Search

Background Purpose Methods Results Conclusions Gadolinium‐based contrast agents are commonly used in brain magnetic resonance imaging (MRI), however, they cannot be used by patients with allergic reactions or poor renal function. For long‐term follow‐up patients, gadolinium deposition in the body can cause nephrogenic systemic fibrosis and other potential risks.Developing a new method of enhanced image synthesis based on the advantages of multisequence MRI has important clinical value for these patients. In this paper, an end‐to‐end synthesis model structure similarity index measure (SSIM)‐based Dual Constrastive Learning with Attention (SDACL) based on contrastive learning is proposed to synthesize contrast‐enhanced T1 (T1ce) using three unenhanced MRI images of T1, T2, and Flair in patients with glioma.The model uses the attention–dilation generator to enlarge the receptive field by expanding the residual blocks and to strengthen the feature representation and context learning of multisequence MRI. To enhance the detail and texture performance of the imaged tumor area, a comprehensive loss function combining patch‐level contrast loss and structural similarity loss is created, which can effectively suppress noise and ensure the consistency of synthesized images and real images.The normalized root‐mean‐square error (NRMSE), peak signal‐to‐noise ratio (PSNR), and SSIM of the model on the independent test set are 0.307 ±$\pm$ 0.12, 23.337 ±$\pm$ 3.21, and 0.881 ±$\pm$ 0.05, respectively.Results show this method can be used for the multisequence synthesis of T1ce images, which can provide valuable information for clinical diagnosis.  [ABSTRACT FROM AUTHOR]

Objective. Medical image registration aims to find the deformation field that can align two images in a spatial position. A medical image registration method based on U-Net architecture has been proposed currently. However, U-Net architecture has few training parameters, which leads to weak learning ability, and it ignores the adverse effects of image noise on the registration accuracy. The article aims at addressing the problem of weak network learning ability and the adverse effects of noisy images on registration. Approach. Here we propose a novel unsupervised 3D brain image registration framework, which introduces the residual unit and singular value decomposition (SVD) denoising layer on the U-Net architecture. Residual unit solves the problem of network degradation, that is, registration accuracy becomes saturated and then degrades rapidly with the increase in network depth. SVD denoising layer uses the estimated model order for SVD-based low-rank image reconstruction. we use Akaike information criterion to estimate the appropriate model order, which is used to remove noise components. We use the exponential linear unit (ELU) as the activation function, which is more robust to noise than other peers. Main results. The proposed method is evaluated on the publicly available brain MRI datasets: Mindboggle101 and LPBA40. Experimental results demonstrate our method outperforms several state-of-the-art methods for the metric of Dice Score. The mean number of folding voxels and registration time are comparable to state-of-the-art methods. Significance. This study shows that Deep Residual-SVD Network can improve registration accuracy. This study also demonstrate that the residual unit can enhance the learning ability of the network, the SVD denoising layer can denoise effectively, and the ELU is more robust to noise. [ABSTRACT FROM AUTHOR]

The identification and protection of critical nodes have a significant influence on the reliability and robustness of the cyber–physical power system (CPPS), which can effectively reduce the risk of cascading failures. Firstly, this paper establishes a one-to-one coupled cascading fault model, which considers different topological characteristics of power and cyber networks. Based on the interdependence between the two networks, the cascading fault propagation mechanism after node failures in CPPS is analyzed. Then, a critical node identification method based on improved adaptive differential evolution (JADE) is proposed to identify the sets of critical nodes that can maximize the impact on the system load of CPPS. Combined with the cascading failure characteristics of CPPS, in the population generation strategy, the test vectors that do not meet the conditions after the crossover operation are filtered and replaced to improve the search efficiency of the algorithm. Finally, in the case study, an interdependent CPPS is constructed with an IEEE 39-bus system and a scale-free network of the same nodes. The simulation results verify the effectiveness of the proposed node importance assessment strategy. In addition, it is also shown that evaluating the critical nodes in power systems is important for enhancing the robustness and ensuring the security of the power grid operation. • An improved JADE method is proposed to identify the sets of critical nodes in CPPS. • By adopting the identification method of JADE, the sets of critical nodes with a greater impact on the system load can be obtained. • The specific solution representation and the population generation technique of power systems are introduced into the improved JADE method to effectively solve the IM problem of CPPS. • The established cascading failure model provides a feasible way to analyze the propagation mechanism after node failure in CPPS. [ABSTRACT FROM AUTHOR]

The identification of critical nodes is important for safe operation and accident prevention in power grids. With the accelerated development of renewable energies, the uncertainty of renewable energy has brought greater challenges to the node importance assessment of the power system. The electrical spreading probability method is proposed in this paper to identify the critical nodes in the power grid containing renewable energy. First, the uncertainty factors of renewable energy are established through probability density functions, and Monte Carlo simulation and stochastic DC optimum power flow are adopted to effectively deal with the impact of uncertain power output from solar and wind energies. Then, considering the system topology and load loss after cascading failures calculated by Monte Carlo simulation, a method is proposed to calculate the probability of nodes being infected. Finally, according to the Susceptible–Infected model, a method depending on the propagation ability of nodes is proposed to identify the critical nodes in the complex power system. The effectiveness of the proposed ESP method is verified through simulation examples of the modified IEEE39 power system and the modified IEEE118 power system. • An electrical spreading probability method is proposed. • By adopting the ESP method, a more accurate assessment result can be obtained. • More effectively eliminate the uncertainty brought by renewable energy integration. [ABSTRACT FROM AUTHOR]

The purpose of this study was to explore the neural mechanism in Chronic prostatitis/Chronic pelvic pain syndrome (CP/CPPS) using resting-state functional magnetic resonance imaging. The functional magnetic resonance imaging was performed on 31 male CP/CPPS-patients and 31 age and education matched male healthy controls on a 3-T magnetic resonance imaging unit. A two-sample t-test was adopted to reveal the regional homogeneity between the patients and healthy controls. The mean regional homogeneity values in the alerted brain regions of patients were correlated with the clinical measurements by using Pearson's correlation analyses. The CP/CPPS-patients had significantly decreased regional homogeneity in the bilateral anterior cingulate cortices, insular cortices and right medial prefrontal cortex, while significantly increased regional homogeneity in the brainstem and right thalamus compared with the healthy controls. In the CP/CPPS-patients, the mean regional homogeneity value in the left anterior cingulate cortex, bilateral insular cortices and brainstem were respectively correlated with the National Institutes of Health Chronic Prostatitis Symptom Index total score and pain subscale. These brain regions are important in the pain modulation process. Therefore, an impaired pain modulatory system, either by decreased descending pain inhibition or enhanced pain facilitation, may explain the pain symptoms in CP/CPPS. [ABSTRACT FROM AUTHOR]

Nickel (Ni) particles were compounded into polyimide (PI) and PI reinforced with carbon fiber (CF). Role of Ni particles on tribological performance of the PI-based materials sliding against a bearing steel were investigated under boundary and mixed lubrication regimes. Remarkably, PI composites filled with Ni exhibit ultra-low friction and wear. Interestingly, friction- and wear-reduction roles of Ni are much more significant than those of CF. The results provide direct evidence that an extremely thin NiO glaze layer grows on the steel counterface, above which a uniform C-based tribofilm is formed. It is assumed that the NiO layer can catalyze dehydrogenation of oil molecules and promote tribofilm formation. The present work proposes a design concept of high-performance tribofilm for improving boundary lubrication of motion components. • Ni particles were compounded into PI and CF-reinforcing PI. • Ni greatly improve tribological performance of PI composites under harsh lubrication conditions. • Friction- and wear-reduction roles of Ni are much more significant than those of CF. • A thin NiO glaze layer grows on steel counterface, which can promote tribofilm formation. [ABSTRACT FROM AUTHOR]

Purpose: To develop and validate an effective model to differentiate NF-pNET from PDAC.Materials and Methods: Between July 2014 and December 2017, 147 patients (80 patients with PDAC and 67 patients with atypical NF-pNET) with pathology results and enhanced CT were consecutively enrolled and chronologically divided into primary and validation cohorts. Three models were built to differentiate atypical NF-pNET from PDAC, including a model based on radiomic signature alone, one based on clinicoradiological features alone and one that integrated the two. The diagnostic performance of the three models was estimated and compared with the area under the receiver operating characteristic curve (AUC) in the validation cohort. A nomogram was used to represent the model with the best performance, and the associated calibration was also assessed.Results: In the validation cohort, the AUC for differential diagnosis was 0.884 with the integrated model, which was significantly improved over that of the model based on clinicoradiological features (AUC = 0.775, p value = 0.004) and was comparable to that of the model based on the radiomic signature (AUC = 0.873, p value = 0.512). The nomogram representing the integrated model achieved good discrimination performances in both the primary and validation cohorts, with C-indices of 0.960 and 0.884, respectively.Conclusion: The integrated model outperformed the model based on clinicoradiological features alone and was comparable to the model based on the radiomic signature alone with respect to the differential diagnosis of atypical NF-pNET and PDAC. The nomogram achieved an optimal preoperative, noninvasive differential diagnosis between atypical pNET and PDAC, which can better inform therapeutic choice in clinical practice. [ABSTRACT FROM AUTHOR]

Glioma detection and segmentation is a challenging task for radiologists and clinicians. The research reported in this paper seeks to develop a better clinical decision support algorithm for clinicians diagnosis. This paper presents a probabilistic method for detection and segmentation between abnormal tissue regions and brain tumour (tumour core and edema) portions from Magnetic Resonance Imaging (MRI). A framework is constructed to learn structure of undirected graphical models that can represent the spatial relationships among variables and apply it to glioma segmentation. Compared with the pixel of image, the superpixel is more consistent with human visual cognition and contains less redundancy, thus, the superpixels are considered as the basic unit of structure learning and glioma segmentation scheme. ℓ1-regularization techniques are applied to learn the appropriate structure for modeling graphical models. Conditional Random Fields (CRF) are used to model the spatial interactions among image superpixel regions and their measurements. A number of features including statistics features, the combined features from the local binary pattern as well as gray level run length, curve features, and fractal features were extracted from each superpixel. The features are then passed by ℓ1-regularization to ensure a robust classification. The proposed method is compared with support vector machine and Fuzzy c-means to classify each superpixel into normal and abnormal tissue. The proposed system is tested for the presence of low grade as well as high grade glioma tumors on images collected from BRATS2013, BRATS2015 data set and Henan Provincial People’s Hospital (HNPPH) data set. The experiments performed provides similarity between segmented and truth image up to 91.5% by correlation method. [ABSTRACT FROM AUTHOR]

The phenomenal success and popularity of peer-to-peer (p2p) streaming over the last decade took many providers, researchers, as well as the mass, by surprise. It would become the dominant type of traffic over the Internet in the very near future. The released Windows Vista contains its own P2P networking system. Though P2P streaming has become one of the most attractive network applications, it is still awaiting some technological breakthroughs. P2P streaming faces very different challenges from other P2P applications, such as file download. In live P2P streaming, the stringent real-time performance requirement in terms of bandwidth and latency is one of the challenges it faces. In addition, frequent joining and leaving of the autonomous end-hosts have more significant impact on the system performance. So the churn problem and reconstruction due to uncertainty are key challenges of P2P streaming. A number of solutions were proposed which did not take all the factors into account. This paper presents IAM (IP Address Matching), a novel protocol for P2P live streaming system. For overlay structure, neighbor selection algorithm-FAMM (Forward Address Maximum Matching), which allows the peer choose the close peers as neighbors, is proposed. In this mechanism peer selects neighbors by matching IP address in regular expression. IP address is assigned by area basically, so the closer the peers are, the more the same bits of IP address they have. Peer chooses the first m (m > 0) peers whose IP address has same bits with it as the neighbors. Meanwhile, the latency is generally low. FAMM just likes the DHT routing. As managing peer failures and proper recovery are of critical importance for a robust P2P streaming system, a new peer exception mechanism is also proposed which is the other central issue of the IAM. According to the different error information which the peer receives, it detects the departure or failure of the neighbor intelligently and recovers from an unstable state promptly. To evaluate the performance of the IAM, we have conducted extensive simulations and real-network experiment. The results indicate that IAM shortens the latency and is robust to the dynamic peers. It achieves superior comprehensive performance over Random scheme. It is proved effective in the real-network environment, and the latency of recovery is shortened significantly which is only 25% of that with the usual mechanism, as well. [ABSTRACT FROM AUTHOR]

In recent years, deep learning (DNN) based methods have made leapfrogging level breakthroughs in detecting cardiac arrhythmias as the cost effectiveness of arithmetic power, and data size has broken through the tipping point. However, the inability of these methods to provide a basis for modeling decisions limits clinicians' confidence on such methods. In this paper, a Gate Recurrent Unit (GRU) and decision tree fusion model, referred to as (T-GRU), was designed to explore the problem of arrhythmia recognition and to improve the credibility of deep learning methods. The fusion model multipathway processing time-frequency domain featured the introduction of decision tree probability analysis of frequency domain features, the regularization of GRU model parameters and weight control to improve the decision tree model output weights. The MIT-BIH arrhythmia database was used for validation. Results showed that the low-frequency band features dominated the model prediction. The fusion model had an accuracy of 98.31%, sensitivity of 96.85%, specificity of 98.81%, and precision of 96.73%, indicating its high reliability and clinical significance. [ABSTRACT FROM AUTHOR]

Purpose: Breast mass segmentation is a prerequisite step in the use of computer‐aided tools designed for breast cancer diagnosis and treatment planning. However, mass segmentation remains challenging due to the low contrast, irregular shapes, and fuzzy boundaries of masses. In this work, we propose a mammography mass segmentation model for improving segmentation performance. Methods: We propose a mammography mass segmentation model called SAP‐cGAN, which is based on an improved conditional generative adversarial network (cGAN). We introduce a superpixel average pooling layer into the cGAN decoder, which utilizes superpixels as a pooling layout to improve boundary segmentation. In addition, we adopt a multiscale input strategy to enable the network to learn scale‐invariant features with increased robustness. The performance of the model is evaluated with two public datasets: CBIS‐DDSM and INbreast. Moreover, ablation analysis is conducted to evaluate further the individual contribution of each block to the performance of the network. Results: Dice and Jaccard scores of 93.37% and 87.57%, respectively, are obtained for the CBIS‐DDSM dataset. The Dice and Jaccard scores for the INbreast dataset are 91.54% and 84.40%, respectively. These results indicate that our proposed model outperforms current state‐of‐the‐art breast mass segmentation methods. The superpixel average pooling layer and multiscale input strategy has improved the Dice and Jaccard scores of the original cGAN by 7.8% and 12.79%, respectively. Conclusions: Adversarial learning with the addition of a superpixel average pooling layer and multiscale input strategy can encourage the Generator network to generate masks with increased realism and improve breast mass segmentation performance through the minimax game between the Generator network and Discriminator network. [ABSTRACT FROM AUTHOR]

Image enhancement technology is often used to improve the quality of medical images and helps doctors or expert systems identify and diagnose diseases. This paper aimed at the characteristics of magnetic resonance imaging (MRI) with complex and difficult-to-enhance details and to propose a nonsubsampled contourlet transform- (NSCT-) based enhancement algorithm called MIE-NSCT. NSCT was used for MRI sub-band decomposition. For high-pass sub-bands, four fuzzy rules were proposed to enhance multiscale and multidirectional edge contour details from adjacent eight directions, whilst for low-pass sub-bands, a new adaptive histogram enhancement algorithm was proposed. The problem of noise amplification and loss of details during the enhancement process was solved. The algorithm was verified on the public dataset BraTS2017 and compared with other advanced methods. Experimental results showed that MIE-NSCT had obvious advantages in improving the quality of medical images, and high-quality medical images showed enhanced performance in grading tumour. MIE-NSCT is suitable for integration into an interactive expert system to provide support for the visualization of disease diagnosis. [ABSTRACT FROM AUTHOR]

Purpose: Patients with skull base chordoma and chondrosarcoma have different prognoses and are not readily differentiated preoperatively on imaging. Multiparametric magnetic resonance imaging (MRI) is a routine diagnostic tool that can noninvasively characterize the salient characteristics of tumors. In the present study, we developed and validated a preoperative multiparametric MRI-based radiomic signature for differentiating these tumors.Method: This retrospective study enrolled 210 patients and consecutively divided them into the primary and validation cohorts. A total of 1941 radiomic features were acquired from preoperative T1-weighted imaging, T2-weighted imaging and contrast-enhanced T1-weighted imaging for each patient. The most discriminative features were selected by minimum-redundancy maximum-relevancy and recursive feature elimination algorithms in the primary cohort. The multiparametric and single-sequence MRI signatures were constructed with the selected features using a support vector machine model in the primary cohort. The ability of the novel radiomic signatures to differentiate chordoma from chondrosarcoma were assessed using receiver operating characteristic curve analysis in the validation cohort.Results: The multiparametric radiomic signature, which consisted of 11 selected features, reached an area under the receiver operating characteristic curve of 0.9745 and 0.8720 in the primary and validation cohorts, respectively. Moreover, compared with each single-sequence MRI signature, the multiparametric radiomic signature exhibited better classification performance with significant improvement (p <  0.05, Delong's test) in the primary cohorts.Conclusion: By combining features from three MRI sequences, the multiparametric radiomics signature can accurately and robustly differentiate skull base chordoma from chondrosarcoma. [ABSTRACT FROM AUTHOR]

Amide proton transfer (APT) imaging is a noninvasive molecular magnetic resonance imaging (MRI) technique based on the chemical exchange-dependent saturation transfer mechanism. The purpose of this study was to investigate the diagnostic performance of APT MRI in detecting intracranial hemorrhage (ICH) at hyperacute, acute and subacute stages by comparing with susceptibility weighted imaging (SWI). APT MRI and SWI were performed on 33 included patients with ICH by using a 3-T MRI unit. A two-sided Mann-Whitney U test was used to detect differences in APT-weighted (APTw) and SWI signal intensities of ICH at hyperacute, acute and subacute stages. Receiver operating characteristic analysis was used to assess the diagnostic utilities of APT MRI and SWI. Our results showed that APT MRI could detect ICH at hyperacute, acute and subacute stages. Therefore, APTw signal intensity may serve as a reliable, noninvasive imaging biomarker for detecting ICH at hyperacute, acute and subacute stages. Moreover, APT MRI could provide additional information for the ICH compared with SWI. [ABSTRACT FROM AUTHOR]

Dendritic-like BiVO 4 :Ag heterostructure was formed in the process of visible light-irradiated photocatalysis using dendritic-like BiVO 4 as photocatalyst, AgNO 3 as additive and photocatalytic degradation of Rhodamine B (RhB) solution as model reaction. In the coexistence of BiVO 4 and AgNO 3 , Ag islands (nanoparticles) could be formed on the surface of dendritic-like BiVO 4 crystals after Ag + ions captured the photo-generated electrons, and hence the BiVO 4 :Ag heterostructure was obtained. The formation of Ag islands can be directly confirmed by TEM technique. The synergistic effect of the formation of BiVO 4 :Ag heterostructure and Ag + ions as electron capture agent leads to prominent improvement of the photocatalytic activity, i.e., the decolor efficiency of the dendritic-like BiVO 4 photocatalysts for degradation of RhB solution was prominently improved from 34.4% to 91.4% under visible light irradiation only for 20 min. [ABSTRACT FROM AUTHOR]

To establish a radiomics nomogram by integrating clinical risk factors and radiomics features extracted from digital mammography (MG) images for pre-operative prediction of axillary lymph node (ALN) metastasis in breast cancer. 216 patients with breast cancer lesions confirmed by surgical excision pathology were divided into the primary cohort (n = 144) and validation cohort (n = 72). Radiomics features were extracted from craniocaudal (CC) view of mammograms, and radiomics features selection were performed using the methods of ANOVA F-value and least absolute shrinkage and selection operator; then a radiomics signature was constructed with the method of support vector machine. Multivariate logistic regression analysis was used to establish a radiomics nomogram based on the combination of radiomics signature and clinical factors. The C-index and calibration curves were derived based on the regression analysis both in the primary and validation cohorts. 95 of 216 patients were confirmed with ALN metastasis by pathology, and 52 cases were diagnosed as ALN metastasis based on MG-reported criteria. The sensitivity, specificity, accuracy and AUC (area under the receiver operating characteristic curve of MG-reported criteria were 42.7%, 90.8%, 24.1% and 0.666 (95% confidence interval: 0.591–0.741]. The radiomics nomogram, comprising progesterone receptor status, molecular subtype and radiomics signature, showed good calibration and better favorite performance for the metastatic ALN detection (AUC 0.883 and 0.863 in the primary and validation cohorts) than each independent clinical features (AUC 0.707 and 0.657 in the primary and validation cohorts) and radiomics signature (AUC 0.876 and 0.862 in the primary and validation cohorts). The MG-based radiomics nomogram could be used as a non-invasive and reliable tool in predicting ALN metastasis and may facilitate to assist clinicians for pre-operative decision-making. ALN status remains among the most important breast cancer prognostic factors and is essential for making treatment decisions. However, the value of detecting metastatic ALN by MG is very limited. The studies on pre-operative ALN metastasis prediction using the method of MG-based radiomics in breast cancer are very few. Therefore, we studied whether MG-based radiomics nomogram could be used as a predictive biomarker for the detection of metastatic ALN. [ABSTRACT FROM AUTHOR]

Purpose: The preoperative prediction of treatment response is important for determining individual treatment strategies for invasive functional pituitary adenoma (IFPA). This study aimed to develop and validate a magnetic resonance imaging (MRI)-based radiomic signature for preoperative prediction of treatment response in IFPA.Method: One hundred and sixty-three patients with IFPA were enrolled and divided into primary (n = 108) and validation cohorts (n = 55) according to time point. IFPA patients were divided into remission and non-remission according to postoperative hormone levels. Radiomic features were extracted from their MR images and a radiomic signature was built using a support vector machine. Subsequently, multivariable logistic regression analysis was used to select the most informative clinical features, and a radiomic model incorporating the radiomic signature and selected clinical features was constructed and used as the final predictive model.Results: Seven radiomic features were selected to construct the radiomic signature, which achieved an area under the curve (AUC) of 0.834 and 0.808 on the primary and validation cohorts respectively. The radiomic model incorporating the radiomic signature and Knosp grade showed good discrimination abilities and calibration, with AUCs of 0.832 and 0.811 for the primary and validation cohorts respectively. The radiomic signature and radiomic model better estimated the treatment responses of patients with IFPA than our clinical features model. Decision curve analysis showed the radiomic model was clinically useful.Conclusions: This radiomic model may help neurosurgeons predict the treatment responses of patients with IFPA before surgery and determine individual treatment strategies. [ABSTRACT FROM AUTHOR]