fracture lines using the Hausdorff distance-based K-means approach and assess the usefulness of it in the clinical setting. METHODS: We retrospectively analyzed the data of 504 patients with intertrochanteric fractures who underwent closed reduction and intramedullary internal fixation. The morphological fracture lines of all patients extracted from computed tomography were transcribed freehand onto the template. All fracture lines were then clustered into five distinct types using the Hausdorff distance-based K-means clustering method. Five radiographic parameters and four functional parameters were used to evaluate the postoperative functional states and mobilization levels. Postoperative complications were also recorded. RESULTS: Intertrochanteric fractures were classified into five types: type I (108/504, 21.4%), simple fracture with intact lateral femoral wall and greater trochanter fragment; type II (85/504, 16.9%), simple fracture with intact lateral femoral wall with/without lesser trochanter detachment; type III (147/504, 29.2%), fractures with intertrochanteric crest detachment involving the lesser trochanter and greater trochanter with an intact lateral femoral wall; type IV (113/504, 22.4%), fractures with large intertrochanteric crest detachment and large lesser trochanter and greater trochanter detachment partially involving the lateral femoral wall and less medial cortical support; type V (51/504, 10.1%), a combination of pertrochanteric and lateral fracture line involving the entire lateral femoral wall and lesser trochanter detachment. Parameters of femoral neck-shaft angle and sliding distance of the cephalic nail were significantly different among types. The complication rate generally increased from type I to type V (P = 0.035). CONCLUSIONS: The unsupervised clustering can achieve identification of the type of intertrochanteric fractures with clinical significance. The Tang classification can be used to describe fracture morphology, predict the possibility of achieving stable reduction and the risk of complications following intramedullary fixation.

An algorithm of computing 3D geometric attenuation factor.

Precisely evaluating the geometrical attenuation factor is critical for constructing a more complete bidirectional reflectance distribution function (BRDF) model. Conventional theories for determining the geometrical attenuation factor neglect the correlation between height and slope and the self-shadowing or self-masking effects on microsurfaces, leading to results that are discrepant from reality, apparently. This paper presents a three-dimensional (3D) geometrical attenuation factor formulation on 3D Gaussian random rough surfaces. The proposed numerical analysis of 3D geometrical attenuation factor is much more precise for a practical application, especially near grazing angles. Our proposed numerical analysis of 3D geometrical attenuation factor can precisely evaluate the BRDF model.

Development and validation of a new method to diagnose apical hypertrophic cardiomyopathy by gated single-photon emission computed tomography myocardial perfusion imaging.

AIM: The aim of this study is to develop and validate a new method to diagnose apical hypertrophic cardiomyopathy (AHCM) by the integral quantitative analysis of myocardial perfusion and wall thickening from gated single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI). PATIENTS AND METHODS: Twenty-two consecutive patients, who showed T wave inversion of at least 3 mm in precordial leads and sinus rhythm in ECG, were enrolled. All the patients underwent cardiac magnetic resonance (CMR), gated rest SPECT MPI and echocardiography. According to CMR diagnostic results, 13 patients were categorized as in the AHCM group and the remaining nine patients were categorized as in the non-AHCM group. Operators who were blinded to the CMR diagnosis independently performed the diagnosis by gated SPECT MPI. The regions of interest inside the apical hotspots on the perfusion polar map were drawn and the mean values of wall thickening in the drawn region of interests were calculated. Using MRI diagnosis as the gold standard, AHCM was diagnosed based on receiver operating characteristic analysis of the mean wall thickening in the apical perfusion hotspot. The area under curve, sensitivity, specificity, and accuracy of our method were 0.97, 100%, 89%, and 95%, respectively. CONCLUSION: Our new method has high sensitivity, specificity, and accuracy against CMR diagnosis. It has great promise to become a clinical tool in the diagnosis of AHCM.

Content-oriented sparse representation (COSR) for CT denoising with preservation of texture and edge.

PURPOSE: Denoising has been a challenging research subject in medical imaging, since the suppression of noise conflicts with the preservation of texture and edges. To address this challenge, we develop a content-oriented sparse representation (COSR) method for denoising in computed tomography (CT). METHODS: An image is segmented into a number of content areas and each of them consists of similar material. Having been ex-painted, each content area is sparsely coded using the dictionary learnt from patches extracted from the corresponding content area. By constraining sparsity, noise is suppressed and the final image is formed by aggregating all denoised content areas. The performance of COSR method is examined with images simulated by computer and generated by multidetector row CT (MDCT), cone beam CT (CBCT), and micro-CT, in which water phantom, anthropomorphic phantom, a human subject, and a small animal are engaged, using the figures of merit, such as standard division (SD), contrast to noise ratio (CNR), and thresholded edge keeping index (EKIth ) and structural similarity index (SSIM). In addition, the optimization of performance by parameter tuning is also investigated. RESULTS: Quantitatively gauged by metrics of noise, EKIth and SSIM, the performance evaluation shows that the proposed COSR method is effective in denoising (>50% reduction in noise) while it outperforms the conventional sparse representation method in preservation of texture and edge by ~20% (gauged by SSIM). It has also been shown that the COSR method is tolerable to inaccuracy in content area segmentation and variation in dictionary learning. Moreover, the computational efficiency of COSR can be substantially improved using prelearnt dictionaries. CONCLUSIONS: The COSR method would find its utility in clinical and preclinical applications, such as low-dose CT, image segmentation, registration, and computer-aided diagnosis. The proposal of COSR denoising is of innovation and significance in the theory and practice of denoising in medical imaging. A demonstration code package is available at https://github.com/xiehq/COSR.

Optimization based beam-hardening correction in CT under data integral invariant constraint.

In computed tomography (CT), the polychromatic characteristics of x-ray photons, which are emitted from a source, interact with materials and are absorbed by a detector, may lead to beam-hardening effect in signal detection and image formation, especially in situations where materials of high attenuation (e.g. the bone or metal implants) are in the x-ray beam. Usually, a beam-hardening correction (BHC) method is used to suppress the artifacts induced by bone or other objects of high attenuation, in which a calibration-oriented iterative operation is carried out to determine a set of parameters for all situations. Based on the Helgasson-Ludwig consistency condition (HLCC), an optimization based method has been proposed by turning the calibration-oriented iterative operation of BHC into solving an optimization problem sustained by projection data. However, the optimization based HLCC-BHC method demands the engagement of a large number of neighboring projection views acquired at relatively high and uniform angular sampling rate, hindering its application in situations where the angular sampling in projection view is sparse or non-uniform. By defining an objective function based on the data integral invariant constraint (DIIC), we again turn BHC into solving an optimization problem sustained by projection data. As it only needs a pair of projection views at any view angle, the proposed BHC method can be applicable in the challenging scenarios mentioned above. Using the projection data simulated by computer, we evaluate and verify the proposed optimization based DIIC-BHC method's performance. Moreover, with the projection data of a head scan by a multi-detector row MDCT, we show the proposed DIIC-BHC method's utility in clinical applications.

Three-Dimensional Weighting in Cone Beam FBP Reconstruction and Its Transformation Over Geometries.

GOALS: With substantially increased number of detector rows in multidetector CT (MDCT), axial scan with projection data acquired along a circular source trajectory has become the method-of-choice in increasing clinical applications. Recognizing the practical relevance of image reconstruction directly from the projection data acquired in the native cone beam (CB) geometry, especially in scenarios wherein the most achievable in-plane resolution is desirable, we present a three-dimensional (3-D) weighted CB-FBP algorithm in such geometry in this paper. METHODS: We start the algorithm's derivation in the cone-parallel geometry. Via changing of variables, taking the Jacobian into account and making heuristic and empirical assumptions, we arrive at the formulas for 3-D weighted image reconstruction in the native CB geometry. RESULTS: Using the projection data simulated by computer and acquired by an MDCT scanner, we evaluate and verify performance of the proposed algorithm for image reconstruction directly from projection data acquired in the native CB geometry. CONCLUSION: The preliminary data show that the proposed algorithm performs as well as the 3-D weighted CB-FBP algorithm in the cone-parallel geometry. SIGNIFICANCE: The proposed algorithm is anticipated to find its utility in extensive clinical and preclinical applications wherein the reconstruction of images in the native CB geometry, i.e., the geometry for data acquisition, is of relevance.

Investigation of the preconditioner-parameter in the preconditioned Chambolle-Pock algorithm applied to optimization-based image reconstruction.

The optimization-based image reconstruction methods have been thoroughly investigated in the field of medical imaging. The Chambolle-Pock (CP) algorithm may be employed to solve these convex optimization image reconstruction programs. The preconditioned CP (PCP) algorithm has been shown to have much higher convergence rate than the ordinary CP (OCP) algorithm. This algorithm utilizes a preconditioner-parameter to tune the implementation of the algorithm to the specific application, which ranges from 0 and 2, but is often set to 1. In this work, we investigated the impact of the preconditioner-parameter on the convergence rate of the PCP algorithm when it is applied to the TV constrained, data-divergence minimization (TVDM) optimization based image reconstruction. We performed the investigations in the context of 2D computed tomography (CT) and 3D electron paramagnetic resonance imaging (EPRI). For 2D CT, we used the Shepp-Logan and two FORBILD phantoms. For 3D EPRI, we used a simulated 6-spheres phantom and a physical phantom. Study results showed that the optimal preconditioner-parameter depends on the specific imaging conditions. Simply setting the parameter equal to 1 cannot guarantee a fast convergence rate. Thus, this study suggests that one should adaptively tune the preconditioner-parameter to obtain the optimal convergence rate of the PCP algorithm.

A Review of Image-guided Approaches for Cardiac Resynchronisation Therapy.

Cardiac resynchronisation therapy (CRT) is a standard treatment for patients with heart failure; however, the low response rate significantly reduces its cost-effectiveness. A favourable CRT response primarily depends on whether implanters can identify the optimal left ventricular (LV) lead position and accurately place the lead at the recommended site. Myocardial imaging techniques, including echocardiography, cardiac magnetic resonance imaging and nuclear imaging, have been used to assess LV myocardial viability and mechanical dyssynchrony, and deduce the optimal LV lead position. The optimal position, presented as a segment of the myocardial wall, is then overlaid with images of the coronary veins from fluoroscopy to aid navigation of the LV lead to the target venous site. Once validated by large clinical trials, these image-guided techniques for CRT lead placement may have an impact on current clinical practice.

Node Immunization with Time-Sensitive Restrictions.

When we encounter a malicious rumor or an infectious disease outbreak, immunizing k nodes of the relevant network with limited resources is always treated as an extremely effective method. The key challenge is how we can insulate limited nodes to minimize the propagation of those contagious things. In previous works, the best k immunised nodes are selected by learning the initial status of nodes and their strategies even if there is no feedback in the propagation process, which eventually leads to ineffective performance of their solutions. In this paper, we design a novel vaccines placement strategy for protecting much more healthy nodes from being infected by infectious nodes. The main idea of our solution is that we are not only utilizing the status of changing nodes as auxiliary knowledge to adjust our scheme, but also comparing the performance of vaccines in various transmission slots. Thus, our solution has a better chance to get more benefit from these limited vaccines. Extensive experiments have been conducted on several real-world data sets and the results have shown that our algorithm has a better performance than previous works.

Axial Cone-Beam Reconstruction by Weighted BPF/DBPF and Orthogonal Butterfly Filtering.

GOAL: The backprojection-filtration (BPF) and the derivative backprojection filtered (DBPF) algorithms, in which Hilbert filtering is the common algorithmic feature, are originally derived for exact helical reconstruction from cone-beam (CB) scan data and axial reconstruction from fan beam data, respectively. These two algorithms can be heuristically extended for image reconstruction from axial CB scan data, but induce severe artifacts in images located away from the central plane, determined by the circular source trajectory. We propose an algorithmic solution herein to eliminate the artifacts. METHODS: The solution is an integration of three-dimensional (3-D) weighted axial CB-BPF/DBPF algorithm with orthogonal butterfly filtering, namely axial CB-BPF/DBPF cascaded with orthogonal butterfly filtering. Using the computer simulated Forbild head and thoracic phantoms that are rigorous in inspecting the reconstruction accuracy, and an anthropomorphic thoracic phantom with projection data acquired by a CT scanner, we evaluate the performance of the proposed algorithm. RESULTS: Preliminary results show that the orthogonal butterfly filtering can eliminate the severe streak artifacts existing in the images reconstructed by the 3-D weighted axial CB-BPF/DBPF algorithm located at off-central planes. CONCLUSION: Integrated with orthogonal butterfly filtering, the 3-D weighted CB-BPF/DBPF algorithm can perform at least as well as the 3-D weighted CB-FBP algorithm in image reconstruction from axial CB scan data. SIGNIFICANCE: The proposed 3-D weighted axial CB-BPF/DBPF cascaded with orthogonal butterfly filtering can be an algorithmic solution for CT imaging in extensive clinical and preclinical applications.