Search

Single-modal medical images contain limited disease-specific information. To analyze and diagnose patients, clinicians often need to integrate multiple modal images. However, due to limited medical resources and treatment time, it may be difficult to obtain multi-modal images. Cross-modal image reconstruction can generate medical images for clinical needs, thus assisting clinicians in accurately diagnosing and treating diseases. Traditional cross-modal reconstruction techniques have been applied in some clinical scenarios, but the quality of the reconstructed images needs further improvement. Generative adversarial network (GAN) can recover high-quality and complete image data from low-quality or incomplete medical image data, maximally savings medical equipment resources and accelerating medical treatment speed. This article summarizes the applications of GAN technology in cross-modal image reconstruction across X-ray imaging, computed tomography imaging, magnetic resonance imaging, and positron emission tomography imaging, to provide reference for the development of more advanced cross-modal reconstruction techniques.

Automatic and precise segmentation of lung images can assist doctors in locating and diagnosing lung lesions. However, current traditional lung CT image lesion segmentation algorithms suffer from the problem of low segmentation accuracy, while deep learning-based segmentation algorithms struggle to strike a better balance between lightweight and high accuracy. In response to this issue, a multi-scale and lightweight U-Net lung image segmentation algorithm with an attention mechanism is proposed. This algorithm introduces CA convolution after the convolution in the encoding stage to extract channel relationships and positional information from the feature maps. Furthermore, the RFB module is employed to extract features from different perspectives. Lastly, upward residual connections are introduced between the RFB modules in the encoder and decoder to enhance inter-network information interaction. Experiments conducted on the LUNA (lung nodule analysis) dataset and the COVID-QU-Ex dataset for COVID-19 pneumonia demonstrate that the proposed MSA-UNet algorithm achieves the best results in terms of Precision and Dice metrics. It outperforms mainstream models such as U-Net++ and DeeplabV3+ in terms of segmentation effectiveness and segmentation generality. The model has a floating-point operation count (FLOPs) of 18.15 G, a network parameter counts of 8.83×106, and achieves a Precision of 99.37%. The algorithm achieves a good balance between computational efficiency, model size, and segmentation accuracy. [ABSTRACT FROM AUTHOR]

In recent years, UNet and its derivative networks have gained widespread recognition as major methods of medical image segmentation. However, networks like UNet often struggle with Point-of-Care (POC) healthcare applications due to their high number of parameters and computational complexity. To tackle these challenges, this paper introduces an efficient network designed for medical image segmentation called MCU-Net, which leverages ConvNeXt to enhance UNet. 1) Based on ConvNeXt, MCU-Net proposes the MCU Block, which employs techniques such as large kernel convolution, depth-wise separable convolution, and an inverted bottleneck design. To ensure stable segmentation performance, it also integrates global response normalization (GRN) layers and Gaussian Error Linear Unit (GELU) activation functions. 2) Additionally, MCU-Net introduces an enhanced Multi-Scale Convolution Attention (MSCA) module after the original UNet's skip connections, emphasizing medical image features and capturing semantic insights across multiple scales. 3)The downsampling process replaces pooling layers with convolutions, and both upsampling and downsampling stages incorporate batch normalization (BN) layers to enhance model stability during training. The experimental results demonstrate that MCU-Net, with a parameter count of 2.19 million and computational complexity of 19.73 FLOPs, outperforms other segmentation models. The overall performance of MCU-Net in medical image segmentation surpasses that of other models, achieving a Dice score of 91.8% and mIoU of 84.7% on the GlaS dataset. When compared to UNet on the BUSI dataset, MCU-Net shows an improvement of 2% in Dice and 2.9% in mIoU. [ABSTRACT FROM AUTHOR]

Paired electrolysis in anion-exchange membrane (AEM) electrolyzers toward the cathodic nitrate reduction reaction (NO3RR) and anodic benzylamine oxidation reaction (BOR) could generate high value-added N-containing compounds simultaneously. The key challenge is to develop bifunctional electrocatalysts with a wide potential window, which can achieve highly efficient conversion of anode and cathode reactants. Herein, Ni3Se4 with Se vacancies was prepared and employed as the cathode and anode of AEM electrolyzers for NO3RR and BOR. 15N isotope-labeling online differential electrochemical mass spectrometry (DEMS) proved that ammonium was reduced from nitrates and revealed the reaction pathway of NO3RR. The density functional theory calculation clarified that Se vacancies regulate d-band centers, and then further modulate the adsorption energy of adsorbed hydrogen, NO3− and intermediates on the Ni3Se4-60s surface in NO3RR, so as to optimize the hydrogenation of NO3− into ammonia. Moreover, during the BOR, the Se vacancy can promote the adsorption of OH−, which is easier to form the active species of NiOOH. The technical and economic evaluation exhibited that the cost of paired electrolysis is 1.21 times lower and the profit is 1.42 times higher than that of the unpaired electrolysis, which shows the economic attraction of paired electrolysis. This work delivers the guidance for the design of efficient catalysts for paired electrolysis in AEM electrolyzer toward the sustainable synthesis of value-added chemicals. [ABSTRACT FROM AUTHOR]

Inspired by the design criteria of heteroditopic receptors for ion-pair binding, we herein describe a new strategy to construct a rotaxane transporter (RR[2]) for K+/Cl− co-transport. The use of a rigid axle improves the transport activity with an EC50 value of 0.58 μM, presenting a significant step toward developing rotaxane artificial channels. [ABSTRACT FROM AUTHOR]

Due to their excellent properties and unique structures, transition metal sulfides play an important role in the development of efficient and stable photoelectric catalysts. In recent years, their potential applications have expanded from photoelectric catalysis to energy storage, especially as materials for key components of electrochemical energy storage. As a typical multifunctional metal sulfide catalyst, Co9S8 is highly attractive due to its high conductivity, better stability, suitable band structure, enhanced performance and wide applications. A large number of studies have shown that strategically modified Co9S8-based materials have greater advantages in various applications compared with pure Co9S8. Therefore, this review will evaluate the physicochemical properties and the preparation of different dimensions of Co9S8-based materials, and the influence of different structures on the photoelectrochemical energy of materials will be described. In addition, the research progress regarding the evolution of hydrogen photocatalytic, electrocatalytic water splitting and various electrochemical energy storage materials will be emphasized. Finally, the challenges faced by Co9S8-based materials and the research directions for their future applications will be discussed. [ABSTRACT FROM AUTHOR]

Large‐scale uninform ZnO hexagonal nanorods were obtained by tuning the molar ratio of Mg2+ and Zn2+ without any organic surfactant or any further treatment, then the ZnO@ZnS heterojunction were obtained by in‐situ sulfidation method. The photocatalytic activity of as‐prepared photocatalyst sample was evaluated by their photocatalytic of Congo Red (CR) in a fixed‐bed microreactor and photocatalytic hydrogen production. The photocatalytic experiments showed that Z@ZS‐4 possesses higher photocatalytic performance for a sulfidation time up to 4 h. Probable photogenerated charge transfer mechanism has been proposed, and the corresponding photoluminescence and photoelectrochemical measurements revealed the higher charge transfer rate across the Z@ZS‐4 interface. [ABSTRACT FROM AUTHOR]

Sentiment classification aims to complete the automatic judgment task of text sentiment tendency. In the sentiment classification task of online reviews, traditional deep learning models require a large number of manually annotated samples of sentiment tendency for supervised training. Faced with massive online review data, the feasibility of manual tagging is worrisome. In addition, the traditional deep learning model ignores the imbalanced distribution of the number of classification samples, which will lead to a decline in classification performance in the practical application of the model. Considering that the online review data contains weak tagging information such as scores and labels, and the distribution is imbalanced, a weak tagging and imbalanced networks for online review sentiment classification is constructed. The experimental results show that the model significantly outperforms the traditional deep learning model in the sentiment classification task of hotel review data. [ABSTRACT FROM AUTHOR]

Transition metal chalcogenides are a promising and extremely pivotal class of electrocatalysts with potential applications in alkaline hydrogen evolution reaction (HER), especially, molybdenum diselenide. Although the exposed edge sites are generally considered to be the active sites of MoSe2 for HER, an intrinsic behavior (surface species evolution, structure/morphology conversion, stability) of MoSe2 electrode itself was not unveiled. Herein, the origin of MoSe2‐electrocatalyzed HER activity monitored by the quasi‐operando XPS and in situ Raman spectroscopy is presented. The findings clearly show dynamic evolution of both Mo and Se species on MoSe2 electrode surface for promoting HER activity and maintaining long‐term catalytic stability and reveal an electro‐oxidative dissolution and re‐adsorption mechanism. Theoretical calculations also corroborate these results. As expected, the addition of single or mixed MoO42− and SeO32− to the electrolyte of nickel foam directly verifies the critical role of surface‐adsorbed Mo and Se species for boosting HER activity and stability. Additionally, the oxidative dissolution of Se on NixSey electrode surface during HER is also observed, revealing the universality of oxidative dissolution of Se in transition metal selenides. This study provides a unique insight into the species evolution and surface structure transformation mechanism and activity improved origin of materials during the electroreduction process. [ABSTRACT FROM AUTHOR]

A distinct S-scheme heterojunction 0D/3D CeO2/Bi2O2CO3 photocatalyst was successfully synthesized by a hydrothermal method for the photocatalytic degradation of methylene blue (MB), tetracycline (TC) and aureomycin (AM). Compared with bare Bi2O2CO3 and CeO2, CeO2/Bi2O2CO3 possesses admirable photodegradation capacity. Additionally, the influence of the molar ratio of CeO2 in the compounds was also discussed, and the optimal molar ratio was identified as 15% (nCe/nBi), for which the photodegradation of MB reaches 98% in 120 min with light irradiation. Favorable retrogradation effects were achieved in the photodegradation of TC and AM. Furthermore, UV–vis diffuse reflectance spectroscopy revealed that the absorption range of solar illumination was successfully expanded to the visible light range for the CeO2/Bi2O2CO3 composites (with a molar ratio of 15%). Besides, based on photoelectrochemical detection, active species capture experiment and density functional theory (DFT), the constructed catalyst conforms to a step-scheme (S-scheme) heterojunction charge transfer mechanism. The satisfactory degradation activity and the outstanding solar light response performance benefit from the driving force in the space separation of photogenerated carriers, optimized energy band structure and high-quality redox capacity. It is speculated that the novel CeO2/Bi2O2CO3 composite would have broad application prospects in the degradation of organic contaminants. [ABSTRACT FROM AUTHOR]