Search

The spatial resolution of photoacoustic tomography (PAT) can be characterized by the point spread function (PSF) of the imaging system. Due to the tomographic detection geometry, the PAT image degradation model could be generally described by using spatially variant PSFs. Deconvolution of the PAT image with these PSFs could restore image resolution and recover object details. Previous PAT image restoration algorithms assume that the degraded images can be restored by either a single uniform PSF, or some blind estimation of the spatially variant PSFs. In this work, we propose a PAT image restoration method to improve image quality and resolution based on experimentally measured spatially variant PSFs. Using photoacoustic absorbing microspheres, we design a rigorous PSF measurement procedure, and successfully acquire a dense set of spatially variant PSFs for a commercial cross-sectional PAT system. A pixel-wise PSF map is further obtained by employing a multi-Gaussian-based fitting and interpolation algorithm. To perform image restoration, an optimization-based iterative restoration model with two kinds of regularizations is proposed. We perform phantom and in vivo mice imaging experiments to verify the proposed method, and the results show significant image quality and resolution improvement.

Background and objective Photoacoustic tomography (PAT) is capable of obtaining cross-sectional images of small animals that represent the optical absorption of biological tissues. The multispectral Interlaced Sparse Sampling PAT, or ISS-PAT, is a previously proposed PAT imaging method that offered high quality images with much sparser transducer angular coverage. Although it provides superior imaging performance, the original ISS-PAT method suffered from a heavy computation burden, which hinders its practical application. Methods Here, we propose a new regularization scheme based on the directional total variation (dTV) for ISS-PAT. This method efficiently imposes the structural information by considering both the edge position and direction information of the anatomical prior image in ISS-PAT. It does not require image segmentation, and can be conveniently solved by a modified alternating direction of multipliers (ADMM) algorithm. Results We perform simulation, tissue mimicking phantom and in vivo small animal experiments to evaluate the proposed scheme. The reconstructed PAT images showed image quality and spectral un-mixing accuracy close to those obtained by non-local means based ISS-PAT, but with much shorter image reconstruction time. For a 1/6 sparse sampling rate, the average efficiency improvement is nearly 16-folds. Conclusions The experimental results demonstrate the feasibility of the dTV regularization scheme for ISS-PAT. Its efficient image reconstruction performance facilitates the potential of the hardware realization and practical applications of the ISS-PAT.

Conducting an accurate motion correction of liver dynamic contrast-enhanced magnetic resonance (DCE-MR) imaging remains challenging because of intensity variations caused by contrast agents. Such variations lead to the failure of the traditional intensity-based registration method. To address this problem, we propose a correlation-weighted sparse representation framework to separate the contrast agent from original liver DCE-MR images. This framework allows the robust registration of motion components over time without intensity variances. Existing sparse coding techniques recover a 3D image containing only contrast agents (named contrast enhancement component) from a manually labeled dictionary, whose column has the same size with the original 3D volume (3D-t mode). The high dimension of the recovery target (3D volume) and the indistinguishability between the unenhanced and enhanced images make accurate coding difficult. In this paper, we predefine an ideal time-intensity curve containing only contrast agents (named contrast agent curve) and recover it from the transpose dictionary (t-3D mode), whose column has been updated into the original time-intensity curves. The low dimension of the target (1D curve) and the significant intergroup difference between contrast agent curves and non-contrast agent curves can estimate a series of pure contrast agent curves. A "correlation-weighted" constraint is introduced for the selection of a coding subset with more contrast agent curves, leading to an efficient and accurate sparse recovery process. Then, the contrast enhancement component can be estimated by the solved sparse coefficients' map and the ideal curve and subtracted from the original DCE-MRI. Finally, we register the de-enhanced images and apply the obtained deformation fields for the original DCE-MRI to achieve the goal of motion correction. We conduct the experiments on both simulated and real liver DCE-MRI data. Compared with other state-of-the-art DCE-MRI registration methods, the experimental results show that our method achieves a better registration performance with less computational efficiency.

Purpose To develop a machine learning approach using convolutional neural network for reducing MRI Gibbs-ringing artifact. Theory and methods Gibbs-ringing artifact in MR images is caused by insufficient sampling of the high frequency data. Existing methods exploit smooth constraints to reduce intensity oscillations near sharp edges at the cost of blurring details. In this work, we developed a machine learning approach for removing the Gibbs-ringing artifact from MR images. The ringing artifact was extracted from the original image using a deep convolutional neural network and then subtracted from the original image to obtain the artifact-free image. Finally, its low-frequency k-space data were replaced with measured counterparts to enforce data fidelity further. We trained the convolutional neural network using 17,532 T2-weighted (T2W) normal brain images and evaluated its performance on T2W images of normal and tumor brains, diffusion-weighted brain images, and T2W knee images. Results The proposed method effectively removed the ringing artifact without noticeable smoothing in T2W and diffusion-weighted images. Quantitatively, images produced by the proposed method were closer to the fully-sampled reference images in terms of the root-mean-square error, peak signal-to-noise ratio, and structural similarity index, compared with current state-of-the-art methods. Conclusion The proposed method presents a novel and effective approach for Gibbs-ringing reduction in MRI. The convolutional neural network-based approach is simple, computationally efficient, and highly applicable in routine clinical MRI.

Four-dimensional cone beam CT (4D-CBCT) imaging can provide accurate location information of real-time breathing for imaging-guided radiotherapy. How to improve the accuracy of 4D-CBCT reconstruction image is a hot topic in current studies. PICCS algorithm performs remarkably in all 4D-CBCT reconstruction algorithms based on CS theory. The improved PICCS algorithm proposed in this paper improves the prior image on the basis of the traditional PICCS algorithm. According to the location information of each phase, the corresponding prior image is constructed, which completely eliminates the motion blur of the reconstructed image caused by the mismatch of the projection data. Meanwhile, the data fidelity model of the proposed method is consistent with the traditional PICCS algorithm. The experimental results showed that the reconstructed image using the proposed method had a clearer organization boundary compared with that of images reconstructed using the traditional PICCS algorithm. This proposed method significantly reduced the motion artifact and improved the image resolution.

Purpose To extend image reconstruction using image-space sampling function (IRIS) to address large-scale motion in multishot diffusion-weighted imaging (DWI). Methods A clustered IRIS (CIRIS) algorithm that would extend IRIS was proposed to correct for large-scale motion. For DWI, CIRIS initially groups the shots into clusters without intracluster large-scale motion and reconstructs each cluster by using IRIS. Then, CIRIS registers these cluster images and combines the registered images by using a weighted average to correct for voxel mismatch caused by intercluster large-scale motion. For diffusion tensor imaging (DTI), CIRIS further reduces the effect of motion on diffusion directions by treating motion-induced direction changes as additional diffusion directions. CIRIS also introduces the detection and rejection of motion-corrupted data to avoid corresponding image degradation. The proposed method was evaluated by simulation and in vivo diffusion datasets. Results Experiments demonstrated that CIRIS can reduce motion-induced blurring and artifacts in DWI and provide more accurate DTI estimations in the presence of large-scale motion, compared with IRIS. Conclusion The proposed method presents a novel approach to correct for large-scale in-plane motion for multishot DWI and is expected to benefit the practical application of high-resolution diffusion imaging.

Preclinical imaging with photoacoustic tomography (PAT) has attracted wide attention in recent years since it is capable of providing molecular contrast with deep imaging depth. The automatic extraction and segmentation of the animal in PAT images is crucial for improving image analysis efficiency and enabling advanced image post-processing, such as light fluence (LF) correction for quantitative PAT imaging. Previous automatic segmentation methods are mostly two-dimensional approaches, which failed to conserve the 3-D surface continuity because the image slices were processed separately. This discontinuity problem further hampers LF correction, which, ideally, should be carried out in 3-D due to spatially diffused illumination. Here, to solve these problems, we propose a volumetric auto-segmentation method for small animal PAT imaging based on the 3-D optimal graph search (3-D GS) algorithm. The 3-D GS algorithm takes into account the relation among image slices by constructing a 3-D node-weighted directed graph, and thus ensures surface continuity. In view of the characteristics of PAT images, we improve the original 3-D GS algorithm on graph construction, solution guidance and cost assignment, such that the accuracy and smoothness of the segmented animal surface were guaranteed. We tested the performance of the proposed method by conducting in vivo nude mice imaging experiments with a commercial preclinical cross-sectional PAT system. The results showed that our method successfully retained the continuous global surface structure of the whole 3-D animal body, as well as smooth local subcutaneous tumor boundaries at different development stages. Moreover, based on the 3-D segmentation result, we were able to simulate volumetric LF distribution of the entire animal body and obtained LF corrected PAT images with enhanced structural visibility and uniform image intensity.

In dynamic positron emission tomography (PET) imaging, the reconstructed image of a single frame often exhibits high noise due to limited counting statistics of projection data. This study proposed a median nonlocal means (MNLM)-based kernel method for dynamic PET image reconstruction. The kernel matrix is derived from median nonlocal means of pre-reconstructed composite images. Then the PET image intensities in all voxels were modeled as a kernel matrix multiplied by coefficients and incorporated into the forward model of PET projection data. Then, the coefficients of each feature were estimated by the maximum likelihood method. Using simulated low-count dynamic data of Zubal head phantom, the quantitative performance of the proposed MNLM kernel method was investigated and compared with the maximum-likelihood method, conventional kernel method with and without median filter, and nonlocal means (NLM) kernel method. Simulation results showed that the MNLM kernel method achieved visual and quantitative accuracy improvements (in terms of the ensemble mean squared error, bias versus variance, and contrast versus noise performances). Especially for frame 2 with the lowest count level of a single frame, the MNLM kernel method achieves lower ensemble mean squared error (10.43%) than the NLM kernel method (13.68%), conventional kernel method with and without median filter (11.88% and 23.50%), and MLEM algorithm (24.77%). The study on real low-dose 18F-FDG rat data also showed that the MNLM kernel method outperformed other methods in visual and quantitative accuracy improvements (in terms of regional noise versus intensity mean performance).

To develop a radiomics signature to predict locoregional recurrence (LR) and distant metastasis (DM), as extracted from pretreatment 2-deoxy-2-[18F]fluoro-d-glucose ([18F]FDG) positron emission tomography/X-ray computed tomography (PET/CT) images in locally advanced nasopharyngeal carcinoma (NPC). Eighty-five patients with Stage III–IVB NPC underwent pretreatment [18F]FDG PET/CT scans and received radiotherapy or chemoradiotherapy. 53 of them achieved disease control, and 32 of them failed after treatment (15: LR, 17: DM). A total of 114 radiomic features were extracted from PET/CT images. For univariate analysis, Wilcoxon test and Chi-square test were used to compare median values of features between different treatment outcomes and predict the risk of treatment failure, respectively. For multivariate analysis, all features were grouped into clusters based on Pearson correlation using hierarchical clustering, and the representative feature of each cluster was chosen by the Relief algorithm. Then sequential floating forward selection (SFFS) coupled with a support vector machine (SVM) classifier were used to derive the optimized feature set in terms of the area under receiver operating characteristic (ROC) curve (AUC). The performance of the model was evaluated by leave-one-out-cross-validation, fivefold cross-validation, tenfold cross-validation. Twenty features had significant differences between disease control and treatment failure. NPC patients with values of Compactness1, Compactness2, Coarseness_NGTDM or SGE_GLGLM above the median as well as patients with values of Irregularity, RLN_GLRLM or GLV_GLSZM below the median, showed a significant (p

Multispectral photoacoustic tomography (PAT) is capable of resolving tissue chromophore distribution based on spectral un-mixing. It works by identifying the absorption spectrum variations from a sequence of photoacoustic images acquired at multiple illumination wavelengths. Due to multispectral acquisition, this inevitably creates a large dataset. To cut down the data volume, sparse sampling methods that reduce the number of detectors have been developed. However, image reconstruction of sparse sampling PAT is challenging because of insufficient angular coverage. During spectral un-mixing, these inaccurate reconstructions will further amplify imaging artefacts and contaminate the results. To solve this problem, we present the interlaced sparse sampling (ISS) PAT, a method that involved: 1) a novel scanning-based image acquisition scheme in which the sparse detector array rotates while switching illumination wavelength, such that a dense angular coverage could be achieved by using only a few detectors; and 2) a corresponding image reconstruction algorithm that makes use of an anatomical prior image created from the ISS strategy to guide PAT image computation. Reconstructed from the signals acquired at different wavelengths (angles), this self-generated prior image fuses multispectral and angular information, and thus has rich anatomical features and minimum artefacts. A specialized iterative imaging model that effectively incorporates this anatomical prior image into the reconstruction process is also developed. Simulation, phantom, and in vivo animal experiments showed that even under 1/6 or 1/8 sparse sampling rate, our method achieved comparable image reconstruction and spectral un-mixing results to those obtained by conventional dense sampling method.

Magnetic resonance electrical properties tomography (MR-EPT) maps the spatial distribution of the patient's electrical conductivity and permittivity using the measured ${{\boldsymbol{B}}_1} \ $ data in a magnetic resonance imaging (MRI) system. Existing MR-EPT methods are usually not clinically accessible owing to their technical limits such as strong noise sensitivity. In this study, we develop a new MR-EPT method that re-expresses the involved differential equations (DEs) based on the divergence theorem. In comparison with traditional methods, the proposed method avoids the grid-wise computation of the second-order derivatives of $\ {\boldsymbol{B}}_1^ + $ , thereby improving the robustness against noise. Besides, for applications where the structural information can be determined in advance, EPs of a region of interest (ROI) can be calculated in a fast and efficient manner. The proposed method is firstly validated with numerical simulations, in which a three-block phantom and an anatomically accurate Duke Head model are used to evaluate the proposed method. Experiments on the 9.4T MRI system were then conducted to validate the simulations. Both results indicated that the proposed MR-EPT solution could provide a more robust reconstruction of electrical properties maps compared with conventional methods.

PURPOSE This study aims to develop an accurate and robust phase-unwrapping method that works effectively under severe noise, rapid-varying phase, and disconnected regions for water-fat Dixon MRI. METHODS The proposed method first segments the phase map into blocks by automatically detecting phase jumps, and then clusters the pixels near phase jumps into residual pixels. Thereafter, the proposed method sequentially performs intrablock, interblock, and residual-pixel unwrapping using the local surface fitting approach. To address intrablock wraps, the proposed method segments each block into subblocks using the phase partition approach and then performs inter-subblock unwrapping using a block-growing approach. The phase derivative variance is used as the quality criterion to determine the region-growing path of residual pixels. The performance of the proposed method was evaluated on simulation and in vivo Dixon data. RESULTS The proposed method obtained accurate phase-unwrapping results in the simulation experiment with severe noise, rapid-varying phase, and disconnected regions, and the mean and SD error ratio was 0.26 ± 0.07%. For 505 in vivo knee and ankle images, the total water-fat swap ratio by the proposed method was 1.78%, whereas those by phase region expanding labeler for unwrapping discrete estimates and clustering and local surface fitting were 38.42% and 7.72%, respectively. CONCLUSION The proposed method achieves accurate and robust performance in phase unwrapping and can benefit phase-related MRI applications such as Dixon water-fat separation.

Attenuation correction for positron-emission tomography (PET)/magnetic resonance (MR) hybrid imaging systems and dose planning for MR-based radiation therapy remain challenging due to insufficient high-energy photon attenuation information. We present a novel approach that uses the learned nonlinear local descriptors and feature matching to predict pseudo computed tomography (pCT) images from T1-weighted and T2-weighted magnetic resonance imaging (MRI) data. The nonlinear local descriptors are obtained by projecting the linear descriptors into the nonlinear high-dimensional space using an explicit feature map and low-rank approximation with supervised manifold regularization. The nearest neighbors of each local descriptor in the input MR images are searched in a constrained spatial range of the MR images among the training dataset. Then the pCT patches are estimated through k-nearest neighbor regression. The proposed method for pCT prediction is quantitatively analyzed on a dataset consisting of paired brain MRI and CT images from 13 subjects. Our method generates pCT images with a mean absolute error (MAE) of 75.25 ± 18.05 Hounsfield units, a peak signal-to-noise ratio of 30.87 ± 1.15 dB, a relative MAE of 1.56 ± 0.5% in PET attenuation correction, and a dose relative structure volume difference of 0.055 ± 0.107% in ${D}_{98\%}$ , as compared with true CT. The experimental results also show that our method outperforms four state-of-the-art methods.

Segmenting organs at risk from head and neck CT images is a prerequisite for the treatment of head and neck cancer using intensity modulated radiotherapy. However, accurate and automatic segmentation of organs at risk is a challenging task due to the low contrast of soft tissue and image artifact in CT images. Shape priors have been proved effective in addressing this challenging task. However, conventional methods incorporating shape priors often suffer from sensitivity to shape initialization and also shape variations across individuals. In this paper, we propose a novel approach to incorporate shape priors into a hierarchical learning-based model. The contributions of our proposed approach are as follows: 1) a novel mechanism for critical vertices identification is proposed to identify vertices with distinctive appearances and strong consistency across different subjects; 2) a new strategy of hierarchical vertex regression is also used to gradually locate more vertices with the guidance of previously located vertices; and 3) an innovative framework of joint shape and appearance learning is further developed to capture salient shape and appearance features simultaneously. Using these innovative strategies, our proposed approach can essentially overcome drawbacks of the conventional shape-based segmentation methods. Experimental results show that our approach can achieve much better results than state-of-the-art methods.

Dynamic cerebral perfusion computed tomography (DCPCT) has the ability to evaluate the hemodynamic information throughout the brain. However, due to multiple 3-D image volume acquisitions protocol, DCPCT scanning imposes high radiation dose on the patients with growing concerns. To address this issue, in this paper, based on the robust principal component analysis (RPCA, or equivalently the low-rank and sparsity decomposition) model and the DCPCT imaging procedure, we propose a new DCPCT image reconstruction algorithm to improve low-dose DCPCT and perfusion maps quality via using a powerful measure, called Kronecker-basis-representation tensor sparsity regularization, for measuring low-rankness extent of a tensor. For simplicity, the first proposed model is termed tensor-based RPCA (T-RPCA). Specifically, the T-RPCA model views the DCPCT sequential images as a mixture of low-rank, sparse, and noise components to describe the maximum temporal coherence of spatial structure among phases in a tensor framework intrinsically. Moreover, the low-rank component corresponds to the "background" part with spatial-temporal correlations, e.g., static anatomical contribution, which is stationary over time about structure, and the sparse component represents the time-varying component with spatial-temporal continuity, e.g., dynamic perfusion enhanced information, which is approximately sparse over time. Furthermore, an improved nonlocal patch-based T-RPCA (NL-T-RPCA) model which describes the 3-D block groups of the "background" in a tensor is also proposed. The NL-T-RPCA model utilizes the intrinsic characteristics underlying the DCPCT images, i.e., nonlocal self-similarity and global correlation. Two efficient algorithms using alternating direction method of multipliers are developed to solve the proposed T-RPCA and NL-T-RPCA models, respectively. Extensive experiments with a digital brain perfusion phantom, preclinical monkey data, and clinical patient data clearly demonstrate that the two proposed models can achieve more gains than the existing popular algorithms in terms of both quantitative and visual quality evaluations from low-dose acquisitions, especially as low as 20 mAs.

Lung 4D computed tomography (4D-CT), which is a time-resolved CT data acquisition, performs an important role in explicitly including respiratory motion in treatment planning and delivery. However, the radiation dose is usually reduced at the expense of inter-slice spatial resolution to minimize radiation-related health risk. Therefore, resolution enhancement along the superior-inferior direction is necessary. In this paper, a super-resolution (SR) reconstruction method based on a patch low-rank matrix reconstruction is proposed to improve the resolution of lung 4D-CT images. Specifically, a low-rank matrix related to every patch is constructed by using a patch searching strategy. Thereafter, the singular value shrinkage is employed to recover the high-resolution patch under the constraints of the image degradation model. The output high-resolution patches are finally assembled to output the entire image. This method is extensively evaluated using two public data sets. Quantitative analysis shows that the proposed algorithm decreases the root mean square error by 9.7%-33.4% and the edge width by 11.4%-24.3%, relative to linear interpolation, back projection (BP) and Zhang et al's algorithm. A new algorithm has been developed to improve the resolution of 4D-CT. In all experiments, the proposed method outperforms various interpolation methods, as well as BP and Zhang et al's method, thus indicating the effectivity and competitiveness of the proposed algorithm.

Purpose Dynamic myocardial perfusion computed tomography (DM-PCT) imaging offers benefits over quantitative assessment of myocardial blood flow (MBF) for diagnosis and risk stratification of coronary artery disease. However, one major drawback of DM-PCT imaging is that a high radiation level is imparted by repeated scanning. To address this issue, in this work, we developed a statistical iterative reconstruction algorithm based on the penalized weighted least-squares (PWLS) scheme by incorporating a motion adaptive sparsity prior (MASP) model to achieve high-quality DM-PCT imaging with low tube current dynamic data acquisition. For simplicity, we refer to the proposed algorithm as “PWLS-MASP’’. Methods The MASP models both the spatial and temporal structured sparsity of DM-PCT sequence images with the assumption that the differences between adjacent frames after motion correction are sparse in the gradient image domain. To validate and evaluate the effectiveness of the present PWLS-MASP algorithm thoroughly, a modified XCAT phantom and preclinical porcine DM-PCT dataset were used in the study. Results The present PWLS-MASP algorithm can obtain high-quality DM-PCT images in both phantom and porcine cases, and outperforms the existing filtered back-projection algorithm and PWLS-based algorithms with total variation regularization (PWLS-TV) and robust principal component analysis regularization (PWLS-RPCA) in terms of noise reduction, streak artifacts mitigation, and time density curve estimation. Moreover, the PWLS-MASP algorithm can yield more accurate diagnostic hemodynamic parametric maps than the PWLS-TV and PWLS-RPCA algorithms. Conclusions The study indicates that there is a substantial advantage in using the present PWLS-MASP algorithm for low-dose DM-PCT, and potentially in other dynamic tomography areas.

Noise usually affects the reliability of quantitative analysis in diffusion-weighted (DW) magnetic resonance imaging (MRI), especially at high b-values and/or high spatial resolution. Higher-order singular value decomposition (HOSVD) has recently emerged as a simple, effective, and adaptive transform to exploit sparseness within multidimensional data. In particular, the patch-based HOSVD denoising has demonstrated superb performance when applied to T1-, T2-, and proton density-weighted MRI data. In this study, we aim to investigate the feasibility of denoising DW data using the HOSVD transform. With the low signal-to-noise ratio in typical DW data, the patch-based HOSVD denoising suffers from stripe artifacts in homogeneous regions because of the HOSVD bases learned from the noisy patches. To address this problem, we propose a novel denoising method. It first introduces a global HOSVD-based denoising as a prefiltering stage to guide the subsequent patch-based HOSVD denoising stage. The HOSVD bases from the patch groups in prefiltered images are then used to transform the noisy patch groups in original DW data. Experiments were performed using simulated and in vivo DW data. Results show that the proposed method significantly reduces stripe artifacts compared with conventional patch-based HOSVD denoising methods, and outperforms two state-of-the-art denoising methods in terms of denoising quality and diffusion parameters estimation.

Four dimensional cone-beam computed tomography (4D-CBCT) has great potential clinical value because of its ability to describe tumor and organ motion. But the challenge in 4D-CBCT reconstruction is the limited number of projections at each phase, which result in a reconstruction full of noise and streak artifacts with the conventional analytical algorithms. To address this problem, in this paper, we propose a motion compensated total variation regularization approach which tries to fully explore the temporal coherence of the spatial structures among the 4D-CBCT phases. In this work, we additionally conduct motion estimation/motion compensation (ME/MC) on the 4D-CBCT volume by using inter-phase deformation vector fields (DVFs). The motion compensated 4D-CBCT volume is then viewed as a pseudo-static sequence, of which the regularization function was imposed on. The regularization used in this work is the 3D spatial total variation minimization combined with 1D temporal total variation minimization. We subsequently construct a cost function for a reconstruction pass, and minimize this cost function using a variable splitting algorithm. Simulation and real patient data were used to evaluate the proposed algorithm. Results show that the introduction of additional temporal correlation along the phase direction can improve the 4D-CBCT image quality.

Suppression of bony structures in chest radiographs (CXRs) is potentially useful for radiologists and computer-aided diagnostic schemes. In this paper, we present an effective deep learning method for bone suppression in single conventional CXR using deep convolutional neural networks (ConvNets) as basic prediction units. The deep ConvNets were adapted to learn the mapping between the gradients of the CXRs and the corresponding bone images. We propose a cascade architecture of ConvNets (called CamsNet) to refine progressively the predicted bone gradients in which the ConvNets work at successively increased resolutions. The predicted bone gradients at different scales from the CamsNet are fused in a maximum-a-posteriori framework to produce the final estimation of a bone image. This estimation of a bone image is subtracted from the original CXR to produce a soft-tissue image in which the bone components are eliminated. Our method was evaluated on a dataset that consisted of 504 cases of real two-exposure dual-energy subtraction chest radiographs (404 cases for training and 100 cases for test). The results demonstrate that our method can produce high-quality and high-resolution bone and soft-tissue images. The average relative mean absolute error of the produced bone images and peak signal-to-noise ratio of the produced soft-tissue images were 3.83% and 38.7dB, respectively. The average bone suppression ratio of our method was 83.8% for the CXRs with pixel sizes of nearly 0.194mm. Furthermore, we apply the trained CamsNet model on the CXRs acquired by various types of X-ray machines, including scanned films, and our method can also produce visually appealing bone and soft-tissue images.

For decades, commercial X-ray computed tomography (CT) scanners have been using the filtered backprojection (FBP) algorithm for image reconstruction. However, the desire for lower radiation doses has pushed the FBP algorithm to its limit. Previous studies have made significant efforts to improve the results of FBP through preprocessing the sinogram, modifying the ramp filter, or postprocessing the reconstructed images. In this paper, we focus on analyzing and processing the stacked view-by-view backprojections (named VVBP-Tensor) in the FBP algorithm. A key challenge for our analysis lies in the radial structures in each backprojection slice. To overcome this difficulty, a sorting operation was introduced to the VVBP-Tensor in its ${z}$ direction (the direction of the projection views). The results show that, after sorting, the tensor contains structures that are similar to those of the object, and structures in different slices of the tensor are correlated. We then analyzed the properties of the VVBP-Tensor, including structural self-similarity, tensor sparsity, and noise statistics. Considering these properties, we have developed an algorithm using the tensor singular value decomposition (named VVBP-tSVD) to denoise the VVBP-Tensor for low-mAs CT imaging. Experiments were conducted using a physical phantom and clinical patient data with different mAs levels. The results demonstrate that the VVBP-tSVD is superior to all competing methods under different reconstruction schemes, including sinogram preprocessing, image postprocessing, and iterative reconstruction. We conclude that the VVBP-Tensor is a suitable processing target for improving the quality of FBP reconstruction, and the proposed VVBP-tSVD is an effective algorithm for noise reduction in low-mAs CT imaging. This preliminary work might provide a heuristic perspective for reviewing and rethinking the FBP algorithm.

To identify optimal machine learning methods for radiomics-based differentiation of local recurrence versus inflammation from post-treatment nasopharyngeal positron emission tomography/X-ray computed tomography (PET/CT) images. Seventy-six nasopharyngeal carcinoma (NPC) patients were enrolled (41/35 local recurrence/inflammation as confirmed by pathology). Four hundred eighty-seven radiomics features were extracted from PET images for each patient. The diagnostic performance was investigated for 42 cross-combinations derived from 6 feature selection methods and 7 classifiers. Of the original cohort, 70 % was applied for feature selection and classifier development, and the remaining 30 % used as an independent validation set. The diagnostic performance was evaluated using area under the ROC curve (AUC), test error, sensitivity, and specificity. Furthermore, the performance of the radiomics signatures against routine features was statistically compared using DeLong’s method. The cross-combination fisher score (FSCR) + k-nearest neighborhood (KNN), FSCR + support vector machines with radial basis function kernel (RBF-SVM), FSCR + random forest (RF), and minimum redundancy maximum relevance (MRMR) + RBF-SVM outperformed others in terms of accuracy (AUC 0.883, 0.867, 0.892, 0.883; sensitivity 0.833, 0.864, 0.831, 0.750; specificity 1, 1, 0.873, 1) and reliability (test error 0.091, 0.136, 0.150, 0.136). Compared with conventional metrics, the radiomics signatures showed higher AUC values (0.867–0.892 vs. 0.817), though the differences were not statistically significant (p = 0.462–0.560). This study identified the most accurate and reliable machine learning methods, which could enhance the application of radiomics methods in the precision of diagnosis of NPC.

Purpose This study aims to develop and evaluate a robust conductivity imaging method that combines total variation and wavelet regularization to enhance the accuracy of conductivity maps. Theory and methods The proposed approach is based on a gradient-based method. The central equation is derived from Maxwell's equation and describes the relationship between conductivity and the transceive phase. A linear system equation is obtained via a finite-difference method and solved using a least-squares method. Total variation and wavelet transform regularization terms are added to the minimization problem and solved using the Split Bregman method to improve reconstruction stability. The proposed approach is compared with conventional and gradient-based methods. Numerical simulations are performed to validate the accuracy of the developed method, and the effects of noise are determined. Phantom and in vivo experiments are conducted at 3 T to verify the clinical applicability of the proposed method. Results Numerical simulations show that the proposed method is more robust than other methods and can suppress the effects of noise. The quantitative conductivity value of the phantom experiment agrees with the measured value. The in vivo experiment results present a clear structure, and the conductivity value of the tumor region is significantly higher than that around healthy tissues. Conclusion The proposed electrical conductivity imaging method can improve the quality of conductivity reconstruction, and thus, has future clinical applications.

Residual cancer burden (RCB) has been proposed to measure the postneoadjuvant breast cancer response. In the workflow of RCB assessment, estimation of cancer cellularity is a critical task, which is conventionally achieved by manually reviewing the hematoxylin and eosin- (H&E-) stained microscopic slides of cancer sections. In this work, we develop an automatic and direct method to estimate cellularity from histopathological image patches using deep feature representation, tree boosting, and support vector machine (SVM), avoiding the segmentation and classification of nuclei. Using a training set of 2394 patches and a test set of 185 patches, the estimations by our method show strong correlation to those by the human pathologists in terms of intraclass correlation (ICC) (0.94 with 95% CI of (0.93, 0.96)), Kendall’s tau (0.83 with 95% CI of (0.79, 0.86)), and the prediction probability (0.93 with 95% CI of (0.91, 0.94)), compared to two other methods (ICC of 0.74 with 95% CI of (0.70, 0.77) and 0.83 with 95% CI of (0.79, 0.86)). Our method improves the accuracy and does not rely on annotations of individual nucleus.

BACKGROUND: Dynamic positron emission tomography (PET) is a powerful tool that provides useful quantitative information on physiological and biochemical processes. However, the low signal-to-noise ratio (SNR) in short dynamic frames is a challenge. OBJECTIVE: To get high SNR in the dynamic PET and to achieve high-quality PET parametric image are the objective of this study. METHODS: Low-rank (LR) modeling and edge-preserving prior are incorporated in this study with a unified mathematical framework to improve the SNR of a dynamic PET image series. The proposed algorithm is designed to reduce noise in homogeneous areas while preserving the edges of regions of interest. RESULTS: The performance of the proposed method (LRH) is compared both visually and quantitatively by using the classic Gaussian filter and an LR expression filter on a digital brain phantom and in vivo rat study. Experimental results demonstrate that the proposed filter can achieve superior visual and quantitative performance without sacrificing spatial resolution. CONCLUSIONS: The proposed LRH is considerably effective and exhibits great potential in processing dynamic PET data with high noise levels.

Magnetic resonance fingerprinting (MRF) can be used to simultaneously obtain multiple parameter maps from a single pulse sequence. However, patient motion during MRF acquisition may result in blurring and artifacts in estimated parameter maps. In this work, a novel motion correction method was proposed to correct for rigid motion in MRF. The proposed method involved sliding-window reconstruction to obtain intermediate images followed by image registration to estimate rigid motion information between these images. Finally, the motion-corrupted k-space data were corrected with the estimated motion parameters and then reconstructed to obtain the parameter maps via the conventional MRF processing pipeline. The proposed method was evaluated using both simulations and in vivo MRF experiments with intently different types of motion. For motion-corrupted data, the proposed method yielded brain T1, T2 and proton density maps with obviously reduced blurring and artifacts and lower normalized root-mean-square error, compared to MRF without motion correction. In conclusion, motion-corrected MRF using the proposed method has the potential to produce accurate parameter maps in the presence of in-plane rigid motion.

Quantitative susceptibility mapping (QSM) is a magnetic resonance imaging technique that quantifies the magnetic susceptibility distribution within biological tissues. QSM calculates the underlying magnetic susceptibility by deconvolving the tissue magnetic field map with a unit dipole kernel. However, this deconvolution problem is ill-posed. The morphology enabled dipole inversion (MEDI) introduces total variation (TV) to regularize the susceptibility reconstruction. However, MEDI results still contain artifacts near tissue boundaries because MEDI only imposes TV constraint on voxels inside smooth regions. We introduce a Morphology-Adaptive TV (MATV) for improving TV-regularized QSM. The MATV method first classifies imaging target into smooth and nonsmooth regions by thresholding magnitude gradients. In the dipole inversion for QSM, the TV regularization weights are a monotonically decreasing function of magnitude gradients. Thus, voxels inside smooth regions are assigned with larger weights than those in nonsmooth regions. Using phantom and in vivo datasets, we compared the performance of MATV with that of MEDI. MATV results had better visual quality than MEDI results, especially near tissue boundaries. Preliminary brain imaging results illustrated that MATV has potential to improve the reconstruction of regions near tissue boundaries.

Image enhancement of lung four-dimensional computed tomography (4D-CT) data is highly important because image resolution remains a crucial point in lung cancer radiotherapy. In this paper, we proposed a method for lung 4D-CT super resolution (SR) by using an adaptive-patch-based projection onto convex sets (POCS) approach, which is in contrast with the global POCS SR algorithm, to recover fine details with lesser artifacts in images. The main contribution of this patch-based approach is that the interfering local structure from other phases can be rejected by employing a similar patch adaptive selection strategy. The effectiveness of our approach is demonstrated through experiments on simulated images and real lung 4D-CT datasets. A comparison with previously published SR reconstruction methods highlights the favorable characteristics of the proposed method.

We proposed a maximum a posterior (MAP) framework for incorporating information from co-registered anatomical images into PET image reconstruction through a novel anato-functional joint prior. The characteristic of the utilized hyperbolic potential function is determinate by the voxel intensity differences within the anatomical image, while the penalization is computed based on voxel intensity differences in reconstructed PET images. Using realistic simulated (18)FDG PET scan data, we optimized the performance of the proposed MAP reconstruction with the joint prior (JP-MAP) and compared its performance with conventional 3D MLEM and 3D MAP reconstructions. The proposed JP-MAP reconstruction algorithm resulted in quantitatively enhanced reconstructed images, as demonstrated in extensive FDG PET simulation study. The proposed method was also tested on a 20 min Florbetapir patient study performed on the high-resolution research tomograph. It was shown to outperform conventional methods in visual as well as quantitative accuracy assessment (in terms of regional noise versus activity value performance). The JP-MAP method was also compared with another MR-guided MAP reconstruction method, utilizing the Bowsher prior and was seen to result in some quantitative enhancements, especially in the case of MR-PET mis-registrations, and a definitive improvement in computational performance.

Liver R2* mapping is often degraded by the low signal-to-noise ratio (SNR) especially in the presence of severe iron. This study aims to improve liver R2* mapping at low SNRs by averaging decay curves before the process of curve-fitting. Independently filtering echo images by nonlocal means (NLM) demonstrated improved quality of R2* mapping, but may introduce new errors due to the nonlinear nature of the NLM filter, during which the averaging weights may vary with different image contents at multiple echo times. In addition, the image denoising effect of the NLM may decline when no sufficient similar patches are available. To overcome these drawbacks, we proposed to filter decay curves instead of images. In this novel scheme, decay curves were averaged in a local window, each with a weight assigned according to the curve-similarity measured by the distance between one of the neighboring curves and the targeted one. The proposed method was tested on simulated, phantom and patient data. The results demonstrate that the proposed method can provide more accurate R2* mapping compared with the NLM algorithm, and hence has the potential to improve diagnosis and therapy in patients with liver iron.

To improve liver R2* mapping by incorporating adaptive neighborhood regularization into pixel-wise curve fitting.Magnetic resonance imaging R2* mapping remains challenging because of the serial images with low signal-to-noise ratio. In this study, we proposed to exploit the neighboring pixels as regularization terms and adaptively determine the regularization parameters according to the interpixel signal similarity. The proposed algorithm, called the pixel-wise curve fitting with adaptive neighborhood regularization (PCANR), was compared with the conventional nonlinear least squares (NLS) and nonlocal means filter-based NLS algorithms on simulated, phantom, and in vivo data.Visually, the PCANR algorithm generates R2* maps with significantly reduced noise and well-preserved tiny structures. Quantitatively, the PCANR algorithm produces R2* maps with lower root mean square errors at varying R2* values and signal-to-noise-ratio levels compared with the NLS and nonlocal means filter-based NLS algorithms. For the high R2* values under low signal-to-noise-ratio levels, the PCANR algorithm outperforms the NLS and nonlocal means filter-based NLS algorithms in the accuracy and precision, in terms of mean and standard deviation of R2* measurements in selected region of interests, respectively.The PCANR algorithm can reduce the effect of noise on liver R2* mapping, and the improved measurement precision will benefit the assessment of hepatic iron in clinical practice. Magn Reson Med 80:792-801, 2018. © 2018 International Society for Magnetic Resonance in Medicine.

Reducing radiation dose in dual energy computed tomography (DECT) is highly desirable but it may lead to excessive noise in the filtered backprojection (FBP) reconstructed DECT images, which can inevitably increase the diagnostic uncertainty. To obtain clinically acceptable DECT images from low-mAs acquisitions, in this work we develop a novel scheme based on measurement of DECT data. In this scheme, inspired by the success of edge-preserving non-local means (NLM) filtering in CT imaging and the intrinsic characteristics underlying DECT images, i.e. global correlation and non-local similarity, an averaged image induced NLM-based (aviNLM) regularization is incorporated into the penalized weighted least-squares (PWLS) framework. Specifically, the presented NLM-based regularization is designed by averaging the acquired DECT images, which takes the image similarity within the two energies into consideration. In addition, the weighted least-squares term takes into account DECT data-dependent variance. For simplicity, the presented scheme was termed as 'PWLS-aviNLM'. The performance of the presented PWLS-aviNLM algorithm was validated and evaluated on digital phantom, physical phantom and patient data. The extensive experiments validated that the presented PWLS-aviNLM algorithm outperforms the FBP, PWLS-TV and PWLS-NLM algorithms quantitatively. More importantly, it delivers the best qualitative results with the finest details and the fewest noise-induced artifacts, due to the aviNLM regularization learned from DECT images. This study demonstrated the feasibility and efficacy of the presented PWLS-aviNLM algorithm to improve the DECT reconstruction and resulting material decomposition.

Background and objective: The absolute quantification of dynamic myocardial perfusion (MP) PET imaging is challenged by the limited spatial resolution of individual frame images due to division of the data into shorter frames. This study aims to develop a method for restoration and enhancement of dynamic PET images. Methods: We propose that the image restoration model should be based on multiple constraints rather than a single constraint, given the fact that the image characteristic is hardly described by a single constraint alone. At the same time, it may be possible, but not optimal, to regularize the image with multiple constraints simultaneously. Fortunately, MP PET images can be decomposed into a superposition of background vs. dynamic components via low-rank plus sparse (L + S) decomposition. Thus, we propose an L + S decomposition based MP PET image restoration model and express it as a convex optimization problem. An iterative soft thresholding algorithm was developed to solve the problem. Using realistic dynamic 82Rb MP PET scan data, we optimized and compared its performance with other restoration methods. Results: The proposed method resulted in substantial visual as well as quantitative accuracy improvements in terms of noise versus bias performance, as demonstrated in extensive 82Rb MP PET simulations. In particular, the myocardium defect in the MP PET images had improved visual as well as contrast versus noise tradeoff. The proposed algorithm was also applied on an 8-min clinical cardiac 82Rb MP PET study performed on the GE Discovery PET/CT, and demonstrated improved quantitative accuracy (CNR and SNR) compared to other algorithms. Conclusions: The proposed method is effective for restoration and enhancement of dynamic PET images.

Lung field segmentation in chest radiographs (CXRs) is an essential preprocessing step in automatically analyzing such images. We present a method for lung field segmentation that is built on a high-quality boundary map detected by an efficient modern boundary detector, namely a structured edge detector (SED). A SED is trained beforehand to detect lung boundaries in CXRs with manually outlined lung fields. Then, an ultrametric contour map (UCM) is transformed from the masked and marked boundary map. Finally, the contours with the highest confidence level in the UCM are extracted as lung contours. Our method is evaluated using the public Japanese Society of Radiological Technology database of scanned films. The average Jaccard index of our method is 95.2%, which is comparable with those of other state-of-the-art methods (95.4%). The computation time of our method is less than 0.1 s for a $256\,\times \,256$ CXR when executed on an ordinary laptop. Our method is also validated on CXRs acquired with different digital radiography units. The results demonstrate the generalization of the trained SED model and the usefulness of our method.

Continuous loop averaging deconvolution (CLAD) is one of the proven methods for recovering transient auditory evoked potentials (AEPs) in rapid stimulation paradigms, which requires an elaborated stimulus sequence design to attenuate impacts from noise in data. The present study aimed to develop a new metric in gauging a CLAD sequence in terms of noise gain factor (NGF), which has been proposed previously but with less effectiveness in the presence of pink (1/f) noise. We derived the new metric by explicitly introducing the 1/f model into the proposed time-continuous sequence. We selected several representative CLAD sequences to test their noise property on typical EEG recordings, as well as on five real CLAD electroencephalogram (EEG) recordings to retrieve the middle latency responses. We also demonstrated the merit of the new metric in generating and quantifying optimized sequences using a classic genetic algorithm. The new metric shows evident improvements in measuring actual noise gains at different frequencies, and better performance than the original NGF in various aspects. The new metric is a generalized NGF measurement that can better quantify the performance of a CLAD sequence, and provide a more efficient mean of generating CLAD sequences via the incorporation with optimization algorithms. The present study can facilitate the specific application of CLAD paradigm with desired sequences in the clinic.

International audience; In low dose computed tomography (LDCT) imaging, the data inconsistency of measured noisy projections can significantly deteriorate reconstruction images. To deal with this problem, we propose here a new sinogram restoration approach, the sinogram-discriminative feature representation (S-DFR) method. Different from other sinogram restoration methods, the proposed method works through a 3-D representation-based feature decomposition of the projected attenuation component and the noise component using a well-designed composite dictionary containing atoms with discriminative features. This method can be easily implemented with good robustness in parameter setting. Its comparison to other competing methods through experiments on simulated and real data demonstrated that the S-DFR method offers a sound alternative in LDCT.

Repeated x-ray computed tomography (CT) scans are often required in several specific applications such as perfusion imaging, image-guided biopsy needle, image-guided intervention, and radiotherapy with noticeable benefits. However, the associated cumulative radiation dose significantly increases as comparison with that used in the conventional CT scan, which has raised major concerns in patients. In this study, to realize radiation dose reduction by reducing the x-ray tube current and exposure time (mAs) in repeated CT scans, we propose a prior-image induced nonlocal (PINL) regularization for statistical iterative reconstruction via the penalized weighted least-squares (PWLS) criteria, which we refer to as “PWLS-PINL”. Specifically, the PINL regularization utilizes the redundant information in the prior image and the weighted least-squares term considers a data-dependent variance estimation, aiming to improve current low-dose image quality. Subsequently, a modified iterative successive over-relaxation algorithm is adopted to optimize the associative objective function. Experimental results on both phantom and patient data show that the present PWLS-PINL method can achieve promising gains over the other existing methods in terms of the noise reduction, low-contrast object detection and edge detail preservation.

Objectives To evaluate the performance of region-of-interest (ROI)-based MRI R2* measurements by using the first-moment noise-corrected model (M1NCM) to correct the non-central Chi noise in magnitude images from phased arrays for hepatic iron content (HIC) assessment. Methods R2* values were quantified using the M1NCM model. Three approaches were employed to determine the representative R2*: fitting of the ROI-averaged signal (average-then-fit, ATF); outputting the median and mean of R2*s from the pixel-wise fitting of decay signals within the ROI (denoted as PWFmed and PWFmea, respectively). The accuracy and precision of the three approaches were evaluated on synthesized data. The agreement among these approaches and their intra- and inter-observer reproducibility were assessed on 105 thalassaemia major patients. Results Simulations showed that ATF consistently yielded the highest accuracy and precision at varying noise levels. By contrast, PWFmed and PWFmea slightly and significantly overestimated high R2* at poor signal-to-noise ratios, respectively. Patient study showed that ATF agreed well with PWFmed, whereas PWFmea produced high R2* measurements for patients with severe HIC. No significant difference was observed in the reproducibility of the three approaches. Conclusions PWFmea tends to overestimate high R2*, whereas ATF and PWFmed can produce more accurate R2* measurements for HIC assessment.

Brain-tumor segmentation is an important clinical requirement for brain-tumor diagnosis and radiotherapy planning. It is well-known that the number of clusters is one of the most important parameters for automatic segmentation. However, it is difficult to define owing to the high diversity in appearance of tumor tissue among different patients and the ambiguous boundaries of lesions. In this study, a nonparametric mixture of Dirichlet process (MDP) model is applied to segment the tumor images, and the MDP segmentation can be performed without the initialization of the number of clusters. Because the classical MDP segmentation cannot be applied for real-time diagnosis, a new nonparametric segmentation algorithm combined with anisotropic diffusion and a Markov random field (MRF) smooth constraint is proposed in this study. Besides the segmentation of single modal brain-tumor images, we developed the algorithm to segment multimodal brain-tumor images by the magnetic resonance (MR) multimodal features and obtain the active tumor and edema in the same time. The proposed algorithm is evaluated using 32 multimodal MR glioma image sequences, and the segmentation results are compared with other approaches. The accuracy and computation time of our algorithm demonstrates very impressive performance and has a great potential for practical real-time clinical use.

Existing maximum a posteriori probability and Markov random field (MRF) models have limitations associated with: (1) the ordinary neighborhood system being unable to differentiate subtle changes due to several-to-one correspondence within the neighborhood; and (2) difficulty finding an appropriate parameter to balance between the spatial context and the data likelihood. Aiming at overcoming the limitations and applications to segmentation of cerebral vessels from magnetic resonance angiography images, we have proposed (1) a multi-pattern neighborhood system and corresponding energy equation to enable the MRF model for segmenting fine cerebral vessels with complicated context; and (2) an iterative approximation algorithm based on the maximum pseudo-likelihood and the space coding mode for the automatic parameter estimation of high level model of MRF. In the implementation, two computational strategies have been employed to speed up: the candidate space of cerebral vessels based on a threshold of the response to multi-scale filtering, and parallel computation of major equations. Three phantoms simulating segmentation challenges of vessels have been devised to quantitatively validate the algorithm. In addition, 10 three-dimensional clinical data sets have been used to validate the algorithm qualitatively. It has been shown that the proposed method could yield smaller error, improve the spatial resolution of MRF model, and better balance the smoothing and data likelihood than the traditional trial-and-error estimation. Comparative studies have shown that the proposed method is better than the 3 segmentation algorithms ( Hassouna et al., 2006; Hao et al., 2008; Gao et al., 2011 ) in terms of segmentation accuracy, robustness to noise and varying curvatures as well as radii.

Brain tumor segmentation is a clinical requirement for brain tumor diagnosis and radiotherapy planning. Automating this process is a challenging task due to the high diversity in appearance of tumor tissue among different patients and the ambiguous boundaries of lesions. In this paper, we propose a method to construct a graph by learning the population- and patient-specific feature sets of multimodal magnetic resonance (MR) images and by utilizing the graph-cut to achieve a final segmentation. The probabilities of each pixel that belongs to the foreground (tumor) and the background are estimated by global and custom classifiers that are trained through learning population- and patient-specific feature sets, respectively. The proposed method is evaluated using 23 glioma image sequences, and the segmentation results are compared with other approaches. The encouraging evaluation results obtained, i.e., DSC (84.5%), Jaccard (74.1%), sensitivity (87.2%), and specificity (83.1%), show that the proposed method can effectively make use of both population- and patient-specific information.

In this paper, we propose an improved Chan-Vese (CV) model that uses Kullback-Leibler (KL) distances and local neighborhood information (LNI). Due to the effects of heterogeneity and complex constructions, the performance of level set segmentation is subject to confounding by the presence of nearby structures of similar intensity, preventing it from discerning the exact boundary of the object. Moreover, the CV model cannot usually obtain accurate results in medical image segmentation in cases of optimal configuration of controlling parameters, which requires substantial manual intervention. To overcome the above deficiency, we improve the segmentation accuracy by the usage of KL distance and LNI, thereby introducing the image local characteristics. Performance evaluation of the present method was achieved through experiments on the synthetic images and a series of real medical images. The extensive experimental results showed the superior performance of the proposed method over the state-of-the-art methods, in terms of both robustness and efficiency.

Efficient segmentation of tumors in medical images is of great practical importance in early diagnosis and radiation plan. This paper proposes a novel semi-automatic segmentation method based on population and individual statistical information to segment brain tumors in magnetic resonance (MR) images. First, high-dimensional image features are extracted. Neighborhood components analysis is proposed to learn two optimal distance metrics, which contain population and patient-specific information, respectively. The probability of each pixel belonging to the foreground (tumor) and the background is estimated by the k-nearest neighborhood classifier under the learned optimal distance metrics. A cost function for segmentation is constructed through these probabilities and is optimized using graph cuts. Finally, some morphological operations are performed to improve the achieved segmentation results. Our dataset consists of 137 brain MR images, including 68 for training and 69 for testing. The proposed method overcomes segmentation difficulties caused by the uneven gray level distribution of the tumors and even can get satisfactory results if the tumors have fuzzy edges. Experimental results demonstrate that the proposed method is robust to brain tumor segmentation.

The advantages of open, vertical-field, magnetic resonance-guided, focused ultrasound surgery (MRgFUS) are attractive. The inverse technique using the bi-boundary conditions is proposed to design a uterine-oriented intraoperative RF coil with an ultrasound aperture for the MRgFUS system. In the current proposed scheme, the desired magnetic field of the RF coil was set to completely overlap the target organ. The current density distribution on the RF coil surface, accounting for the expected magnetic field, was solved using the inverse technique. The stream function was available through the ‘discretization’ of the current density distribution on the RF coil surface. The coil windings were obtained from the contour plot of the stream function. As a modification of previous designs, the bi-boundary conditions are proposed in the inverse technique for the existence of the ultrasound aperture. Based on the obtained coil windings, a prototype coil was constructed. MR imaging of the phantom and the human body was performed to show the efficacy of the prototype coil. The results of temperature measurement using the prototype coil in a 0.4-T MR system were satisfactory. The performance of the prototype coil improved compared with the previously reported design.

Dynamic myocardial perfusion computed tomography (MPCT) is a promising technique for quick diagnosis and risk stratification of coronary artery disease. However, one major drawback of dynamic MPCT imaging is the heavy radiation dose to patients due to its dynamic images acquisition protocol. In this work, to address this issue, we present a robust dynamic MPCT deconvolution algorithm via adaptive-weighted tensor total variation (AwTTV) regularization for accurate residue function estimation with low-mAs data acquisitions. For simplicity, the presented method is termed as “MPD-AwTTV”. More specifically, the gains of the AwTTV regularization are from the anisotropic edge property of the sequential MPCT images over the original tensor total variation regularization. To minimize the associative objective function we propose an efficient iterative optimization strategy with fast convergence rate under the framework of iterative shrinkage/thresholding algorithm. We validate and evaluate the presented algorithm using both digital XCAT phantom and preclinical porcine data. The preliminary experimental results have demonstrated that the presented MPD-AwTTV deconvolution algorithm can achieve remarkable gains in noise-induced artifacts suppression, edge details preservation and accurate flow-scaled residue function and MPHM estimation as compared with the other existing deconvolution algorithms in the digital phantom studies, and the similar gains can be obtained in the porcine data experiment.

To develop and evaluate a novel 2D phase-unwrapping method that works robustly in the presence of severe noise, rapid phase changes, and disconnected regions.The MR phase map usually varies rapidly in regions adjacent to wraps. In contrast, the phasors can vary slowly, especially in regions distant from tissue boundaries. Based on this observation, this paper develops a phase-unwrapping method by using a pixel clustering and local surface fitting (CLOSE) approach to exploit different local variation characteristics between the phase and phasor data. The CLOSE approach classifies pixels into easy-to-unwrap blocks and difficult-to-unwrap residual pixels first, and then sequentially performs intrablock, interblock, and residual-pixel phase unwrapping by a region-growing surface-fitting method. The CLOSE method was evaluated on simulation and in vivo water-fat Dixon data, and was compared with phase region expanding labeler for unwrapping discrete estimates (PRELUDE).In the simulation experiment, the mean error ratio by CLOSE was less than 1.50%, even in areas with signal-to-noise ratio equal to 0.5, phase changes larger than π, and disconnected regions. For 350 in vivo knee and ankle images, the water-fat swap ratio of CLOSE was 4.29%, whereas that of PRELUDE was 25.71%.The CLOSE approach can correctly unwrap phase with high robustness, and benefit MRI applications that require phase unwrapping. Magn Reson Med 79:515-528, 2018. © 2017 International Society for Magnetic Resonance in Medicine.

Content-based image retrieval (CBIR) techniques have currently gained increasing popularity in the medical field because they can use numerous and valuable archived images to support clinical decisions. In this paper, we concentrate on developing a CBIR system for retrieving brain tumors in T1-weighted contrast-enhanced MRI images. Specifically, when the user roughly outlines the tumor region of a query image, brain tumor images in the database of the same pathological type are expected to be returned. We propose a novel feature extraction framework to improve the retrieval performance. The proposed framework consists of three steps. First, we augment the tumor region and use the augmented tumor region as the region of interest to incorporate informative contextual information. Second, the augmented tumor region is split into subregions by an adaptive spatial division method based on intensity orders; within each subregion, we extract raw image patches as local features. Third, we apply the Fisher kernel framework to aggregate the local features of each subregion into a respective single vector representation and concatenate these per-subregion vector representations to obtain an image-level signature. After feature extraction, a closed-form metric learning algorithm is applied to measure the similarity between the query image and database images. Extensive experiments are conducted on a large dataset of 3604 images with three types of brain tumors, namely, meningiomas, gliomas, and pituitary tumors. The mean average precision can reach 94.68%. Experimental results demonstrate the power of the proposed algorithm against some related state-of-the-art methods on the same dataset.

Cerebral perfusion computed tomography (PCT) imaging as an accurate and fast acute ischemic stroke examination has been widely used in clinic. Meanwhile, a major drawback of PCT imaging is the high radiation dose due to its dynamic scan protocol. The purpose of this work is to develop a robust perfusion deconvolution approach via structure tensor total variation (STV) regularization (PD-STV) for estimating an accurate residue function in PCT imaging with the low-milliampere-seconds (low-mAs) data acquisition.Besides modeling the spatio-temporal structure information of PCT data, the STV regularization of the present PD-STV approach can utilize the higher order derivatives of the residue function to enhance denoising performance. To minimize the objective function, the authors propose an effective iterative algorithm with a shrinkage/thresholding scheme. A simulation study on a digital brain perfusion phantom and a clinical study on an old infarction patient were conducted to validate and evaluate the performance of the present PD-STV approach.In the digital phantom study, visual inspection and quantitative metrics (i.e., the normalized mean square error, the peak signal-to-noise ratio, and the universal quality index) assessments demonstrated that the PD-STV approach outperformed other existing approaches in terms of the performance of noise-induced artifacts reduction and accurate perfusion hemodynamic maps (PHM) estimation. In the patient data study, the present PD-STV approach could yield accurate PHM estimation with several noticeable gains over other existing approaches in terms of visual inspection and correlation analysis.This study demonstrated the feasibility and efficacy of the present PD-STV approach in utilizing STV regularization to improve the accuracy of residue function estimation of cerebral PCT imaging in the case of low-mAs.

This paper is aimed at developing and evaluating a content-based retrieval method for contrast-enhanced liver computed tomographic (CT) images using bag-of-visual-words (BoW) representations of single and multiple phases. The BoW histograms are extracted using the raw intensity as local patch descriptor for each enhance phase by densely sampling the image patches within the liver lesion regions. The distance metric learning algorithms are employed to obtain the semantic similarity on the Hellinger kernel feature map of the BoW histograms. The different visual vocabularies for BoW and learned distance metrics are evaluated in a contrast-enhanced CT image dataset comprised of 189 patients with three types of focal liver lesions, including 87 hepatomas, 62 cysts, and 60 hemangiomas. For each single enhance phase, the mean of average precision (mAP) of BoW representations for retrieval can reach above 90 % which is significantly higher than that of intensity histogram and Gabor filters. Furthermore, the combined BoW representations of the three enhance phases can improve mAP to 94.5 %. These preliminary results demonstrate that the BoW representation is effective and feasible for retrieval of liver lesions in contrast-enhanced CT images.

The most critical step in grayscale medical image retrieval systems is feature extraction. Understanding the interrelatedness between the characteristics of lesion images and corresponding imaging features is crucial for image training, as well as for features extraction. A feature-extraction algorithm is developed based on different imaging properties of lesions and on the discrepancy in density between the lesions and their surrounding normal liver tissues in triple-phase contrast-enhanced computed tomographic (CT) scans. The algorithm includes mainly two processes: (1) distance transformation, which is used to divide the lesion into distinct regions and represents the spatial structure distribution and (2) representation using bag of visual words (BoW) based on regions. The evaluation of this system based on the proposed feature extraction algorithm shows excellent retrieval results for three types of liver lesions visible on triple-phase scans CT images. The results of the proposed feature extraction algorithm show that although single-phase scans achieve the average precision of 81.9%, 80.8%, and 70.2%, dual- and triple-phase scans achieve 86.3% and 88.0%.