Dual-TranSpeckle: Dual-pathway transformer based encoder-decoder network for medical ultrasound image despeckling.

The majority of existing deep learning-based image denoising algorithms mainly focus on processing the overall image features, ignoring the fine differences between the semantic and pixel features. Hence, we propose Dual-TranSpeckle (DTS), a medical ultrasound image despeckling network built on a dual-path Transformer. The DTS introduces two different paths, named "semantic path" and "pixel path," to facilitate the parallel transfer of feature information within the image. The semantic path passes a global view of the input semantic features, and the image features are passed through a Semantic Block to extract global semantic information from pixel-level features. The pixel path is employed to transmit finer-grained pixel features. Within the dual-path network framework, two essential modules, namely Dual Block and Merge Block, are designed. These leverage the Transformer architecture during the encoding and decoding stages. The Dual Block module facilitates information interaction between the semantic and pixel features by considering the interdependencies across both paths. Meanwhile, the Merge Block module enables parallel transfer of feature information by merging the dual path features, thereby facilitating the self-attention calculations for the overall feature representation. Our DTS is extensively evaluated on two public datasets and one private dataset. The DTS network demonstrates significant enhancements in quantitative evaluation results in terms of peak signal-to-noise ratio (PSNR), structural similarity (SSIM), feature similarity (FSIM), and naturalness image quality evaluator (NIQE). Furthermore, our qualitative analysis confirms that the DTS has significant improvements in despeckling performance, effectively suppressing speckle noise while preserving essential image structures.

Improved brain community structure detection by two-step weighted modularity maximization.

The human brain can be regarded as a complex network with interacting connections between brain regions. Complex brain network analyses have been widely applied to functional magnetic resonance imaging (fMRI) data and have revealed the existence of community structures in brain networks. The identification of communities may provide insight into understanding the topological functions of brain networks. Among various community detection methods, the modularity maximization (MM) method has the advantages of model conciseness, fast convergence and strong adaptability to large-scale networks and has been extended from single-layer networks to multilayer networks to investigate the community structure changes of brain networks. However, the problems of MM, suffering from instability and failing to detect hierarchical community structure in networks, largely limit the application of MM in the community detection of brain networks. In this study, we proposed the weighted modularity maximization (WMM) method by using the weight matrix to weight the adjacency matrix and improve the performance of MM. Moreover, we further proposed the two-step WMM method to detect the hierarchical community structures of networks by utilizing node attributes. The results of the synthetic networks without node attributes demonstrated that WMM showed better partition accuracy than both MM and robust MM and better stability than MM. The two-step WMM method showed better accuracy of community partitioning than WMM for synthetic networks with node attributes. Moreover, the results of resting state fMRI (rs-fMRI) data showed that two-step WMM had the advantage of detecting the hierarchical communities over WMM and was more insensitive to the density of the rs-fMRI networks than WMM.

HCformer: Hybrid CNN-Transformer for LDCT Image Denoising.

Low-dose computed tomography (LDCT) is an effective way to reduce radiation exposure for patients. However, it will increase the noise of reconstructed CT images and affect the precision of clinical diagnosis. The majority of the current deep learning-based denoising methods are built on convolutional neural networks (CNNs), which concentrate on local information and have little capacity for multiple structures modeling. Transformer structures are capable of computing each pixel's response on a global scale, but their extensive computation requirements prevent them from being widely used in medical image processing. To reduce the impact of LDCT scans on patients, this paper aims to develop an image post-processing method by combining CNN and Transformer structures. This method can obtain a high-quality images from LDCT. A hybrid CNN-Transformer (HCformer) codec network model is proposed for LDCT image denoising. A neighborhood feature enhancement (NEF) module is designed to introduce the local information into the Transformer's operation, and the representation of adjacent pixel information in the LDCT image denoising task is increased. The shifting window method is utilized to lower the computational complexity of the network model and overcome the problems that come with computing the MSA (Multi-head self-attention) process in a fixed window. Meanwhile, W/SW-MSA (Windows/Shifted window Multi-head self-attention) is alternately used in two layers of the Transformer to gain the information interaction between various Transformer layers. This approach can successfully decrease the Transformer's overall computational cost. The AAPM 2016 LDCT grand challenge dataset is employed for ablation and comparison experiments to demonstrate the viability of the proposed LDCT denoising method. Per the experimental findings, HCformer can increase the image quality metrics SSIM, HuRMSE and FSIM from 0.8017, 34.1898, and 0.6885 to 0.8507, 17.7213, and 0.7247, respectively. Additionally, the proposed HCformer algorithm will preserves image details while it reduces noise. In this paper, an HCformer structure is proposed based on deep learning and evaluated by using the AAPM LDCT dataset. Both the qualitative and quantitative comparison results confirm that the proposed HCformer outperforms other methods. The contribution of each component of the HCformer is also confirmed by the ablation experiments. HCformer can combine the advantages of CNN and Transformer, and it has great potential for LDCT image denoising and other tasks.

Regional perception and multi-scale feature fusion network for cardiac segmentation.

Objective.Cardiovascular disease (CVD) is a group of diseases affecting cardiac and blood vessels, and short-axis cardiac magnetic resonance (CMR) images are considered the gold standard for the diagnosis and assessment of CVD. In CMR images, accurate segmentation of cardiac structures (e.g. left ventricle) assists in the parametric quantification of cardiac function. However, the dynamic beating of the heart renders the location of the heart with respect to other tissues difficult to resolve, and the myocardium and its surrounding tissues are similar in grayscale. This makes it challenging to accurately segment the cardiac images. Our goal is to develop a more accurate CMR image segmentation approach.Approach.In this study, we propose a regional perception and multi-scale feature fusion network (RMFNet) for CMR image segmentation. We design two regional perception modules, a window selection transformer (WST) module and a grid extraction transformer (GET) module. The WST module introduces a window selection block to adaptively select the window of interest to perceive information, and a windowed transformer block to enhance global information extraction within each feature window. The WST module enhances the network performance by improving the window of interest. The GET module grids the feature maps to decrease the redundant information in the feature maps and enhances the extraction of latent feature information of the network. The RMFNet further introduces a novel multi-scale feature extraction module to improve the ability to retain detailed information.Main results.The RMFNet is validated with experiments on three cardiac data sets. The results show that the RMFNet outperforms other advanced methods in overall performance. The RMFNet is further validated for generalizability on a multi-organ data set. The results also show that the RMFNet surpasses other comparison methods.Significance.Accurate medical image segmentation can reduce the stress of radiologists and play an important role in image-guided clinical procedures.

3D SAACNet with GBM for the classification of benign and malignant lung nodules.

In view of the low diagnostic accuracy of the current classification methods of benign and malignant pulmonary nodules, this paper proposes a 3D segmentation attention network integrating asymmetric convolution (SAACNet) classification model combined with a gradient boosting machine (GBM). This can make full use of the spatial information of pulmonary nodules. First, the asymmetric convolution (AC) designed in SAACNet can not only strengthen feature extraction but also improve the network's robustness to object flip and rotation detection and improve network performance. Second, the segmentation attention network integrating AC (SAAC) block can effectively extract more fine-grained multiscale spatial information while adaptively recalibrating multidimensional channel attention weights. The SAACNet also uses a dual-path connection for feature reuse, where the model makes full use of features. In addition, this article makes the loss function pay more attention to difficult and misclassified samples by adding adjustment factors. Third, the GBM is used to splice the nodule size, originally cropped nodule pixels, and the depth features learned by SAACNet to improve the prediction accuracy of the overall model. A comprehensive ablation experiment is carried out on the public dataset LUNA16 and compared with other lung nodule classification models. The classification accuracy (ACC) is 95.18%, and the area under the curve (AUC) is 0.977. The results show that this method effectively improves the classification performance of pulmonary nodules. The proposed method has advantages in the classification of benign and malignant pulmonary nodules, and it can effectively assist radiologists in pulmonary nodule classification.

Lightweight YOLOv4 with Multiple Receptive Fields for Detection of Pulmonary Tuberculosis.

The characteristics of pulmonary tuberculosis are complex, and the cost of manual screening is high. The detection model based on convolutional neural network is an essential method for assisted diagnosis with artificial intelligence. However, it also has the disadvantages of complex structure and a large number of parameters, and the detection accuracy needs to be further improved. Therefore, an improved lightweight YOLOv4 pulmonary tuberculosis detection model named MIP-MY is proposed. Firstly, over 300 actual cases are selected to make a common dataset by professional physicians, which is used to evaluate the performance of the model. Subsequently, by introducing the inverted residual channel attention and the pyramid pooling module, a new structure of MIP is created and used as the backbone extractor of MIP-MY, which could further decrease the number of parameters and fuse context information. Then the multiple receptive field module is added after the three effective feature layers of the backbone extractor, which effectively enhances the information extraction ability of the deep feature layer and reduces the miss detection rate of small pulmonary tuberculosis lesions. Finally, the pulmonary tuberculosis detection model MIP-MY with lightweight and multiple receptive field characteristics is constructed by combining each improved modules with multiscale structure. Compared to the original YOLOv4, the model parameters of MIP-MY is reduced by 47%, while the mAP value is raised to 95.32% and the miss detection rate is decreased to 6%. It is verified that the model can effectively assist radiologists in the diagnosis of pulmonary tuberculosis.

Fine-grained calibrated double-attention convolutional network for left ventricular segmentation.

Objective.Left ventricular (LV) segmentation of cardiac magnetic resonance imaging (MRI) is essential for diagnosing and treating the early stage of heart diseases. In convolutional neural networks, the target information of the LV in feature maps may be lost with convolution and max-pooling, particularly at the end of systolic. Fine segmentation of ventricular contour is still a challenge, and it may cause problems with inaccurate calculation of clinical parameters (e.g. ventricular volume). In order to improve the similarity of the neural network output and the target segmentation region, in this paper, a fine-grained calibrated double-attention convolutional network (FCDA-Net) is proposed to finely segment the endocardium and epicardium from ventricular MRI.Approach.FCDA-Nettakes the U-net as the backbone network, and the encoder-decoder structure incorporates a double grouped-attention module that is constructed by a fine calibration spatial attention module (fcSAM) and a fine calibration channel attention module (fcCAM). The double grouped-attention mechanism enhances the expression of information in both spatial and channelwise feature maps to achieve fine calibration.Main Results.The proposed approach is evaluated on the public MICCAI 2009 challenge dataset, and ablation experiments are conducted to demonstrate the effect of each grouped-attention module. Compared with other advanced segmentation methods,FCDA-Netcan obtain better LV segmentation performance.Significance.The LV segmentation results of MRI can be used to perform more accurate quantitative analysis of many essential clinical parameters and it can play an important role in image-guided clinical surgery.

MSANet: Multiscale Aggregation Network Integrating Spatial and Channel Information for Lung Nodule Detection.

Improving the detection accuracy of pulmonary nodules plays an important role in the diagnosis and early treatment of lung cancer. In this paper, a multiscale aggregation network (MSANet), which integrates spatial and channel information, is proposed for 3D pulmonary nodule detection. MSANet is designed to improve the network's ability to extract information and realize multiscale information fusion. First, multiscale aggregation interaction strategies are used to extract multilevel features and avoid feature fusion interference caused by large resolution differences. These strategies can effectively integrate the contextual information of adjacent resolutions and help to detect different sized nodules. Second, the feature extraction module is designed for efficient channel attention and self-calibrated convolutions (ECA-SC) to enhance the interchannel and local spatial information. ECA-SC also recalibrates the features in the feature extraction process, which can realize adaptive learning of feature weights and enhance the information extraction ability of features. Third, the distribution ranking (DR) loss is introduced as the classification loss function to solve the problem of imbalanced data between positive and negative samples. The proposed MSANet is comprehensively compared with other pulmonary nodule detection networks on the LUNA16 dataset, and a CPM score of 0.920 is obtained. The results show that the sensitivity for detecting pulmonary nodules is improved and that the average number of false-positives is effectively reduced. The proposed method has advantages in pulmonary nodule detection and can effectively assist radiologists in pulmonary nodule detection.

Breaking the barrier to biomolecule limit-of-detection via 3D printed multi-length-scale graphene-coated electrodes.

Sensing of clinically relevant biomolecules such as neurotransmitters at low concentrations can enable an early detection and treatment of a range of diseases. Several nanostructures are being explored by researchers to detect biomolecules at sensitivities beyond the picomolar range. It is recognized, however, that nanostructuring of surfaces alone is not sufficient to enhance sensor sensitivities down to the femtomolar level. In this paper, we break this barrier/limit by introducing a sensing platform that uses a multi-length-scale electrode architecture consisting of 3D printed silver micropillars decorated with graphene nanoflakes and use it to demonstrate the detection of dopamine at a limit-of-detection of 500 attomoles. The graphene provides a high surface area at nanoscale, while micropillar array accelerates the interaction of diffusing analyte molecules with the electrode at low concentrations. The hierarchical electrode architecture introduced in this work opens the possibility of detecting biomolecules at ultralow concentrations.

Dynamic Functional Network Connectivity Changes Associated with fMRI Neurofeedback of Right Premotor Cortex.

Neurofeedback of real-time functional magnetic resonance imaging (rtfMRI) can enable people to self-regulate motor-related brain regions and lead to alteration of motor performance and functional connectivity (FC) underlying motor execution tasks. Numerous studies suggest that FCs dynamically fluctuate over time. However, little is known about the impact of neurofeedback training of the motor-related region on the dynamic characteristics of FC underlying motor execution tasks. This study aims to investigate the mechanism of self-regulation of the right premotor area (PMA) on the underlying dynamic functional network connectivity (DFNC) of motor execution (ME) tasks and reveal the relationship between DFNC, training effect, and motor performance. The results indicate that the experimental group spent less time on state 2, with overall weak connections, and more time on state 6, having strong positive connections between motor-related networks than the control group after the training. For the experimental group's state 2, the mean dwell time after the training showed negative correlation with the tapping frequency and the amount of upregulation of PMA. The findings show that rtfMRI neurofeedback can change the temporal properties of DFNC, and the DFNC changes in state with overall weak connections were associated with the training effect and the improvement in motor performance.

Enhancing Thermal Interface Conductance to Graphene Using Ni-Pd Alloy Contacts.

To identify superior thermal contacts to graphene, we implement a high-throughput methodology that systematically explores the Ni-Pd alloy composition spectrum and the effect of Cr adhesion layer thickness on thermal interface conductance with monolayer graphene. Frequency domain thermoreflectance measurements of two independently prepared Ni-Pd/Cr/graphene/SiO2 samples identify a maximum metal/graphene/SiO2 junction thermal interface conductance of 114 ± (39, 25) MW/m2 K and 113 ± (33, 22) MW/m2 K at ∼10 at. % Pd in Ni-nearly double the highest reported value for pure metals and 3 times that of pure Ni or Pd. The presence of Cr, at any thickness, suppresses this maximum. Although the origin of the peak is unresolved, we find that it correlates with a region of the Ni-Pd phase diagram that exhibits a miscibility gap. Cross-sectional imaging by high-resolution transmission electron microscopy identifies striations in the alloy at this particular composition, consistent with separation into multiple phases. Through this work, we draw attention to alloys in the search for better contacts to two-dimensional materials for next-generation devices.

Modified Sauve-Kapandji Procedure for Patients with Old Fractures of the Distal Radius.

OBJECTIVE: To evaluate the clinical and radiographic outcomes of a modified Sauve-Kapandji procedure for patients with old fractures in the distal radius. METHODS: Fifteen patients (10 male and 5 female patients with an average age of 40 years old) were treated by the modified Sauve-Kapandji procedure from January 2014 to April 2016. All patients had undergone at least one previous operation on the involved wrist, and they were still suffering from pain and functional limitations at the time of admission. The postoperative follow-up period was 12-26 months and the average was 20 months. Functional assessment was made at the last follow-up. All patients were evaluated according a Modified Mayo Wrist Score system. RESULTS: Of the fifteen patients with posttraumatic arthritis, thirteen had excellent results, two had good results, and one had fair results. There were no major complications. CONCLUSIONS: The modified Sauve-Kapandji procedure is a safe and effective surgical alternative for intractable disorders of the distal radioulnar joint and can be recommended as a salvage procedure when previous treatments fail.

Downregulation of microRNA­574 in cancer stem cells causes recurrence of prostate cancer via targeting REL.

miR­574­5p has been reported involved in the pathogenesis of numerous human malignancies such as colorectal and lung cancer. In this study, we aimed to explore the roles of REL and miR­574 in the recurrence of prostate cancer (PCa) and to identify the underlying molecular mechanisms. Our literature search found that miR­574 is regulated in cancer stem cells (CSCs), and next we used the microRNA (miRNA) database (www.mirdb.org) to find REL as a target of miR­574. Luciferase assay was performed to verify the miRNA/target relationship. Oligo-transfection, real­time PCR and western blot analysis were used to support the conclusions. We validated REL to be the direct gene via luciferase reporter assay system, and real­time PCR and western blot analysis were also conducted to study the mRNA and protein expression level of REL between different groups (recurrence and non­recurrence) or cells treated with scramble control, miR­574 mimics, REL siRNA and miR­574 inhibitors, indicating the negative regulatory relationship between miR­574 and REL. We also investigated the relative viability of prostate CSCs when transfected with scramble control, miR­574 mimics, REL siRNA and miR­574 inhibitors to validate miR­574 to be positively interfering with the viability of prostate CSCs. We then investigated the relative apoptosis of prostate CSCs when transfected with scramble control, miR­574 mimics, REL siRNA and miR­574 inhibitors. The results showed miR­574 inhibited apoptosis. In conclusion, miR­574 might be a novel prognostic and therapeutic target in the management of PCa recurrence.

Development of epidermal growth factor receptor tyrosine kinase inhibitors against EGFR T790M. Mutation in non small-cell lung carcinoma.

Individualized therapies targeting epidermal growth factor receptor (EGFR) mutations show promises for the treatment of non small-cell lung carcinoma (NSCLC). However, disease progression almost invariably occurs 1 year after tyrosine kinase inhibitor (TKI) treatment. The most prominent mechanism of acquired resistance involves the secondary EGFR mutation, namely EGFR T790M, which accounts for 50%-60% of resistant tumors. A large amount of studies have focused on the development of effective strategies to treat TKI-resistant EGFR T790M mutation in lung tumors. Novel generations of EGFR inhibitors are producing encouraging results in patients with acquired resistance against EGFR T790M mutation. This review will summarize the novel inhibitors, which might overcome resistance against EGFR T790M mutation.

[Effects of NaCl stress on photosynthesis characteristics and fast chlorophyll fluorescence induction dynamics of Pistacia chinensis leaves].

By using fast chlorophyll fluorescence induction dynamics analysis technique (JIP-test), this paper studied the photosynthesis characteristics and fast chlorophyll fluorescence induction dynamics of 1-year old Pistacia chinensis seedlings under the stress of NaCl at the concentrations 0% (CK), 0.15%, 0.3%, 0.45%, and 0.6%. With the increasing concentration of NaCl, the contents of Chl a, Chl b, and Chl (a+b) in the seedlings leaves decreased, the Chl a/b ratio decreased after an initial increase, and the carotenoid content increased. The net photosynthetic rate (P(n)) and stomatal conductance (g(s)) decreased gradually with increasing NaCl concentration. The decrease of P(n) was mainly attributed to the stomatal limitation when the NaCl concentration was lower than 0.3%, and to the non-stomatal limitation when the NaCl concentration was higher than 0.3%. The trapped energy flux per RC (TR0/CS0), electron transport flux per RC (ET0/CS0), density of RCs (RC/CS0), and yield or flux ratio (psi(0) or phi(E0)) decreased, but the absorption flux per CS (ABS/CS0) and the K phase (W(k)) and J phase (V) in the O-J-I-P chlorophyll fluorescence induction curves increased distinctly, indicating that NaCl stress damaged the leaf oxygen-evolving complex (OEC), donor sides, and PS II reaction centers. When the NaCl concentration reached 0.3%, the maximum photochemical efficiency (F(v)/F(m)) and performance index (PI(ABS)) decreased 17.7% and 36.6%, respectively, as compared with the control.

Thermodynamic modeling of ferric phosphate precipitation for phosphorus removal and recovery from wastewater.

Phosphorus removal and recovery by ferric phosphate (FePO(4) x 2 H(2)O) precipitation has been considered as an effective technology. In the present study, we examined chemical precipitation thermodynamic modeling of the PHREEQC program for phosphorus removal and recovery from wastewater. The objective of this research was to employ thermodynamic modeling to evaluate the effect of solution factors on FePO(4) x 2 H(2)O precipitation. In order to provide comparison, with the evaluation of thermodynamic modeling, the case study of phosphate removal from anaerobic supernatant was studied. The results indicated that the saturation-index (SI) of FePO(4) x 2 H(2)O followed a polynomial function of pH, and the solution pH influenced the ion activities of ferric iron salts and phosphate. The SI of FePO(4) x 2 H(2)O increased with a logarithmic function of Fe(3+):PO(4)(3-) molar ratio (Fe/P) and initial PO(4)(3-) concentration, respectively. Furthermore, the SI of FePO(4) x 2 H(2)O decreased with a logarithmic function of alkalinity and ionic strength, respectively. With an increase in temperature, the SI at pH 6.0 and 9.0 decreased with a linear function, and the SI at pH 4.0 followed a polynomial function. For the case study of phosphate removal from anaerobic supernatant, the phosphate removal trend at different pH and Fe/P was closer to the predictions of thermodynamic modeling. The results indicated that the thermodynamic modeling of FePO(4) x 2 H(2)O precipitation could be utilized to predict the technology parameters for phosphorus removal and recovery.