الملخص
Objective To evaluate the clinical practical value of the golden angle radial sparse parallel(GRASP)technology in the MR imaging quality of lung cancer under free-breathing state.Methods The imaging data of 30 lung cancer patients diagnosed with CT screening were collected by using a large-aperture 3.0T MR scanner.All patients underwent routine Cartesian breath-hold volume interpolation(BH-VIBE)scanning,then free-breathing dynamic contrast-enhanced magnetic resonance imaging(DCE-MRI)scanning based on GRASP technology,and another repetitive BH-VIBE scanning.The MR imaging quality was independently evaluated by two experienced thoracic radiologists including overall image quality,lesion outline,artifact grade and diagnostic confidence,mean-while,the CT images of the patient at the same time were used as a reference.The sequence information on MR images was also pro-cessed blindly.Results The GRASP sequence could effectively eliminate the interference of motion artifacts such as respiration and cardiac large vessel beats,and the image quality,lesion outline,artifact grade,and diagnostic confidence of the GRASP sequence were significantly better than the BH-VIBE(P<0.01).The image quality of the GRASP sequence was more satisfactory with clea-rer tumor boundary and more details.Conclusion Free-breathing high-temporal-spatial resolution GRASP technology has better image quality than traditional BH-VIBE scanning,and it is a reliable method for high-resolution imaging of lung cancer.
الملخص
Clinical applications of cone-beam breast CT(CBBCT) are hindered by relatively higher radiation dose and longer scan time. This study proposes sparse-view CBBCT, i.e. with a small number of projections, to overcome the above bottlenecks. A deep learning method - conditional generative adversarial network constrained by image edges (ECGAN) - is proposed to suppress artifacts on sparse-view CBBCT images reconstructed by filtered backprojection (FBP). The discriminator of the ECGAN is the combination of patchGAN and LSGAN for preserving high frequency information, with a modified U-net as the generator. To further preserve subtle structures and micro calcifications which are particularly important for breast cancer screening and diagnosis, edge images of CBBCT are added to both the generator and the discriminator to guide the learning. The proposed algorithm has been evaluated on 20 clinical raw datasets of CBBCT. ECGAN substantially improves the image qualities of sparse-view CBBCT, with a performance superior to those of total variation (TV) based iterative reconstruction and FBPConvNet based post-processing. On one CBBCT case with the projection number reduced from 300 to 100, ECGAN enhances peak-signal-to-noise ratio (PSNR) and structural similarity (SSIM) on FBP reconstruction from 24.26 and 0.812 to 37.78 and 0.963, respectively. These results indicate that ECGAN successfully reduces radiation dose and scan time of CBBCT by 1/3 with only small image degradations.
الموضوعات
Humans , Algorithms , Breast , Cone-Beam Computed Tomography , Image Processing, Computer-Assisted , Phantoms, Imaging , Tomography, X-Ray Computedالملخص
Motor imagery electroencephalogram (EEG) signals are non-stationary time series with a low signal-to-noise ratio. Therefore, the single-channel EEG analysis method is difficult to effectively describe the interaction characteristics between multi-channel signals. This paper proposed a deep learning network model based on the multi-channel attention mechanism. First, we performed time-frequency sparse decomposition on the pre-processed data, which enhanced the difference of time-frequency characteristics of EEG signals. Then we used the attention module to map the data in time and space so that the model could make full use of the data characteristics of different channels of EEG signals. Finally, the improved time-convolution network (TCN) was used for feature fusion and classification. The BCI competition IV-2a data set was used to verify the proposed algorithm. The experimental results showed that the proposed algorithm could effectively improve the classification accuracy of motor imagination EEG signals, which achieved an average accuracy of 83.03% for 9 subjects. Compared with the existing methods, the classification accuracy of EEG signals was improved. With the enhanced difference features between different motor imagery EEG data, the proposed method is important for the study of improving classifier performance.
الموضوعات
Humans , Algorithms , Brain-Computer Interfaces , Electroencephalography/methods , Imagery, Psychotherapy , Imaginationالملخص
Speech feature learning is the core and key of speech recognition method for mental illness. Deep feature learning can automatically extract speech features, but it is limited by the problem of small samples. Traditional feature extraction (original features) can avoid the impact of small samples, but it relies heavily on experience and is poorly adaptive. To solve this problem, this paper proposes a deep embedded hybrid feature sparse stack autoencoder manifold ensemble algorithm. Firstly, based on the prior knowledge, the psychotic speech features are extracted, and the original features are constructed. Secondly, the original features are embedded in the sparse stack autoencoder (deep network), and the output of the hidden layer is filtered to enhance the complementarity between the deep features and the original features. Third, the L1 regularization feature selection mechanism is designed to compress the dimensions of the mixed feature set composed of deep features and original features. Finally, a weighted local preserving projection algorithm and an ensemble learning mechanism are designed, and a manifold projection classifier ensemble model is constructed, which further improves the classification stability of feature fusion under small samples. In addition, this paper designs a medium-to-large-scale psychotic speech collection program for the first time, collects and constructs a large-scale Chinese psychotic speech database for the verification of psychotic speech recognition algorithms. The experimental results show that the main innovation of the algorithm is effective, and the classification accuracy is better than other representative algorithms, and the maximum improvement is 3.3%. In conclusion, this paper proposes a new method of psychotic speech recognition based on embedded mixed sparse stack autoencoder and manifold ensemble, which effectively improves the recognition rate of psychotic speech.
الموضوعات
Humans , Algorithms , Databases, Factual , Psychotic Disorders , Speech , Speech Perceptionالملخص
The purpose of this article was to introduce the goodness of fit test and its SAS implementation. The main contents included the following four aspects: ① Pearson΄s goodness of fit test; ② deviance or likelihood ratio goodness of fit test; ③ Hosmer-Lemeshow goodness of fit test; ④ goodness of fit test for the sparse data. In the aforementioned “fourth aspect”, there were six specific test approaches, namely “information matrix test” “information matrix diagonal test” “Osius-Rojek test” “unweighted residual sum of squares test” “Spiegelhalter test” and “Stukel test”. The paper implemented the four types of the goodness of fit tests mentioned above with the help of the SAS software through an example, explained the output results, and made statistical and professional conclusions.
الملخص
In order to solve the problem that the early onset of paroxysmal atrial fibrillation is very short and difficult to detect, a detection algorithm based on sparse coding of Riemannian manifolds is proposed. The proposed method takes into account that the nonlinear manifold geometry is closer to the real feature space structure, and the computational covariance matrix is used to characterize the heart rate variability (RR interval variation), so that the data is in the Riemannian manifold space. Sparse coding is applied to the manifold, and each covariance matrix is represented as a sparse linear combination of Riemann dictionary atoms. The sparse reconstruction loss is defined by the affine invariant Riemannian metric, and the Riemann dictionary is learned by iterative method. Compared with the existing methods, this method used shorter heart rate variability signal, the calculation was simple and had no dependence on the parameters, and the better prediction accuracy was obtained. The final classification on MIT-BIH AF database resulted in a sensitivity of 99.34%, a specificity of 95.41% and an accuracy of 97.45%. At the same time, a specificity of 95.18% was realized in MIT-BIH NSR database. The high precision paroxysmal atrial fibrillation detection algorithm proposed in this paper has a potential application prospect in the long-term monitoring of wearable devices.
الموضوعات
Humans , Algorithms , Atrial Fibrillation , Databases, Factual , Electrocardiography , Wearable Electronic Devicesالملخص
Anesthesia consciousness monitoring is an important issue in basic neuroscience and clinical applications, which has received extensive attention. In this study, in order to find the indicators for monitoring the state of clinical anesthesia, a total of 14 patients undergoing general anesthesia were collected for 5 minutes resting electroencephalogram data under three states of consciousness (awake, moderate and deep anesthesia). Sparse partial least squares (SPLS) and traditional synchronized likelihood (SL) are used to calculate brain functional connectivity, and the three conscious states before and after anesthesia were distinguished by the connection features. The results show that through the whole brain network analysis, SPLS and traditional SL method have the same trend of network parameters in different states of consciousness, and the results obtained by SPLS method are statistically significant ( <0.05). The connection features obtained by the SPLS method are classified by the support vector machine, and the classification accuracy is 87.93%, which is 7.69% higher than that of the connection feature classification obtained by SL method. The results of this study show that the functional connectivity based on the SPLS method has better performance in distinguishing three kinds of consciousness states, and may provides a new idea for clinical anesthesia monitoring.
الملخص
Objective@#To explore the characteristics of the default memory network (DMN) and working memory network (WMN) at resting state brain functional network of exercise addiction people.@*Methods@#Twenty-nine sports addicts and 26 non-sports addicts matched by sex, age, average education level and sports dependence were screened by the exercise addiction index (EAI). Resting status brain scanning was performed with 3.0T magnetic resonance scanner.Sparse approximation coefficients independent component analysis (SACICA) model was used to analyze the independent components of brain networks.@*Results@#Compared with the DMN template, four features were extracted, including " basic conformity" , " less frontal lobe" , " more frontal lobe" and " less occipitoparietal lobe" . Compared with the parameters of " basic conformity" , the proportion of exercise addiction group (33.3%, 9/27) was higher than that of control group (18.2%, 4/22). In the other three parameters, the proportion of exercise addiction group (37.0%, 10/27; 3.7%, 1/27; 22.2%, 6/27) was lower than those of control group (45.5%, 10/22; 22.7%, 5/22; 27.3%, 6/22). But Chi-square test showed that there was no significant difference between the two groups(all P>0.05). Compared with the WMN template, six features were extracted, including " basic conformity" , " more frontal and parietal lobes" , " more parietal lobes" , " more frontal lobes" , " less frontal lobes" and " less parietal lobes" . The percentages of the first three features in exercise addiction group (22.2%, 6/27; 7.4%, 2/27; 7.4%, 2/27) were less than those in the control group (45.5%, 10/22; 22.7%, 5/22; 9.1%, 2/22), while the percentages of the last three features in the exercise addiction group (7.4%, 2/27; 37.0%, 10/27; 14.8%, 4/27) were higher than those in the control group (4.5%, 1/22; 13.6%, 3/22; 0, 0). Chi-square test showed that there was no significant difference in all features between the two groups was statistically(P>0.05).@*Conclusion@#No significant characteristic changes are found in DMN and WMN networks of exercise addiction population.
الملخص
Objective: To explore the correlation between imaging data and genetic data of schizophrenia patients using imaging genetics method. Methods A group sparse canonical analysis method was proposed, group sparse constraints λ1||u||G and λ2||v||G were added to sparse canonical correlation analysis model to select features groups. Then, features within one group were selected by sparse constraints τ1||u||1 and τ2||v||1. The imaging genetics method based on group sparse canonical correlation analysis method was used to analyze the correlation between brain regions and genes of schizophrenia, and the stability and ability of this method to select biomarkers were also verified. Results Several pairs canonical brain regions and genes were identified. The left insula and gene AKT1 demonstrated the most significant correlation (r=0.653 8), and r value between right rectus and gene DAOA, MAGI2 were larger than 0.6. The correlation coefficients of selected features were 0.626 9±0.016 1 with group sparse canonical correlation analysis and 0.625 5±0.018 1 with sparse canonical correlation analysis. After 10 selections, the proportion of 75 genes related to schizophrenia was higher than that of non-related genes randomly selected in the most related 20 genes selected by group sparse canonical correlation analysis. Conclusion: Several pairs canonical brain regions and genes can be identified by the group sparse canonical analysis method, which may provide a new way for the study of schizophrenia and other complex mental disorders.
الملخص
This paper aims to realize the decoding of single trial motor imagery electroencephalogram (EEG) signal by extracting and classifying the optimized features of EEG signal. In the classification and recognition of multi-channel EEG signals, there is often a lack of effective feature selection strategies in the selection of the data of each channel and the dimension of spatial filters. In view of this problem, a method combining sparse idea and greedy search (GS) was proposed to improve the feature extraction of common spatial pattern (CSP). The improved common spatial pattern could effectively overcome the problem of repeated selection of feature patterns in the feature vector space extracted by the traditional method, and make the extracted features have more obvious characteristic differences. Then the extracted features were classified by Fisher linear discriminant analysis (FLDA). The experimental results showed that the classification accuracy obtained by proposed method was 19% higher on average than that of traditional common spatial pattern. And high classification accuracy could be obtained by selecting feature set with small size. The research results obtained in the feature extraction of EEG signals lay the foundation for the realization of motor imagery EEG decoding.
الموضوعات
Algorithms , Brain-Computer Interfaces , Discriminant Analysis , Electroencephalography , Imagination , Signal Processing, Computer-Assistedالملخص
Sparse labeling of neurons contributes to uncovering their morphology, and rapid expression of a fluorescent protein reduces the experiment range. To achieve the goal of rapid and sparse labeling of neurons in vivo, we established a rapid method for depicting the fine structure of neurons at 24 h post-infection based on a mutant virus-like particle of Semliki Forest virus. Approximately 0.014 fluorescent focus-forming units of the mutant virus-like particle transferred enhanced green fluorescent protein into neurons in vivo, and its affinity for neurons in vivo was stronger than for neurons in vitro and BHK21 (baby hamster kidney) cells. Collectively, the mutant virus-like particle provides a robust and convenient way to reveal the fine structure of neurons and is expected to be a helper virus for combining with other tools to determine their connectivity. Our work adds a new tool to the approaches for rapid and sparse labeling of neurons in vivo.
الموضوعات
Animals , Male , Cells, Cultured , Gene Expression , Genetic Vectors , Genetics , Metabolism , Green Fluorescent Proteins , Genetics , Metabolism , Immunohistochemistry , Methods , Mice, Inbred C57BL , Microscopy, Fluorescence , Methods , Neurons , Cell Biology , Metabolism , Purkinje Cells , Cell Biology , Metabolism , Semliki forest virus , Geneticsالملخص
In order to provide a theoretical basis for better understanding the function and properties of proteins, we proposed a simple and effective feature extraction method for protein sequences to determine the subcellular localization of proteins. First, we introduced sparse coding combined with the information of amino acid composition to extract the feature values of protein sequences. Then the multilayer pooling integration was performed according to different sizes of dictionaries. Finally, the extracted feature values were sent into the support vector machine to test the effectiveness of our model. The success rates in data set ZD98, CH317 and Gram1253 were 95.9%, 93.4% and 94.7%, respectively as verified by the Jackknife test. Experiments showed that our method based on multilayer sparse coding can remarkably improve the accuracy of the prediction of protein subcellular localization.
الموضوعات
Algorithms , Amino Acid Sequence , Computational Biology , Protein Transport , Proteins , Subcellular Fractions , Support Vector Machineالملخص
OBJECTIVE@#We propose a sparse-view helical CT iterative reconstruction algorithm based on projection of convex set tensor total generalized variation minimization (TTGV-POCS) to reduce the X-ray dose of helical CT scanning.@*METHODS@#The three-dimensional volume data of helical CT reconstruction was viewed as the third-order tensor. The tensor generalized total variation (TTGV) was used to describe the structural sparsity of the three-dimensional image. The POCS iterative reconstruction framework was adopted to achieve a robust result of sparse-view helical CT reconstruction. The TTGV-POCS algorithm fully used the structural sparsity of first-order and second-order derivation and the correlation between the slices of helical CT image data to effectively suppress artifacts and noise in the image of sparse-view reconstruction and better preserve image edge information.@*RESULTS@#The experimental results of XCAT phantom and patient scan data showed that the TTGVPOCS algorithm had better performance in reducing noise, removing artifacts and maintaining edges than the existing reconstruction algorithms. Comparison of the sparse-view reconstruction results of XCAT phantom data with 144 exposure views showed that the TTGV-POCS algorithm proposed herein increased the PSNR quantitative index by 9.17%-15.24% compared with the experimental comparison algorithm; the FSIM quantitative index was increased by 1.27%-9.30%.@*CONCLUSIONS@#The TTGV-POCS algorithm can effectively improve the image quality of helical CT sparse-view reconstruction and reduce the radiation dose of helical CT examination to improve the clinical imaging diagnosis.
الملخص
OBJECTIVE: To compare the image quality of three-dimensional time-of-flight (TOF) magnetic resonance angiography (MRA) with sparse undersampling and iterative reconstruction (sparse TOF) with that of conventional TOF MRA. MATERIALS AND METHODS: This study included 56 patients who had undergone sparse TOF MRA for intracranial artery evaluation on a 3T MR scanner. Conventional TOF MRA scans were also acquired from 29 patients with matched acquisition times and another 27 patients with matched scanning parameters. The image quality was scored using a five-point scale based on the delineation of arterial vessel segments, artifacts, overall vessel visualization, and overall image quality by two radiologists independently, and the data were analyzed using the non-parametric Wilcoxon signed-rank test. Contrast ratios (CRs) of vessels were compared using the paired t test. Interobserver agreement was calculated using the kappa test. RESULTS: Compared with conventional TOF at the same spatial resolution, sparse TOF with an acceleration factor of 3.5 could reduce acquisition time by 40% and showed comparable image quality. In addition, when compared with conventional TOF with the same acquisition time, sparse TOF with an acceleration factor of 5 could also achieve higher spatial resolution, better delineation of vessel segments, fewer artifacts, higher image quality, and a higher CR (p < 0.05). Good-to-excellent interobserver agreement (κ: 0.65–1.00) was obtained between the two radiologists. CONCLUSION: Compared with conventional TOF, sparse TOF can achieve equivalent image quality in a reduced duration. Furthermore, using the same acquisition time, sparse TOF could improve the delineation of vessels and decrease image artifacts.
الموضوعات
Humans , Acceleration , Arteries , Artifacts , Magnetic Resonance Angiographyالملخص
OBJECTIVE: To compare a high acceleration three-dimensional (3D) T1-weighted gradient-recalled-echo (GRE) sequence using the combined compressed sensing (CS)-sensitivity encoding (SENSE) method with a conventional 3D GRE sequence using SENSE, with respect to image quality and detectability of solid focal liver lesions (FLLs) in the hepatobiliary phase (HBP) of gadoxetic acid-enhanced liver MRI. MATERIALS AND METHODS: A total of 217 patients with gadoxetic acid-enhanced liver MRI at 3T (54 in the preliminary study and 163 in the main study) were retrospectively included. In the main study, HBP imaging was done twice using the standard mDixon-3D-GRE technique with SENSE (acceleration factor [AF]: 2.8, standard mDixon-GRE) and the high acceleration mDixon-3D GRE technique using the combined CS-SENSE technique (CS-SENSE mDixon-GRE). Two abdominal radiologists assessed the two MRI data sets for image quality in consensus. Three other abdominal radiologists independently assessed the diagnostic performance of each data set and its ability to detect solid FLLs in 117 patients with 193 solid nodules and compared them using jackknife alternative free-response receiver operating characteristics (JAFROC). RESULTS: There was no significant difference in the overall image quality. CS-SENSE mDixon-GRE showed higher image noise, but lesser motion artifact levels compared with the standard mDixon-GRE (all p < 0.05). In terms of lesion detection, reader-averaged figures-of-merit estimated with JAFROC was 0.918 for standard mDixon-GRE, and 0.953 for CS-SENSE mDixon-GRE (p = 0.142). The non-inferiority of CS-SENSE mDixon-GRE over standard mDixon-GRE was confirmed (difference: 0.064 [−0.012, 0.081]). CONCLUSION: The CS-SENSE mDixon-GRE HBP sequence provided comparable overall image quality and non-inferior solid FFL detectability compared with the standard mDixon-GRE sequence, with reduced acquisition time.
الموضوعات
Humans , Acceleration , Artifacts , Consensus , Dataset , Liver , Magnetic Resonance Imaging , Methods , Noise , Retrospective Studies , ROC Curveالملخص
Magnetic resonance imaging (MRI) plays an important role in abdominal imaging. The high contrast resolution offered by MRI provides better lesion detection and its capacity to provide multiparametric images facilitates lesion characterization more effectively than computed tomography. However, the relatively long acquisition time of MRI often detrimentally affects the image quality and limits its accessibility. Recent developments have addressed these drawbacks. Specifically, multiphasic acquisition of contrast-enhanced MRI, free-breathing dynamic MRI using compressed sensing technique, simultaneous multi-slice acquisition for diffusion-weighted imaging, and breath-hold three-dimensional magnetic resonance cholangiopancreatography are recent notable advances in this field. This review explores the aforementioned state-of-the-art techniques by focusing on their clinical applications and potential benefits, as well as their likely future direction.
الموضوعات
Cholangiopancreatography, Magnetic Resonance , Hand Strength , Magnetic Resonance Imagingالملخص
Combining classical pharmacokinetic principles with statistical models, population pharmacokinetics (popPK) can effectively utilize sparse data for pharmacokinetic analysis. An optimally designed population pharmacokinetic study will balance the efficiency of a popPK study and the precision with which the parameters are estimated to ensure the unbiased estimation of pharmacokinetic parameters and facilitate the development of clinical and non-clinical trials. Sparse sampling methods have been developed for designing population pharmacokinetic experiments including random sampling method, limited sampling strategy, maximum a posteriori Bayesian method, Fisher information matrix method, and informative block randomized design, which have been widely applied in the uni-response and multi-response popPK sampling optimization. In recent years, population pharmacokinetics has been developed rapidly in Chinese materia medica (CMM), but few studies have been conducted to optimize sampling. By comparing the advantages and disadvantages of each sparse point sampling optimization method and the applicable conditions, this work provides a comparative review of optimal design methodologies and gives its application examples, which provides a reference for pharmacokinetic sampling optimization of CMM.
الملخص
It is of great clinical significance in the differential diagnosis of primary central nervous system lymphoma (PCNSL) and glioblastoma (GBM) because there are enormous differences between them in terms of therapeutic regimens. In this paper, we propose a system based on sparse representation for automatic classification of PCNSL and GBM. The proposed system distinguishes the two tumors by using of the different texture detail information of the two tumors on T1 contrast magnetic resonance imaging (MRI) images. First, inspired by the process of radiomics, we designed a dictionary learning and sparse representation-based method to extract texture information, and with this approach, the tumors with different volume and shape were transformed into 968 quantitative texture features. Next, aiming at the problem of the redundancy in the extracted features, feature selection based on iterative sparse representation was set up to select some key texture features with high stability and discrimination. Finally, the selected key features are used for differentiation based on sparse representation classification (SRC) method. By using ten-fold cross-validation method, the differentiation based on the proposed approach presents accuracy of 96.36%, sensitivity 96.30%, and specificity 96.43%. Experimental results show that our approach not only effectively distinguish the two tumors but also has strong robustness in practical application since it avoids the process of parameter extraction on advanced MRI images.
الملخص
The medical magnetic resonance (MR) image reconstruction is one of the key technologies in the field of magnetic resonance imaging (MRI). The compressed sensing (CS) theory indicates that the image can be reconstructed accurately from highly undersampled measurements by using the sparsity of the MR image. However, how to improve the image reconstruction quality by employing more sparse priors of the image becomes a crucial issue for MRI. In this paper, an adaptive image reconstruction model fusing the double dictionary learning is proposed by exploiting sparse priors of the MR image in the image domain and transform domain. The double sparse model which combines synthesis sparse model with sparse transform model is applied to the CS MR image reconstruction according to the complementarity of synthesis sparse and sparse transform model. Making full use of the two sparse priors of the image under the synthesis dictionary and transform dictionary learning, the proposed model is tackled in stages by the iterative alternating minimization algorithm. The solution procedure needs to utilize the synthesis and transform K-singular value decomposition (K-SVD) algorithms. Compared with the existing MRI models, the experimental results show that the proposed model can more efficiently improve the quality of the image reconstruction, and has faster convergence speed and better robustness to noise.
الملخص
This paper explores the relationship between the cardiac volume and time, which is applied to control dynamic heart phantom. We selected 50 patients to collect their cardiac computed tomography angiography (CTA) images, which have 20 points in time series CTA images using retrospective electrocardiograph gating, and measure the volume of four chamber in 20-time points with cardiac function analysis software. Then we grouped patients by gender, age, weight, height, heartbeat, and utilize repeated measurement design to conduct statistical analyses. We proposed structured sparse learning to estimate the mathematic expression of cardiac volume variation. The research indicates that all patients' groups are statistically significant in time factor ( = 0.000); there are interactive effects between time and gender groups in left ventricle ( = 8.597, = 0.006) while no interactive effects in other chambers with the remaining groups; and the different weight groups' volume is statistically significant in right ventricle ( = 9.004, = 0.005) while no statistical significance in other chambers with remaining groups. The accuracy of cardiac volume and time relationship utilizing structured sparse learning is close to the least square method, but the former's expression is more concise and more robust. The number of nonzero basic function of the structured sparse model is just 2.2 percent of that of least square model. Hence, the work provides more the accurate and concise expression of the cardiac for cardiac motion simulation.