Machine Learning-Aided Discovery of Low-Pt High Entropy Intermetallic Compounds for Electrochemical Oxygen Reduction Reaction.

Advancing the design of cathode catalysts to significantly maximize platinum utilization and augment the longevity has emerged as a formidable challenge in the field of fuel cells. Herein, we rationally design a high entropy intermetallic compound (HEIC, Pt(FeCoNiCu)3) for catalyzing oxygen reduction reaction (ORR) by an efficient machine learning stategy, where crystal graph convolutional neural networks are employed to expedite the multicomponent design. Based on a dataset generated from first-principles calculations, the model can achieve a high prediction accuracy with mean absolute errors of 0.003 for surface strain and 0.011 eV atom-1 for formation energy. In addition, we identify two chemical features (atomic size difference and mixing enthalpy) as new descriptors to explore advanced ORR catalysts. The carbon supported Pt(FeCoNiCu)3 catalyst with small particle size is successfully synthesized by a freeze-drying-annealing technology, and exhibits ultrahigh mass activity (4.09 A mgPt-1) and specific activity (7.92 mA cm-2). Meanwhile, The catalyst also shows significantly enhanced electrochemical stability which can be ascribed to the sluggish difussion effect in the HEIC structure. Beyond offering a promising low-Pt electrocatalysts for fuel cell cathode, this work offers a new paradigm to rationally design advanced catalysts for energy storage and conversion devices.

Geometry-Aware Attenuation Learning for Sparse-View CBCT Reconstruction.

Cone Beam Computed Tomography (CBCT) plays a vital role in clinical imaging. Traditional methods typically require hundreds of 2D X-ray projections to reconstruct a high-quality 3D CBCT image, leading to considerable radiation exposure. This has led to a growing interest in sparse-view CBCT reconstruction to reduce radiation doses. While recent advances, including deep learning and neural rendering algorithms, have made strides in this area, these methods either produce unsatisfactory results or suffer from time inefficiency of individual optimization. In this paper, we introduce a novel geometry-aware encoder-decoder framework to solve this problem. Our framework starts by encoding multi-view 2D features from various 2D X-ray projections with a 2D CNN encoder. Leveraging the geometry of CBCT scanning, it then back-projects the multi-view 2D features into the 3D space to formulate a comprehensive volumetric feature map, followed by a 3D CNN decoder to recover 3D CBCT image. Importantly, our approach respects the geometric relationship between 3D CBCT image and its 2D X-ray projections during feature back projection stage, and enjoys the prior knowledge learned from the data population. This ensures its adaptability in dealing with extremely sparse view inputs without individual training, such as scenarios with only 5 or 10 X-ray projections. Extensive evaluations on two simulated datasets and one real-world dataset demonstrate exceptional reconstruction quality and time efficiency of our method.

[Accuracy of tooth segmentation algorithm based on deep learning].

PURPOSE: The established automatic AI tooth segmentation algorithm was used to achieve rapid and automatic tooth segmentation from CBCT images. The three-dimensional data obtained by oral scanning of real isolated teeth were used as the gold standard to verify the accuracy of the algorithm. METHODS: Thirty sets of CBCT data and corresponding 59 isolated teeth were collected from Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine. The three-dimensional tooth data in CBCT images were segmented by the algorithm. The digital information obtained by scanning the extracted teeth after processing was used as the gold standard. In order to compare the difference between the segmentation results and the scanning results of the algorithm. The Dice coefficient(Dice), sensitivity (Sen) and average symmetric surface distance (ASSD) were selected to evaluate the segmentation accuracy of the algorithm. The intra-class correlation coefficient(ICC) was used to evaluate the differences in length, area, and volume between the single tooth obtained by the AI system and the digital isolated tooth. Due to the existence of CBCT with different resolution, ANOVA was used to analyze the differences between groups with different resolution, and SNK method was used to compare them between two groups. SPSS 25.0 software package was used to analyze the data. RESULTS: After comparing the segmentation results with the in vitro dental scanning results, the average Dice value was (94.7±1.88)%, the average Sen was (95.8±2.02)%, and the average ASSD was (0.49±0.12) mm. By comparing the length, area and volume of a single tooth obtained by the digital isolated tooth and the AI system, the ICC values of the intra-group correlation coefficients were 0.734, 0.719 and 0.885, respectively. The single tooth divided by the AI system has a good consistency with the digital model in evaluating the length, area and volume, but the segmentation results were still different from the real situation in terms of specific values. The smaller the voxel of CBCT, the higher the resolution, the better the segmentation results. CONCLUSIONS: The CBCT tooth segmentation algorithm established in this study can accurately achieve the tooth segmentation of the whole dentition in CBCT at all resolutions. The improvement of CBCT resolution ratio can make the algorithm more accurate. Compared with the current segmentation algorithms, our algorithm has better performance. Compared with the real situation, there are still some differences, and the algorithm needs to be further improved and verified.

Integrating Eye Tracking with Grouped Fusion Networks for Semantic Segmentation on Mammogram Images.

Medical image segmentation has seen great progress in recent years, largely due to the development of deep neural networks. However, unlike in computer vision, high-quality clinical data is relatively scarce, and the annotation process is often a burden for clinicians. As a result, the scarcity of medical data limits the performance of existing medical image segmentation models. In this paper, we propose a novel framework that integrates eye tracking information from experienced radiologists during the screening process to improve the performance of deep neural networks with limited data. Our approach, a grouped hierarchical network, guides the network to learn from its faults by using gaze information as weak supervision. We demonstrate the effectiveness of our framework on mammogram images, particularly for handling segmentation classes with large scale differences.We evaluate the impact of gaze information on medical image segmentation tasks and show that our method achieves better segmentation performance compared to state-of-the-art models. A robustness study is conducted to investigate the influence of distraction or inaccuracies in gaze collection. We also develop a convenient system for collecting gaze data without interrupting the normal clinical workflow. Our work offers novel insights into the potential benefits of integrating gaze information into medical image segmentation tasks.

Robust and smooth Couinaud segmentation via anatomical structure-guided point-voxel network.

Precise Couinaud segmentation from preoperative liver computed tomography (CT) is crucial for surgical planning and lesion examination. However, this task is challenging as it is defined based on vessel structures, and there is no intensity contrast between adjacent Couinaud segments in CT images. To solve this challenge, we design a multi-scale point-voxel fusion framework, which can more effectively model the spatial relationship of points and the semantic information of the image, producing robust and smooth Couinaud segmentations. Specifically, we first segment the liver and vessels from the CT image and generate 3D liver point clouds and voxel grids embedded with the vessel structure. Then, our method with two input-specific branches extracts complementary feature representations from points and voxels, respectively. The local attention module adaptively fuses features from the two branches at different scales to balance the contribution of different branches in learning more discriminative features. Furthermore, we propose a novel distance loss at the feature level to make the features in the segment more compact, thereby improving the certainty of segmentation between segments. Our experimental results on three public liver datasets demonstrate that our proposed method outperforms several state-of-the-art methods by large margins. Specifically, in out-of-distribution (OOD) testing of LiTS dataset, our method exceeded the voxel-based 3D UNet by approximately 20% in Dice score, and outperformed the point-based PointNet2Plus by approximately 8% in Dice score. Our code and manual annotations of the public datasets presented in this paper are available online: https://github.com/xukun-zhang/Couinaud-Segmentation.

Sieving-type Electric Double Layer with Hydrogen Bond Interlocking to Stable Zinc Metal Anode.

The stability of aqueous zinc metal batteries is significantly affected by side reactions and dendrite growth on the anode interface, which primarily originate from water and anions. Herein, we introduce a multi H-bond site additive, 2, 2'-Sulfonyldiethanol (SDE), into an aqueous electrolyte to construct a sieving-type electric double layer (EDL) by hydrogen bond interlock in order to address these issues. On the one hand, SDE replaces H2O and SO4 2- anions that are adsorbed on the zinc anode surface, expelling H2O/SO4 2- from the EDL and thereby reducing the content of H2O/SO4 2- at the interface. On the other hand, when Zn2+ are de-solvated at the interface during the plating, the strong hydrogen bond interaction between SDE and H2O/SO4 2- can trap H2O/SO4 2- from the EDL, further decreasing their content at the interface. This effectively sieves them out of the zinc anode interface and inhibits the side reactions. Moreover, the unique characteristics of trapped SO4 2- anions can restrict their diffusion, thereby enhancing the transference number of Zn2+ and promoting dendrite-free deposition and growth of Zn. Consequently, utilizing an SDE/ZnSO4 electrolyte enables excellent cycling stability in Zn//Zn symmetrical cells and Zn//MnO2 full cells with lifespans exceeding 3500 h and 2500 cycles respectively.

Postoperative facial prediction for mandibular defect based on surface mesh deformation.

OBJECTIVES: This study aims to introduce a novel predictive model for the post-operative facial contours of patients with mandibular defect, addressing limitations in current methodologies that fail to preserve geometric features and lack interpretability. METHODS: Utilizing surface mesh theory and deep learning, our model diverges from traditional point cloud approaches by employing surface triangular mesh grids. We extract latent variables using a Mesh Convolutional Restricted Boltzmann Machines (MCRBM) model to generate a three-dimensional deformation field, aiming to enhance geometric information preservation and interpretability. RESULTS: Experimental evaluations of our model demonstrate a prediction accuracy of 91.2 %, which represents a significant improvement over traditional machine learning-based methods. CONCLUSIONS: The proposed model offers a promising new tool for pre-operative planning in oral and maxillofacial surgery. It significantly enhances the accuracy of post-operative facial contour predictions for mandibular defect reconstructions, providing substantial advancements over previous approaches.

Extracellular vesicles loaded with ApoB-100 protein affect the occurrence of coronary heart disease in patients after injury of spinal cord.

Spinal cord injury (SCI) patients have an increased susceptibility to coronary heart disease (CHD) due to dysregulated lipid deposition. We conducted a comprehensive investigation to gain insights into the specific roles of Apolipoprotein B-100 (APOB-100) in the development of CHD in patients suffering from SCI. First, we established an SCI rat model through semitransection. APOB-100 expression in plasma exosomes obtained from patients were determined. Subsequently, we found APOB-100 affected macrophage polarization when treating co-cultured neurons/macrophages lacking Sortilin with extracellular vesicles derived from SCI rats, where APOB-100 co-immunoprecipitated with Sortilin. Moreover, APOB-100 upregulation reduced neuronal cell viability and triggered apoptosis by upregulating Sortilin, leading to a decline in the Basso, Beattie, and Bresnahan (BBB) scale, exacerbation of neuron injury, increased macrophage infiltration, and elevated blood lipid-related indicators in SCI rats, which could be reversed by silencing Sortilin. In conclusion, APOB-100 from post-SCI patients' extracellular vesicles upregulates Sortilin, thereby endangering those patients to CHD.

MiR-184-3p in the paraventricular nucleus participates in the neurobiology of depression via regulation of the hypothalamus-pituitary-adrenal axis.

Hyperactivity of the hypothalamic-pituitary-adrenal (HPA) axis during chronic stress is essential for the pathogenesis of depression, and increased activity of cAMP response element binding protein (CREB)-regulated transcription co-activator 1 (CRTC1) in the paraventricular nucleus (PVN) plays a critical role. As a well-investigated microRNA (miRNA), miR-184 has two forms, miR-184-3p and miR-184-5p. Recently, miRNAs target genes predictive analysis and dual-luciferase reporter assays identified an inhibitory role of miR-184-3p on CRTC1 expression. Therefore, we speculated that miR-184-3p regulation was responsible for the effects of chronic stress on CRTC1 in the PVN. Various methods, including the chronic social defeat stress (CSDS) model of depression, behavioral tests, Western blotting, co-immunoprecipitation (Co-IP), quantitative real-time reverse transcription PCR (qRT-PCR), immunofluorescence, and adeno-associated virus (AAV)-mediated gene transfer, were used. CSDS evidently downregulated the level of miR-184-3p, but not miR-184-5p, in the PVN. Genetic knockdown and pharmacological inhibition of miR-184-3p in the PVN induced various depressive-like symptoms (e.g., abnormal behaviors, HPA hyperactivity, enhanced CRTC1 function in PVN neurons, downregulation of hippocampal neurogenesis, and decreased brain-derived neurotrophic factor (BDNF) signaling) in naïve male C57BL/6J mice. In contrast, genetic overexpression and pharmacological activation of miR-184-3p in the PVN produced significant beneficial effects against CSDS. MiR-184-3p in the PVN was necessary for the antidepressant actions of two well-known SSRIs, fluoxetine and paroxetine. Collectively. miR-184-3p was also implicated in the neurobiology of depression and may be a viable target for novel antidepressants.

Fluorine-Doped Carbon Support Enables Superfast Oxygen Reduction Kinetics by Breaking the Scaling Relationship.

It is well-established that Pt-based catalysts suffer from the unfavorable linear scaling relationship (LSR) between *OOH and *OH (ΔG(*OOH)=ΔG(*OH)+3.2±0.2 eV) for the oxygen reduction reaction (ORR), resulting in a great challenge to significantly reduced ORR overpotentials. Herein, we propose a universal and feasible strategy of fluorine-doped carbon supports, which optimize interfacial microenvironment of Pt-based catalysts and thus significantly enhance their reactive kinetics. The introduction of C-F bonds not only weakens the *OH binding energy, but also stabilizes the *OOH intermediate, resulting in a break of LSR. Furthermore, fluorine-doped carbon constructs a local super-hydrophobic interface that facilitates the diffusion of H2O and the mass transfer of O2. Electrochemical tests show that the F-doped carbon-supported Pt catalysts exhibit over 2-fold higher mass activities than those without F modification. More importantly, those catalysts also demonstrate excellent stability in both rotating disk electrode (RDE) and membrane electrode assembly (MEA) tests. This study not only validates the feasibility of tuning the electrocatalytic microenvironment to improve mass transport and to break the scaling relationship, but also provides a universal catalyst design paradigm for other gas-involving electrocatalytic reactions.

The role of cytokine receptor-like factor 1 (CRLF1) in facet joint osteoarthritis pathogenesis.

BACKGROUND: Facet joint osteoarthritis (FJOA) is a prevalent condition contributing to low back pain, particularly in the elderly population. This study aimed to investigate the potential role of Cytokine Receptor-like Factor 1 (CRLF1) in FJOA pathogenesis and its therapeutic implications. METHODS: Bioinformatics analysis was utilized to identify CRLF1 as the target gene, followed by quantification of CRLF1 expression levels and joint degeneration degree using immunohistochemistry (IHC). In primary chondrocytes, the inhibition of CRLF1 expression by siRNA was performed, and Western blot analysis was conducted to evaluate the involvement of the extracellular matrix and MAPK/ERK signaling pathway. Flow cytometry was employed to assess the apoptosis rate of chondrocytes, while immunofluorescence (IF) was utilized to evaluate the localization of CRLF1, cleaved-caspase3, MMP13, COL2A1, and ERK. RESULTS: The expression of CRLF1 was found to be significantly elevated in FJOA tissues compared to normal tissues. Through the use of loss-of-function assays, it was determined that CRLF1 not only enhanced the rate of apoptosis in chondrocytes, but also facilitated the degradation of the extracellular matrix in vitro. Furthermore, CRLF1 was found to activate the ERK1/2 pathways. The pro-arthritic effects elicited by CRLF1 were mitigated by treatment with the MEK inhibitor U0126 in chondrocytes. CONCLUSION: These results suggest that CRLF1 enhances chondrocytes apoptosis and extracellular matrix degration in FJOA and thus may therefore be a potential therapeutic target for FJOA.

A review of deep learning methods for ligand based drug virtual screening.

Drug discovery is costly and time consuming, and modern drug discovery endeavors are progressively reliant on computational methodologies, aiming to mitigate temporal and financial expenditures associated with the process. In particular, the time required for vaccine and drug discovery is prolonged during emergency situations such as the coronavirus 2019 pandemic. Recently, the performance of deep learning methods in drug virtual screening has been particularly prominent. It has become a concern for researchers how to summarize the existing deep learning in drug virtual screening, select different models for different drug screening problems, exploit the advantages of deep learning models, and further improve the capability of deep learning in drug virtual screening. This review first introduces the basic concepts of drug virtual screening, common datasets, and data representation methods. Then, large numbers of common deep learning methods for drug virtual screening are compared and analyzed. In addition, a dataset of different sizes is constructed independently to evaluate the performance of each deep learning model for the difficult problem of large-scale ligand virtual screening. Finally, the existing challenges and future directions in the field of virtual screening are presented.

A Microscopically Heterogeneous Colloid Electrolyte for Extremely Fast-Charging and Long-Calendar-Life Silicon-Based Lithium-Ion Batteries.

Fast-charging capability and calendar life are critical metrics in rechargeable batteries, especially in silicon-based batteries that are susceptible to sluggish Li+ desolvation kinetics and HF-induced corrosion. No existing electrolyte simultaneously tackles both these pivotal challenges. Here we report a microscopically heterogeneous covalent organic nanosheet (CON) colloid electrolyte for extremely fast-charging and long-calendar-life Si-based lithium-ion batteries. Theoretical calculations and operando Raman spectroscopy reveal the fundamental mechanism of the multiscale noncovalent interaction, which involves the mesoscopic CON attenuating the microscopic Li+-solvent coordination, thereby expediting the Li+ desolvation kinetics. This electrolyte design enables extremely fast-charging capabilities of the full cell, both at 8 C (83.1 % state of charge) and 10 C (81.3 % state of charge). Remarkably, the colloid electrolyte demonstrates record-breaking cycling performance at 10 C (capacity retention of 92.39 % after 400 cycles). Moreover, benefiting from the robust adsorption capability of mesoporous CON towards HF and water, a notable improvement is observed in the calendar life of the full cell. This study highlights the role of microscopically heterogeneous colloid electrolytes in enhancing the fast-charging capability and calendar life of Si-based Li-ion batteries. Our work offers fresh perspectives on electrolyte design with multiscale interactions, providing insightful guidance for the development of alkali-ion/metal batteries operating under harsh environments.

Rationally Designed L12-Pt2RhFe Intermetallic Catalyst with High CO-Tolerance for Alkaline Methanol Electrooxidation.

It is a grand challenge to deep understanding of and precise control over functional sites for the rational design of highly efficient catalysts for methanol electrooxidation. Here, an L12-Pt2RhFe intermetallic catalyst with integrated functional components is demonstrated, which exhibits exceptional CO tolerance. The Pt2RhFe/C achieves a superior mass activity of 6.43 A mgPt -1, which is 2.23-fold and 3.53-fold higher than those of PtRu/C and Pt/C. Impressively, the Pt2RhFe/C exhibits a significant enhancement in durability owing to its high CO-tolerance and stability. Density functional theory calculations reveal that high performance of Pt2RhFe intermetallic catalyst arises from the synergistic effect: the strong OH binding energy (OHBE) at Fe sites induce stably adsorbed OH species and thus facilitate the dehydrogenation step of methanol via rapid hydrogen transfer, while moderate OHBE at Rh sites promote the formation of the transition state (Pt-CO···OH-Rh) with a low activation barrier for CO removal. This work provides new insights into the role of OH binding strength in the removal of CO species, which is beneficial for the rational design of highly efficient catalysts.

Analysis of gene expression in microglial apoptotic cell clearance following spinal cord injury based on machine learning algorithms.

Spinal cord injury (SCI) is a severe neurological complication following spinal fracture, which has long posed a challenge for clinicians. Microglia play a dual role in the pathophysiological process after SCI, both beneficial and detrimental. The underlying mechanisms of microglial actions following SCI require further exploration. The present study combined three different machine learning algorithms, namely weighted gene co-expression network analysis, random forest analysis and least absolute shrinkage and selection operator analysis, to screen for differentially expressed genes in the GSE96055 microglia dataset after SCI. It then used protein-protein interaction networks and gene set enrichment analysis with single genes to investigate the key genes and signaling pathways involved in microglial function following SCI. The results indicated that microglia not only participate in neuroinflammation but also serve a significant role in the clearance mechanism of apoptotic cells following SCI. Notably, bioinformatics analysis and lipopolysaccharide + UNC569 (a MerTK-specific inhibitor) stimulation of BV2 cell experiments showed that the expression levels of Anxa2, Myo1e and Spp1 in microglia were significantly upregulated following SCI, thus potentially involved in regulating the clearance mechanism of apoptotic cells. The present study suggested that Anxa2, Myo1e and Spp1 may serve as potential targets for the future treatment of SCI and provided a theoretical basis for the development of new methods and drugs for treating SCI.

A Novel Hierarchical Cross-Stream Aggregation Neural Network for Semantic Segmentation of 3-D Dental Surface Models.

Accurate teeth delineation on 3-D dental models is essential for individualized orthodontic treatment planning. Pioneering works like PointNet suggest a promising direction to conduct efficient and accurate 3-D dental model analyses in end-to-end learnable fashions. Recent studies further imply that multistream architectures to concurrently learn geometric representations from different inputs/views (e.g., coordinates and normals) are beneficial for segmenting teeth with varying conditions. However, such multistream networks typically adopt simple late-fusion strategies to combine features captured from raw inputs that encode complementary but fundamentally different geometric information, potentially hampering their accuracy in end-to-end semantic segmentation. This article presents a hierarchical cross-stream aggregation (HiCA) network to learn more discriminative point/cell-wise representations from multiview inputs for fine-grained 3-D semantic segmentation. Specifically, based upon our multistream backbone with input-tailored feature extractors, we first design a contextual cross-steam aggregation (CA) module conditioned on interstream consistency to boost each view's contextual representation learning jointly. Then, before the late fusion of different streams' outputs for segmentation, we further deploy a discriminative cross-stream aggregation (DA) module to concurrently update all views' discriminative representation learning by leveraging a specific graph attention strategy induced by multiview prototype learning. On both public and in-house datasets of real-patient dental models, our method significantly outperformed state-of-the-art (SOTA) deep learning methods for teeth semantic segmentation. In addition, extended experimental results suggest the applicability of HiCA to other general 3-D shape segmentation tasks. The code is available at https://github.com/ladderlab-xjtu/HiCA.

Pt3Sn0.5Mn0.5 Intermetallic Electrocatalyst with Superior Stability for CO-Resilient Methanol Oxidation.

The sluggish kinetics of methanol oxidation reaction (MOR) and poor long-term durability of catalysts are the main restrictions of the large-scale applications of direct methanol fuel cells (DMFCs). Herein, we demonstrated an inspirational ternary Pt3Sn0.5Mn0.5/DMC intermetallic catalyst that reached 4.78 mA cm-2 and 2.39 A mg-1Pt for methanol oxidation, which were 2.50/2.44 and 5.62/5.31 times that of commercial PtRu/C and Pt/C. After the durability test, Pt3Sn0.5Mn0.5/DMC presented a very low current density attenuation (38.5%), which was significantly lower than those for commercial PtRu/C catalyst (84.2%) and Pt/C (93.1%). Density functional theory (DFT) calculations revealed that the coregulation of Sn and Mn altered the surface electronic structure and endowed Pt3Sn0.5Mn0.5 with selective adsorption of Pt for CO and Sn for OH, which optimized the adsorption strength for intermediates and improved the reaction kinetics of MOR. Beyond offering an advanced electrocatalyst, this study provided a new point of view for the rational design of superior methanol oxidation catalysts for DMFC.

Multi-scale revealing how real catalyst layer interfaces dominate the local oxygen transport resistance in ultra-low platinum PEMFC.

In view of a catalyst layer (CL) with low-Pt causing higher local transport resistance of O2 (Rlocal), we propose a multi-study methodology that combines CO poisoning, the limiting current density method, and electrochemical impedance spectroscopy to reveal how real CL interfaces dominate Rlocal. Experimental results indicate that the ionomer is not evenly distributed on the catalyst surface, and the uniformity of ionomer distribution does not show a positive correlation with the ionomer content. When the ionomer coverage on the supported catalyst surface is below 20 %, the ECSA is only 10 m2·g-1, and the ionomer coverage on the supported catalyst surface reaches 60 %, the ECSA is close to 40 m2·g-1. The ECSA has a positive correlation with ionomer coverage. Because the ECSA is measured by CO poisoning, it can be inferred that the platinum contacted with ionomer can generate effective active sites. Furthermore, a more uniform distribution of ionomer can create additional proton transport channels and reduce the distance for oxygen transport from the catalyst layer bulk to the active sites. A higher ECSA and a shorter distance for oxygen transport will reduce the Rlocal, leading to better performance.

ChatCAD+: Towards a Universal and Reliable Interactive CAD using LLMs.

The integration of Computer-Aided Diagnosis (CAD) with Large Language Models (LLMs) presents a promising frontier in clinical applications, notably in automating diagnostic processes akin to those performed by radiologists and providing consultations similar to a virtual family doctor. Despite the promising potential of this integration, current works face at least two limitations: (1) From the perspective of a radiologist, existing studies typically have a restricted scope of applicable imaging domains, failing to meet the diagnostic needs of different patients. Also, the insufficient diagnostic capability of LLMs further undermine the quality and reliability of the generated medical reports. (2) Current LLMs lack the requisite depth in medical expertise, rendering them less effective as virtual family doctors due to the potential unreliability of the advice provided during patient consultations. To address these limitations, we introduce ChatCAD+, to be universal and reliable. Specifically, it is featured by two main modules: (1) Reliable Report Generation and (2) Reliable Interaction. The Reliable Report Generation module is capable of interpreting medical images from diverse domains and generate high-quality medical reports via our proposed hierarchical in-context learning. Concurrently, the interaction module leverages up-to-date information from reputable medical websites to provide reliable medical advice. Together, these designed modules synergize to closely align with the expertise of human medical professionals, offering enhanced consistency and reliability for interpretation and advice. The source code is available at GitHub.

Pt1.8Pd0.2CuGa Intermetallic Nanocatalysts with Enhanced Methanol Oxidation Performance for Efficient Hybrid Seawater Electrolysis.

Seawater electrolysis is a potentially cost-effective approach to green hydrogen production, but it currently faces substantial challenges for its high energy consumption and the interference of chlorine evolution reaction (ClER). Replacing the energy-demanding oxygen evolution reaction with methanol oxidation reaction (MOR) represents a promising alternative, as MOR occurs at a significantly low anodic potential, which cannot only reduce the voltage needed for electrolysis but also completely circumvents ClER. To this end, developing high-performance MOR catalysts is a key. Herein, a novel quaternary Pt1.8Pd0.2CuGa/C intermetallic nanoparticle (i-NP) catalyst is reported, which shows a high mass activity (11.13 A mgPGM -1), a large specific activity (18.13 mA cmPGM -2), and outstanding stability toward alkaline MOR. Advanced characterization and density functional theory calculations reveal that the introduction of atomically distributed Pd in Pt2CuGa intermetallic markedly promotes the oxidation of key reaction intermediates by enriching electron concentration around Pt sites, resulting in weak adsorption of carbon-containing intermediates and favorable adsorption of synergistic OH- groups near Pd sites. MOR-assisted seawater electrolysis is demonstrated, which continuously operates under 1.23 V for 240 h in simulated seawater and 120 h in natural seawater without notable degradation.