Drug-Target Binding Affinity Prediction in a Continuous Latent Space Using Variational Autoencoders.

Accurate prediction of Drug-Target binding Affinity (DTA) is a daunting yet pivotal task in the sphere of drug discovery. Over the years, a plethora of deep learning-based DTA models have emerged, rendering promising results in predicting the binding affinities between drugs and their target proteins. However, in contrast to the conventional approach of modeling binding affinity in vector spaces, we propose a more nuanced modeling process in a continuous space to account for the diversity of input samples. Initially, the drug is encoded using the Simplified Molecular Input Line Entry System (SMILES), while the target sequences are characterized via a pretrained language model. Subsequently, highly correlative information is extracted utilizing residual gated convolutional neural networks. In a departure from existing deep learning-based models, our model learns the hidden representations of the drugs and targets jointly. Instead of employing two vectors, our hidden representations consist of two Gaussian distributions. To validate the effectiveness of our proposal, we conducted evaluations on commonly utilized benchmark datasets. The experimental outcomes corroborated that our method surpasses the state-of-the-art vectorial representation methods in terms of performance. This approach, therefore, offers potential enhancements in the precision of DTA predictions, potentially contributing to more efficient drug discovery processes.

MRI-Based Clinical-Imaging-Radiomics Nomogram Model for Discriminating Between Benign and Malignant Solid Pulmonary Nodules or Masses.

RATIONALE AND OBJECTIVES: Pulmonary nodules or masses are highly prevalent worldwide, and differential diagnosis of benign and malignant lesions remains difficult. Magnetic resonance imaging (MRI) can provide functional and metabolic information of pulmonary lesions. This study aimed to establish a nomogram model based on clinical features, imaging features, and multi-sequence MRI radiomics to identify benign and malignant solid pulmonary nodules or masses. MATERIALS AND METHODS: A total of 145 eligible patients (76 male; mean age, 58.4 years ± 13.7 [SD]) with solid pulmonary nodules or masses were retrospectively analyzed. The patients were randomized into two groups (training cohort, n = 102; validation cohort, n = 43). The nomogram was used for predicting malignant pulmonary lesions. The diagnostic performance of different models was evaluated by receiver operating characteristic (ROC) curve analysis. RESULTS: Of these patients, 95 patients were diagnosed with benign lesions and 50 with malignant lesions. Multivariate analysis showed that age, DWI value, LSR value, and ADC value were independent predictors of malignant lesions. Among the radiomics models, the multi-sequence MRI-based model (T1WI+T2WI+ADC) achieved the best diagnosis performance with AUCs of 0.858 (95%CI: 0.775, 0.919) and 0.774 (95%CI: 0.621, 0.887) for the training and validation cohorts, respectively. Combining multi-sequence radiomics, clinical and imaging features, the predictive efficacy of the clinical-imaging-radiomics model was significantly better than the clinical model, imaging model and radiomics model (all P < 0.05). CONCLUSION: The MRI-based clinical-imaging-radiomics model is helpful to differentiate benign and malignant solid pulmonary nodules or masses, and may be useful for precision medicine of pulmonary diseases.

3D Carbon Fiber Skeleton Film Modified with Gradient Cu Nanoparticles as Auxiliary Anode Regulates Dendrite-Free, Bottom-Up Zinc Deposition.

Achieving stable Zn plating/stripping under high current density and large area capacity remains a major challenge for metal Zn anodes. To address this issue, common filter paper is utilized to construct 3D carbon fiber skeleton film modified with gradient Cu nanoparticles (CFF@Cu). The original zincophobic hydrophilic CFF is transformed into gradient zincophilic and reversed gradient hydrophilic composite, due to the gradient distribution of Cu nanoparticles. When CFF@Cu is placed above Zn foil as an auxiliary anode, Zn foil anode exhibits stable, reversible, and dendrite-free Zn plating/stripping for 1200 h at 10 mA cm-2 and 2 mAh cm-2, 2000 h at 2 mA cm-2 and 2 mAh cm-2, 340 h at 10 mA cm-2 and 10 mAh cm-2. Additionally, nucleation barrier of Zn, Zn2+ transport and deposition kinetics are improved. The deposits on the Zn foil anode become homogeneous, dense, and fine. Side reactions and by-products are effectively inhibited. The excellent performance is mainly attributed to the gradient zincophilic field in 3D CFF. A portion of Zn2+ is captured by Cu and deposited within CFF@Cu from bottom to top, which reduces and homogenizes Zn2+ flux on Zn foil, as well as weakens and homogenizes electric field on Zn foil.

Confining Co1.11Te2 nanoparticles within mesoporous hollow carbon combination sphere for fast and ultralong sodium storage.

Co1.11Te2 nanoparticles are in-situ uniformly grown within mesoporous hollow carbon combination sphere (MHCCS@Co1.11Te2) using a hard-template and spray drying process, solution impregnation and pyrolysis tellurization. Material characterizations reveal that Co1.11Te2, with a diameter of âˆ¼ 20 nm, is attached to the internal walls of the unit spheres or embedded in the mesopore shells of the unit spheres, presenting a distinctive "ships-in-combination-bottles" nanoencapsulation structure. In sodium-ion half-cells, MHCCS@Co1.11Te2 exhibits excellent cycling stability, achieving reversible capacities of 257 mAh/g at 0.5 A/g after 250 cycles, 235 mAh/g at 1.0 A/g after 300 cycles and 161 mAh/g at 10.0 A/g after 1900 cycles. Electrochemical kinetic analyses and ex-situ characterizations reveal rapid electron/Na+ transport kinetics, prominent surface pseudocapacitive behavior, robust nanocomposite structure, and multi-step conversion reactions of sodium polytellurides. In sodium-ion full-cells, MHCCS@Co1.11Te2 still demonstrates stable cycling performance at 1.0 and 5.0 A/g and excellent rate capability. The superior electrochemical performance is associated with the nanoencapsulation structure based on mesoporous hollow carbon combination spheres, which promotes electron conduction and Na+ transport. The space-confined effect maintains the high electrochemical activity and cycling stability of Co1.11Te2.

Bismuth-Antimony Alloy Nanoparticles Embedded in 3D Hierarchical Porous Carbon Skeleton Film for Superior Sodium Storage.

A composite film that features bismuth-antimony alloy nanoparticles uniformly embedded in a 3D hierarchical porous carbon skeleton is synthesized by the polyacrylonitrile-spreading method. The dissolved polystyrene is used as a soft template. The average diameter of the bismuth-antimony alloy nanoparticles is ~34.5 nm. The content of the Bi-Sb alloy has an impact on the electrochemical performance of the composite film. When the content of the bismuth-antimony alloy is 45.27%, the reversible capacity and cycling stability of the composite film are the best. Importantly, the composite film outperforms the bismuth-antimony alloy nanoparticles embedded in dense carbon film and the cube carbon nanobox in terms of specific capacity, cycling stability, and rate capability. The composite film can provide a discharge capacity of 322 mAh g-1 after 500 cycles at 0.5 A g-1, 292 mAh g-1 after 500 cycles at 1 A g-1, and 185 mAh g-1 after 2000 cycles at 10 A g-1. The carbon film prepared by the spreading method presents a unique integrated composite structure that significantly improves the structural stability and electronic conductivity of Bi-Sb alloy nanoparticles. The 3D hierarchical porous carbon skeleton structure further enhances electrolyte accessibility, promotes Na+ transport, increases reaction kinetics, and buffers internal stress.

Nanocapsule of MnS Nanopolyhedron Core@CoS Nanoparticle/Carbon Shell@Pure Carbon Shell as Anode Material for High-Performance Lithium Storage.

MnS has been explored as an anode material for lithium-ion batteries due to its high theoretical capacity, but low electronic conductivity and severe volume change induce low reversible capacity and poor cycling performance. In this work, the nanocapsule consisting of MnS nanopolyhedrons confined in independent, closed and conductive hollow polyhedral nanospheres is prepared by embedding MnCO3 nanopolyhedrons into ZIF-67, followed by coating of RF resin and gaseous sulfurization/carbonization. Benefiting from the unique nanocapsule structure, especially inner CoS/C shell and outer pure C shell, the MnS@CoS/C@C composite as anode material presents excellent cycling performance (674 mAh g-1 at 1 A g-1 after 300 cycles; 481 mAh g-1 at 5 A g-1 after 300 cycles) and superior rate capability (1133.3 and 650.6 mAh g-1 at 0.1 and 4 A g-1), compared to the control materials (MnS and MnS@CoS/C) and other MnS composites. Kinetics measurements further reveal a high proportion of the capacitive effect and low reaction impedance of MnS@CoS/C@C. SEM and TEM observation on the cycled electrode confirms superior structural stability of MnS@CoS/C@C during long-term cycles. Excellent lithium storage performance and the convenient synthesis strategy demonstrates that the MnS@CoS/C@C nanocapsule is a promising high-performance anode material.

Mechanical Stretch Promotes Macrophage Polarization and Inflammation via the RhoA-ROCK/NF-κB Pathway.

Macrophages play an essential role in the pathogenesis of most inflammatory diseases. Recent studies have shown that mechanical load can influence macrophage function, leading to excessive and uncontrolled inflammation and even systemic damage, including cardiovascular disease and knee osteoarthritis. However, the molecular mechanism remains unclear. In this study, murine RAW264.7 cells were treated with mechanical stretch (MS) using the Flexcell-5000T Tension System. The expression of inflammatory factors and cytokine release were measured by RT-qPCR, ELISA, and Western blotting. The protein expression of NF-κB p65, Iκb-α, p-Iκb-α, RhoA, ROCK1, and ROCK2 was also detected by Western blotting. Then, Flow cytometry was used to detect the proportion of macrophage subsets. Meanwhile, Y-27632 dihydrochloride, a ROCK inhibitor, was added to knockdown ROCK signal transduction in cells. Our results demonstrated that MS upregulated mRNA expression and increased the secretion levels of proinflammatory factors iNOS, IL-1ß, TNF-α, and IL-6. Additionally, MS significantly increased the proportion of CD11b+CD86+ and CD11b+CD206+ subsets in RAW264.7 macrophages. Furthermore, the protein expression of RhoA, ROCK1, ROCK2, NF-κB p65, and IκB-α increased in MS-treated RAW264.7 cells, as well as the IL-6 and iNOS. In contrast, ROCK inhibitor significantly blocked the activation of RhoA-ROCK and NF-κB pathway, decreased the protein expression of IL-6 and iNOS, reduced the proportion of CD11b+CD86+ cells subpopulation, and increased the proportion of CD11b+CD206+ cell subpopulation after MS. These data indicate that mechanical stretch can regulate the RAW264.7 macrophage polarization and enhance inflammatory responses in vitro, which may contribute to activation the RhoA-ROCK/NF-κB pathway.

Comparison of the performance of MS enteroscope series and Japanese double- and single-balloon enteroscopes.

BACKGROUND: Small intestine disease endangers human health and is not easy to locate and diagnose. AIM: To observe the effect of the MS series of small intestine endoscopes on the gastrointestinal tract, the changes in serum gastrin levels and intestinal tissue, and the time required for the examination. METHODS: In vivo experiments in 20 Living pigs were conducted, Bowel preparation was routinely performed, Intravenous anesthesia with propofol and ketamine was applied, the condition of the small intestine was observed and the detection time of the MS series of small intestine endoscopes were recorded, The changes in intestinal tissue using the MS series of small intestine endoscopes observed and compared before and after the examination, Venous blood (3-5 mL) from pigs was collected before and after the experiment; changes in intestinal tissue after use of the MS series of small intestine endoscopes observed after examination. After completion of each type of small intestine endoscope experiment, the pigs were allowed to rest and the next type of small intestine endoscope experiment was performed after 15 days of normal feeding. The detection time data of the single-balloon small intestine endoscope and double-balloon small intestine endoscope were collected from four hospitals. RESULTS: One case of Ascarislumbricoides, one of suspected Crohn's disease, one small intestinal diverticulum and one anesthesia accident were observed in pigs. The small intestine showed no differences in the MS series of small intestine endoscopes and there were no differences in serum gastrin between the groups (P > 0.05). The time required for inspection was recorded, and the overall detection time for the Japanese small intestine endoscopes was approximately 1.68 ± 0.16 h. CONCLUSION: Intestinal ascariasis is a common disease in pigs. Some pigs have abnormal intestinal variation. After continuous upgrade and improvement, the MS-3 and MS-4 small intestine endoscope appear superior in terms of detection time.

Generalizable Beat-by-Beat Arrhythmia Detection by Using Weakly Supervised Deep Learning.

Beat-by-beat arrhythmia detection in ambulatory electrocardiogram (ECG) monitoring is critical for the evaluation and prognosis of cardiac arrhythmias, however, it is a highly professional demanding and time-consuming task. Current methods for automatic beat-by-beat arrhythmia detection suffer from poor generalization ability due to the lack of large-sample and finely-annotated (labels are given to each beat) ECG data for model training. In this work, we propose a weakly supervised deep learning framework for arrhythmia detection (WSDL-AD), which permits training a fine-grained (beat-by-beat) arrhythmia detector with the use of large amounts of coarsely annotated ECG data (labels are given to each recording) to improve the generalization ability. In this framework, heartbeat classification and recording classification are integrated into a deep neural network for end-to-end training with only recording labels. Several techniques, including knowledge-based features, masked aggregation, and supervised pre-training, are proposed to improve the accuracy and stability of the heartbeat classification under weak supervision. The developed WSDL-AD model is trained for the detection of ventricular ectopic beats (VEB) and supraventricular ectopic beats (SVEB) on five large-sample and coarsely-annotated datasets and the model performance is evaluated on three independent benchmarks according to the recommendations from the Association for the Advancement of Medical Instrumentation (AAMI). The experimental results show that our method improves the F 1 score of supraventricular ectopic beats detection by 8%-290% and the F1 of ventricular ectopic beats detection by 4%-11% on the benchmarks compared with the state-of-the-art methods of supervised learning. It demonstrates that the WSDL-AD framework can leverage the abundant coarsely-labeled data to achieve a better generalization ability than previous methods while retaining fine detection granularity. Therefore, this framework has a great potential to be used in clinical and telehealth applications. The source code is available at https://github.com/sdnjly/WSDL-AD.

Inter-subject registration-based one-shot segmentation with alternating union network for cardiac MRI images.

Medical image segmentation based on deep-learning networks makes great progress in assisting disease diagnosis. However, currently, the training of most networks still requires a large amount of data with labels. In reality, labeling a considerable number of medical images is challenging and time-consuming. In order to tackle this challenge, a new one-shot segmentation framework for cardiac MRI images based on an inter-subject registration model called Alternating Union Network (AUN) is proposed in this study. The label of the source image is warped with deformation fields discovered from AUN to segment target images directly. Initially, the volumes are pre-processed by aligning affinely and adjusting the global intensity to simplify subsequent deformation registration. AUN consists of two kinds of subnetworks trained alternately to optimize segmentation gradually. The first kind of subnetwork takes a pair of volumes as inputs and registers them using global intensity similarity. The second kind of subnetwork, which takes the predicted labels generated from the previous subnetwork and the labels refined using the information of intrinsic anatomical structures of interest as inputs, is intensity-independent and focuses attention on registering structures of interest. Specifically, the input of AUN is a pair of a labeled image with the texture in regions of interest removed and a target image. Additionally, a new similarity measurement more appropriate for registering such image pair is defined as Local Squared Error (LSE). The proposed registration-based one-shot segmentation pays attention to the problem of the lack of labeled medical images. In AUN, only one labeled volume is required and a large number of unlabeled ones can be leveraged to improve segmentation performance, which has great advantages in clinical application. In addition, the intensity-independent subnetwork and LSE proposed in this study empower the framework to segment medical images with complicated intensity distribution.

Constructing zigzag-like hollow mesoporous nanospheres MoO2/C with superior lithium storage performance.

Hollow mesoporous nanospheres MoO2/C are successfully constructed through metal chelating reaction between molybdenum acetylacetone and glycerol as well as the Kirkendall effect induced by diammonium hydrogen phosphate. MoO2nanoparticles coupled by amorphous carbon are assembled to unique zigzag-like hollow mesoporous nanosphere with large specific surface area of 147.7 m2g-1and main pore size of 8.7 nm. The content of carbon is 9.1%. As anode material for lithium-ion batteries, the composite shows high specific capacity and excellent cycling performance. At 0.2 A g-1, average discharge capacity stabilizes at 1092 mAh g-1. At 1 A g-1after 700 cycles, the discharge capacity still reaches 512 mAh g-1. Impressively, the composite preserves intact after 700 cycles. Even at 5 A g-1, the discharge capacity can reach 321 mAh g-1, exhibiting superior rate capability. Various kinetics analyses demonstrate that in electrochemical reaction, the proportion of the surface capacitive effect is higher, and the composite has relatively high diffusion coefficient of Li ions and fast faradic reaction kinetics. Excellent lithium storge performance is attributed to the synergistic effect of zigzag-like hollow mesoporous nanosphere and amorphous carbon, which improves reaction kinetics, structure stability and electronic conductivity of MoO2. The present work provides a new useful structure design strategy for advanced energy storage application of MoO2.

Automatic Multi-Label ECG Classification with Category Imbalance and Cost-Sensitive Thresholding.

Automatic electrocardiogram (ECG) classification is a promising technology for the early screening and follow-up management of cardiovascular diseases. It is, by nature, a multi-label classification task owing to the coexistence of different kinds of diseases, and is challenging due to the large number of possible label combinations and the imbalance among categories. Furthermore, the task of multi-label ECG classification is cost-sensitive, a fact that has usually been ignored in previous studies on the development of the model. To address these problems, in this work, we propose a novel deep learning model-based learning framework and a thresholding method, namely category imbalance and cost-sensitive thresholding (CICST), to incorporate prior knowledge about classification costs and the characteristic of category imbalance in designing a multi-label ECG classifier. The learning framework combines a residual convolutional network with a class-wise attention mechanism. We evaluate our method with a cost-sensitive metric on multiple realistic datasets. The results show that CICST achieved a cost-sensitive metric score of 0.641 ± 0.009 in a 5-fold cross-validation, outperforming other commonly used thresholding methods, including rank-based thresholding, proportion-based thresholding, and fixed thresholding. This demonstrates that, by taking into account the category imbalance and predefined cost information, our approach is effective in improving the performance and practicability of multi-label ECG classification models.

Octahedral Shaped PbTiO3-TiO2 Nanocomposites for High-Efficiency Photocatalytic Hydrogen Production.

In this work, octahedral shaped PbTiO3-TiO2 nanocomposites have been synthesized by a facile hydrothermal method, where perovskite ferroelectric PbTiO3 nanooctahedra were employed as substrate. The microstructures of the composites were investigated systemically by using XRD, SEM, TEM and UV-Vis spectroscopy. It was revealed that anantase TiO2 nanocrystals with a size of about 5 nm are dispersed on the surface of the {111} facets of the nanooctahedron crystals. Photocatalytic hydrogen production of the nanocomposites has been evaluated in a methanol alcohol-water solution under UV light enhanced irradiation. The H2 evolution rate of the nanocomposites increased with an increased loading of TiO2 on the nanooctahedra. The highest H2 evolution rate was 630.51 µmol/h with the highest concentration of TiO2 prepared with 2 mL tetrabutyl titanate, which was about 36 times higher than that of the octahedron substrate. The enhanced photocatalytic reactivity of the nanocomposites is possibly ascribed to the UV light absorption of the nanooctahedral substrates, efficient separation of photo-generated carriers via the interface and the reaction on the surface of the TiO2 nanocrystals.

TRIM21 negatively regulates Corynebacterium pseudotuberculosis-induced inflammation and is critical for the survival of C. pseudotuberculosis infected C57BL6 mice.

Corynebacterium pseudotuberculosis, a facultative intracellular bacterium, is an important zoonotic pathogen responsible for chronic inflammatory diseases. TRIM21, an E3 ubiquitin-protein ligase, plays pivotal roles in inflammation regulation. However, its role during C. pseudotuberculosis infection is unclear. Here, we found that TRIM21 expression was significantly increased in C. pseudotuberculosis-infected macrophages. Following infection by C. pseudotuberculosis, we observed a significantly higher number of bacteria and a higher degree of LDH release from Trim21-/- macrophages compared to wild-type (WT) macrophages, suggesting that TRIM21 limits C. pseudotuberculosis replication in macrophages and protects the infected cells from death. Further in vivo experiments showed a significantly higher mortality, higher bacterial load, much more severe abscess formation, and lesions in the organs of C. pseudotuberculosis-infected Trim21-/- mice compared to those of the infected WT mice, suggesting that TRIM21 plays critical roles in protecting against C. pseudotuberculosis infection. Moreover, the secretory levels of IL-1α, IL-1ß, IL-6, and TNF-α were significantly higher in C. pseudotuberculosis-infected Trim21-/- macrophages compared to infected WT macrophages; the levels of these cytokines were also higher in the sera, organs, and ascites of C. pseudotuberculosis-infected Trim21-/- mice compared to infected WT mice. These findings suggest that TRIM21 negatively regulates the secretion of pro-inflammatory cytokines in macrophages, sera, organs, and ascites of mice following C. pseudotuberculosis infection. Collectively, the present study demonstrates that TRIM21 plays a vital role in preventing C. pseudotuberculosis infection, which may be related to the negative regulation of pro-inflammatory cytokines production by TRIM21 during this pathogen infection.

Effects of long-term fasting and confinement on the cardiovascular activity.

Fasting has been demonstrated to improve health and slow aging in human and other species; however, its impact on the human body in the confined environment is still unclear. This work studies the effects of long-term fasting and confined environment on the cardiovascular activities of human via a 10-day fasting experiment with two groups of subjects being in confined (6 subjects) and unconfined (7 subjects) environments respectively and undergoing the same four-stage fasting/feeding process. It is found that the confinement has significant influences on the autonomic regulation to the heart rate during the fasting process by altering the activity of the parasympathetic nervous system, which is manifested by the significant higher pNN50, rMSSD, and Ln-HF of heart rate variability (HRV) (p < 0.05) and slower heart rate (p < 0.01) in the confined group than that in the unconfined group. Furthermore, the long-term fasting induces a series of changes in both groups, including reduced level of serum sodium (p < 0.01), increased the serum calcium (p < 0.05), prolonged QTc intervals (p < 0.05), and reduced systolic blood pressures (p < 0.05). These effects are potentially negative to human health and therefore need to be treated with caution. Study of the effects of fasting and confinement on the cardiovascular activities.

Automatic Detection of QRS Complexes Using Dual Channels Based on U-Net and Bidirectional Long Short-Term Memory.

OBJECTIVE: Detecting changes in the QRS complexes in ECG signals is regarded as a straightforward, noninvasive, inexpensive, and preliminary diagnosis approach for evaluating the cardiac health of patients. Therefore, detecting QRS complexes in ECG signals must be accurate over short times. However, the reliability of automatic QRS detection is restricted by all kinds of noise and complex signal morphologies. The objective of this paper is to address automatic detection of QRS complexes. METHODS: In this paper, we proposed a new algorithm for automatic detection of QRS complexes using dual channels based on U-Net and bidirectional long short-term memory. First, a proposed preprocessor with mean filtering and discrete wavelet transform was initially applied to remove different types of noise. Next the signal was transformed and annotations were relabeled. Finally, a method combining U-Net and bidirectional long short-term memory with dual channels was used for the automatic detection of QRS complexes. RESULTS: The proposed algorithm was trained and tested using 44 ECG records from the MIT-BIH arrhythmia database and CPSC2019 dataset, which achieved 99.06% and 95.13% for sensitivity, 99.22% and 82.03% for positive predictivity, and 98.29% and 78.73% accuracy on the two datasets respectively. CONCLUSION: Experimental results prove that the proposed method may be useful for automatic detection of QRS complex task. SIGNIFICANCE: The proposed method not only has application potential for QRS complex detecting for large ECG data, but also can be extended to other medical signal research fields.

Three-Dimensional Liver Image Segmentation Using Generative Adversarial Networks Based on Feature Restoration.

Medical imaging provides a powerful tool for medical diagnosis. In the process of computer-aided diagnosis and treatment of liver cancer based on medical imaging, accurate segmentation of liver region from abdominal CT images is an important step. However, due to defects of liver tissue and limitations of CT imaging procession, the gray level of liver region in CT image is heterogeneous, and the boundary between the liver and those of adjacent tissues and organs is blurred, which makes the liver segmentation an extremely difficult task. In this study, aiming at solving the problem of low segmentation accuracy of the original 3D U-Net network, an improved network based on the three-dimensional (3D) U-Net, is proposed. Moreover, in order to solve the problem of insufficient training data caused by the difficulty of acquiring labeled 3D data, an improved 3D U-Net network is embedded into the framework of generative adversarial networks (GAN), which establishes a semi-supervised 3D liver segmentation optimization algorithm. Finally, considering the problem of poor quality of 3D abdominal fake images generated by utilizing random noise as input, deep convolutional neural networks (DCNN) based on feature restoration method is designed to generate more realistic fake images. By testing the proposed algorithm on the LiTS-2017 and KiTS19 dataset, experimental results show that the proposed semi-supervised 3D liver segmentation method can greatly improve the segmentation performance of liver, with a Dice score of 0.9424 outperforming other methods.

Heart failure-induced atrial remodelling promotes electrical and conduction alternans.

Heart failure (HF) is associated with an increased propensity for atrial fibrillation (AF), causing higher mortality than AF or HF alone. It is hypothesized that HF-induced remodelling of atrial cellular and tissue properties promotes the genesis of atrial action potential (AP) alternans and conduction alternans that perpetuate AF. However, the mechanism underlying the increased susceptibility to atrial alternans in HF remains incompletely elucidated. In this study, we investigated the effects of how HF-induced atrial cellular electrophysiological (with prolonged AP duration) and tissue structural (reduced cell-to-cell coupling caused by atrial fibrosis) remodelling can have an effect on the generation of atrial AP alternans and their conduction at the cellular and one-dimensional (1D) tissue levels. Simulation results showed that HF-induced atrial electrical remodelling prolonged AP duration, which was accompanied by an increased sarcoplasmic reticulum (SR) Ca2+ content and Ca2+ transient amplitude. Further analysis demonstrated that HF-induced atrial electrical remodelling increased susceptibility to atrial alternans mainly due to the increased sarcoplasmic reticulum Ca2+-ATPase (SERCA) Ca2+ reuptake, modulated by increased phospholamban (PLB) phosphorylation, and the decreased transient outward K+ current (Ito). The underlying mechanism has been suggested that the increased SR Ca2+ content and prolonged AP did not fully recover to their previous levels at the end of diastole, resulting in a smaller SR Ca2+ release and AP in the next beat. These produced Ca2+ transient alternans and AP alternans, and further caused AP alternans and Ca2+ transient alternans through Ca2+→AP coupling and AP→Ca2+ coupling, respectively. Simulation of a 1D tissue model showed that the combined action of HF-induced ion channel remodelling and a decrease in cell-to-cell coupling due to fibrosis increased the heart tissue's susceptibility to the formation of spatially discordant alternans, resulting in an increased functional AP propagation dispersion, which is pro-arrhythmic. These findings provide insights into how HF promotes atrial arrhythmia in association with atrial alternans.

A Novel Approach to Predict Wrinkling of Aluminum Alloy During Warm/Hot Sheet Hydroforming Based on an Improved Yoshida Buckling Test.

In order to predict the wrinkling of sheet metal under the influence of fluid pressure and temperature during warm/hot hydroforming, a numerical simulation model for sheet wrinkling prediction was established, taking into account through-thickness normal stress induced by fluid pressure. From simulations using linear and quadratic elements, respectively, it was found that the latter gave results that were much closer to experimental data. A novel experimental method based on an improved Yoshida Buckling Test (YBT) was proposed for testing the wrinkling properties of sheets under the through-thickness normal stress. A wrinkling coefficient suitable for predicting wrinkling was also presented. Based on the numerical simulations, an experimental validation of wrinkling performance was conducted. Ridge-height curves measured along the main diagonal tensile direction of the sheet were presented and showed that the wrinkling prediction criterion provided good discrimination. Furthermore, the wrinkling properties of several different materials were simulated to evaluate the accuracy of the prediction method, and the results revealed that the improved YBT gave good predictions for wrinkling in the conventional sheet metal forming process, while the prediction results for wrinkling in warm/hot sheet hydroforming were also accurate with the fluid pressure of zero.

Accurate Pelvis and Femur Segmentation in Hip CT With a Novel Patch-Based Refinement.

Due to bone deformation and joint space narrowing in diseased hips, accurate segmentation for pelvis, and femur from hip computed tomography (CT) images remains a challenging task. Therefore, the paper presents a fully automatic segmentation framework for the pelvis and femur in both of healthy and diseased hips. The framework involves three steps: preprocessing, coarse segmentation, and refinement. It starts with a preprocessing procedure to extract the volume of interest (VOI) from original CT images. Then, a coarse segmentation of bone has been obtained by classifying the VOI as bone and nonbone parts based on conditional random field (CRF) model. Finally, the bone is further divided into the pelvis and femur using a patch-based refinement method. The innovation of this study is the novel patch-based refinement method that is particularly suitable for diseased hips. The refinement method starts from the boundary of coarse segmentation, and propagates to the neighbors only when the label is not consistent with the label of CRF-based classification, it increases the reliability of segmentation for diseased hips with bone deformation. We incorporate neighborhood information to label fusion so that final label estimation is more accurate and robust for diseased hips with joint space narrowing. In total, 60 CT data sets, which included 78 healthy hemi-hips and 42 diseased hemi-hips, were used, and three-fold cross validations were carried out. Compared to two state-of-the-art methods, our method achieved significantly increased segmentation accuracy for the diseased hemi-hips, and is, therefore, more suited for automatic segmentation of diseased hips.