sCD14-ST and Related Osteoimmunological Biomarkers: A New Diagnostic Approach to Osteomyelitis.

Osteomyelitis (OM) is a major challenge in orthopedic surgery. The diagnosis of OM is based on imaging and laboratory tests, but it still presents some limitations. Therefore, a deeper comprehension of the pathogenetic mechanisms could enhance diagnostic and treatment approaches. OM pathogenesis is based on an inflammatory response to pathogen infection, leading to bone loss. The present study aims to investigate the potential diagnostic role of a panel of osteoimmunological serum biomarkers in the clinical approach to OM. The focus is on the emerging infection biomarker sCD14-ST, along with osteoimmunological and inflammatory serum biomarkers, to define a comprehensive biomarker panel for a multifaced approach to OM. The results, to our knowledge, demonstrate for the first time the diagnostic and early prognostic role of sCD14-ST in OM patients, suggesting that this biomarker could address the limitations of current laboratory tests, such as traditional inflammatory markers, in diagnosing OM. In addition, the study highlights a relevant diagnostic role of SuPAR, the chemokine CCL2, the anti-inflammatory cytokine IL-10, the Wnt inhibitors DKK-1 and Sclerostin, and the RANKL/OPG ratio. Moreover, CCL2 and SuPAR also exhibited early prognostic value.

Q-ADER: An Effective Q-Learning for Recommendation With Diminishing Action Space.

Deep reinforcement learning (RL) has been widely applied to personalized recommender systems (PRSs) as they can capture user preferences progressively. Among RL-based techniques, deep Q-network (DQN) stands out as the most popular choice due to its simple update strategy and superior performance. Typically, many recommendation scenarios are accompanied by the diminishing action space setting, where the available action space will gradually decrease to avoid recommending duplicate items. However, existing DQN-based recommender systems inherently grapple with a discrepancy between the fixed full action space inherent in the Q-network and the diminishing available action space during recommendation. This article elucidates how this discrepancy induces an issue termed action diminishing error in the vanilla temporal difference (TD) operator. Due to this discrepancy, standard DQN methods prove impractical for learning accurate value estimates, rendering them ineffective in the context of diminishing action space. To mitigate this issue, we propose the Q-learning-based action diminishing error reduction (Q-ADER) algorithm to modify the value estimate error at each step. In practice, Q-ADER augments the standard TD learning with an error reduction term which is straightforward to implement on top of the existing DQN algorithms. Experiments are conducted on four real-world datasets to verify the effectiveness of our proposed algorithm.

Precise Localization for Anatomo-Physiological Hallmarks of the Cervical Spine by Using Neural Memory Ordinary Differential Equation.

In the evaluation of cervical spine disorders, precise positioning of anatomo-physiological hallmarks is fundamental for calculating diverse measurement metrics. Despite the fact that deep learning has achieved impressive results in the field of keypoint localization, there are still many limitations when facing medical image. First, these methods often encounter limitations when faced with the inherent variability in cervical spine datasets, arising from imaging factors. Second, predicting keypoints for only 4% of the entire X-ray image surface area poses a significant challenge. To tackle these issues, we propose a deep neural network architecture, NF-DEKR, specifically tailored for predicting keypoints in cervical spine physiological anatomy. Leveraging neural memory ordinary differential equation with its distinctive memory learning separation and convergence to a singular global attractor characteristic, our design effectively mitigates inherent data variability. Simultaneously, we introduce a Multi-Resolution Focus module to preprocess feature maps before entering the disentangled regression branch and the heatmap branch. Employing a differentiated strategy for feature maps of varying scales, this approach yields more accurate predictions of densely localized keypoints. We construct a medical dataset, SCUSpineXray, comprising X-ray images annotated by orthopedic specialists and conduct similar experiments on the publicly available UWSpineCT dataset. Experimental results demonstrate that compared to the baseline DEKR network, our proposed method enhances average precision by 2% to 3%, accompanied by a marginal increase in model parameters and the floating-point operations (FLOPs). The code (https://github.com/Zhxyi/NF-DEKR) is available.

Automated Quality Assessment of Medical Images in Echocardiography Using Neural Networks with Adaptive Ranking and Structure-Aware Learning.

The quality of medical images is crucial for accurately diagnosing and treating various diseases. However, current automated methods for assessing image quality are based on neural networks, which often focus solely on pixel distortion and overlook the significance of complex structures within the images. This study introduces a novel neural network model designed explicitly for automated image quality assessment that addresses pixel and semantic distortion. The model introduces an adaptive ranking mechanism enhanced with contrast sensitivity weighting to refine the detection of minor variances in similar images for pixel distortion assessment. More significantly, the model integrates a structure-aware learning module employing graph neural networks. This module is adept at deciphering the intricate relationships between an image's semantic structure and quality. When evaluated on two ultrasound imaging datasets, the proposed method outshines existing leading models in performance. Additionally, it boasts seamless integration into clinical workflows, enabling real-time image quality assessment, crucial for precise disease diagnosis and treatment.

A Forward Learning Algorithm for Neural Memory Ordinary Differential Equations.

The deep neural network, based on the backpropagation learning algorithm, has achieved tremendous success. However, the backpropagation algorithm is consistently considered biologically implausible. Many efforts have recently been made to address these biological implausibility issues, nevertheless, these methods are tailored to discrete neural network structures. Continuous neural networks are crucial for investigating novel neural network models with more biologically dynamic characteristics and for interpretability of large language models. The neural memory ordinary differential equation (nmODE) is a recently proposed continuous neural network model that exhibits several intriguing properties. In this study, we present a forward-learning algorithm, called nmForwardLA, for nmODE. This algorithm boasts lower computational dimensions and greater efficiency. Compared with the other learning algorithms, experimental results on MNIST, CIFAR10, and CIFAR100 demonstrate its potency.

Prototype Bayesian Meta-Learning for Few-Shot Image Classification.

Meta-learning aims to leverage prior knowledge from related tasks to enable a base learner to quickly adapt to new tasks with limited labeled samples. However, traditional meta-learning methods have limitations as they provide an optimal initialization for all new tasks, disregarding the inherent uncertainty induced by few-shot tasks and impeding task-specific self-adaptation initialization. In response to this challenge, this article proposes a novel probabilistic meta-learning approach called prototype Bayesian meta-learning (PBML). PBML focuses on meta-learning variational posteriors within a Bayesian framework, guided by prototype-conditioned prior information. Specifically, to capture model uncertainty, PBML treats both meta-and task-specific parameters as random variables and integrates their posterior estimates into hierarchical Bayesian modeling through variational inference (VI). During model inference, PBML employs Laplacian estimation to approximate the integral term over the likelihood loss, deriving a rigorous upper-bound for generalization errors. To enhance the model's expressiveness and enable task-specific adaptive initialization, PBML proposes a data-driven approach to model the task-specific variational posteriors. This is achieved by designing a generative model structure that incorporates prototype-conditioned task-dependent priors into the random generation of task-specific variational posteriors. Additionally, by performing latent embedding optimization, PBML decouples the gradient-based meta-learning from the high-dimensional variational parameter space. Experimental results on benchmark datasets for few-shot image classification illustrate that PBML attains state-of-the-art or competitive performance when compared to other related works. Versatility studies demonstrate the adaptability and applicability of PBML in addressing diverse and challenging few-shot tasks. Furthermore, ablation studies validate the performance gains attributed to the inference and model components.

Mitochondrial GPX4 acetylation is involved in cadmium-induced renal cell ferroptosis.

Increasing evidences demonstrate that environmental stressors are important inducers of acute kidney injury (AKI). This study aimed to investigate the impact of exposure to Cd, an environmental stressor, on renal cell ferroptosis. Transcriptomics analyses showed that arachidonic acid (ARA) metabolic pathway was disrupted in Cd-exposed mouse kidneys. Targeted metabolomics showed that renal oxidized ARA metabolites were increased in Cd-exposed mice. Renal 4-HNE, MDA, and ACSL4, were upregulated in Cd-exposed mouse kidneys. Consistent with animal experiments, the in vitro experiments showed that mitochondrial oxidized lipids were elevated in Cd-exposed HK-2 cells. Ultrastructure showed mitochondrial membrane rupture in Cd-exposed mouse kidneys. Mitochondrial cristae were accordingly reduced in Cd-exposed mouse kidneys. Mitochondrial SIRT3, an NAD+-dependent deacetylase that regulates mitochondrial protein stability, was reduced in Cd-exposed mouse kidneys. Subsequently, mitochondrial GPX4 acetylation was elevated and mitochondrial GPX4 protein was reduced in Cd-exposed mouse kidneys. Interestingly, Cd-induced mitochondrial GPX4 acetylation and renal cell ferroptosis were exacerbated in Sirt3-/- mice. Conversely, Cd-induced mitochondrial oxidized lipids were attenuated in nicotinamide mononucleotide (NMN)-pretreated HK-2 cells. Moreover, Cd-evoked mitochondrial GPX4 acetylation and renal cell ferroptosis were alleviated in NMN-pretreated mouse kidneys. These results suggest that mitochondrial GPX4 acetylation, probably caused by SIRT3 downregulation, is involved in Cd-evoked renal cell ferroptosis.

ICNoduleNet: Enhancing Pulmonary Nodule Detection Performance on Sharp Kernel CT Imaging.

Thoracic computed tomography (CT) currently plays the primary role in pulmonary nodule detection, where the reconstruction kernel significantly impacts performance in computer-aided pulmonary nodule detectors. The issue of kernel selection affecting performance has been overlooked in pulmonary nodule detection. This paper first introduces a novel pulmonary nodule detection dataset named Reconstruction Kernel Imaging for Pulmonary Nodule Detection (RKPN) for quantifying algorithm differences between the two imaging types. The dataset contains pairs of images taken from the same patient on the same date, featuring both smooth (B31f) and sharp kernel (B60f) reconstructions. All other imaging parameters and pulmonary nodule labels remain entirely consistent across these pairs. Extensive quantification reveals mainstream detectors perform better on smooth kernel imaging than on sharp kernel imaging. To address suboptimal detection on the sharp kernel imaging, we further propose an image conversion-based pulmonary nodule detector called ICNoduleNet. A lightweight 3D slice-channel converter (LSCC) module is introduced to convert sharp kernel images into smooth kernel images, which can sufficiently learn inter-slice and inter-channel feature information while avoiding introducing excessive parameters. We conduct thorough experiments that validate the effectiveness of ICNoduleNet, it takes sharp kernel images as input and can achieve comparable or even superior detection performance to the baseline that uses the smooth kernel images. The evaluation shows promising results and proves the effectiveness of ICNoduleNet.

Electrocardiogram-based prediction of conduction disturbances after transcatheter aortic valve replacement with convolutional neural network.

Aims: Permanent pacemaker implantation and left bundle branch block are common complications after transcatheter aortic valve replacement (TAVR) and are associated with impaired prognosis. This study aimed to develop an artificial intelligence (AI) model for predicting conduction disturbances after TAVR using pre-procedural 12-lead electrocardiogram (ECG) images. Methods and results: We collected pre-procedural 12-lead ECGs of patients who underwent TAVR at West China Hospital between March 2016 and March 2022. A hold-out testing set comprising 20% of the sample was randomly selected. We developed an AI model using a convolutional neural network, trained it using five-fold cross-validation and tested it on the hold-out testing cohort. We also developed and validated an enhanced model that included additional clinical features. After applying exclusion criteria, we included 1354 ECGs of 718 patients in the study. The AI model predicted conduction disturbances in the hold-out testing cohort with an area under the curve (AUC) of 0.764, accuracy of 0.743, F1 score of 0.752, sensitivity of 0.876, and specificity of 0.624, based solely on pre-procedural ECG images. The performance was better than the Emory score (AUC = 0.704), as well as the logistic (AUC = 0.574) and XGBoost (AUC = 0.520) models built with previously identified high-risk ECG patterns. After adding clinical features, there was an increase in the overall performance with an AUC of 0.779, accuracy of 0.774, F1 score of 0.776, sensitivity of 0.794, and specificity of 0.752. Conclusion: Artificial intelligence-enhanced ECGs may offer better predictive value than traditionally defined high-risk ECG patterns.

Neural Network Model Based on Branch Architecture for the Quality Assurance of Volumetric Modulated Arc Therapy.

Radiation therapy relies on quality assurance (QA) to verify dose delivery accuracy. However, current QA methods suffer from operation lag as well as inaccurate performance. Hence, to address these shortcomings, this paper proposes a QA neural network model based on branch architecture, which is based on the analysis of the category features of the QA complexity metrics. The designed branch network focuses on category features, which effectively improves the feature extraction capability for complexity metrics. The branch features extracted by the model are fused to predict the GPR for more accurate QA. The performance of the proposed method was validated on the collected dataset. The experiments show that the prediction performance of the model outperforms other QA methods; the average prediction errors for the test set are 2.12% (2%/2 mm), 1.69% (3%/2 mm), and 1.30% (3%/3 mm). Moreover, the results indicate that two-thirds of the validation samples' model predictions perform better than the clinical evaluation results, suggesting that the proposed model can assist physicists in the clinic.

Coexistence of Cyclic Sequential Pattern Recognition and Associative Memory in Neural Networks by Attractor Mechanisms.

Neural networks are developed to model the behavior of the brain. One crucial question in this field pertains to when and how a neural network can memorize a given set of patterns. There are two mechanisms to store information: associative memory and sequential pattern recognition. In the case of associative memory, the neural network operates with dynamical attractors that are point attractors, each corresponding to one of the patterns to be stored within the network. In contrast, sequential pattern recognition involves the network memorizing a set of patterns and subsequently retrieving them in a specific order over time. From a dynamical perspective, this corresponds to the presence of a continuous attractor or a cyclic attractor composed of the sequence of patterns stored within the network in a given order. Evidence suggests that the brain is capable of simultaneously performing both associative memory and sequential pattern recognition. Therefore, these types of attractors coexist within the neural network, signifying that some patterns are stored as point attractors, while others are stored as continuous or cyclic attractors. This article investigates the coexistence of cyclic attractors and continuous or point attractors in certain nonlinear neural networks, enabling the simultaneous emergence of various memory mechanisms. By selectively grouping neurons, conditions are established for the existence of cyclic attractors, continuous attractors, and point attractors, respectively. Furthermore, each attractor is explicitly represented, and a competitive dynamic emerges among these coexisting attractors, primarily regulated by adjustments to external inputs.

A Bidirectional Feedforward Neural Network Architecture Using the Discretized Neural Memory Ordinary Differential Equation.

Deep Feedforward Neural Networks (FNNs) with skip connections have revolutionized various image recognition tasks. In this paper, we propose a novel architecture called bidirectional FNN (BiFNN), which utilizes skip connections to aggregate features between its forward and backward paths. The BiFNN accepts any FNN as a plugin that can incorporate any general FNN model into its forward path, introducing only a few additional parameters in the cross-path connections. The backward path is implemented as a nonparameter layer, utilizing a discretized form of the neural memory Ordinary Differential Equation (nmODE), which is named [Formula: see text]-net. We provide a proof of convergence for the [Formula: see text]-net and evaluate its initial value problem. Our proposed architecture is evaluated on diverse image recognition datasets, including Fashion-MNIST, SVHN, CIFAR-10, CIFAR-100, and Tiny-ImageNet. The results demonstrate that BiFNNs offer significant improvements compared to embedded models such as ConvMixer, ResNet, ResNeXt, and Vision Transformer. Furthermore, BiFNNs can be fine-tuned to achieve comparable performance with embedded models on Tiny-ImageNet and ImageNet-1K datasets by loading the same pretrained parameters.

Analysis of relevant factors influencing size of breast abscess cavity during lactation: a cross-sectional study.

OBJECTIVE: The aim of this study was to investigate risk factors for the severity of breast abscess during lactation. METHODS: A cross-sectional study was conducted using data from the Questionnaire survey of breast abscess patients. According to whether the maximum abscess diameter > 5 cm, the patients were divided into two groups for univariate and multivariate regression analysis. RESULTS: 1805 valid questionnaires were included. Univariate and Binary logistic regression analysis demonstrated that low education (OR = 1.5, 95% CI 1.1-2.0, P = 0.005), non-exclusive breastfeeding (OR = 0.7, 95% CI 0.6-0.9, P = 0.004), fever > 37.5 â„ƒ (OR = 0.7, 95% CI 0.6-0.9, P = 0.003), flat or inverted nipples (OR = 0.7, 95% CI 0.6-0.9, P = 0.005), antibiotic used (OR = 0.7, 95% CI 0.6-0.9, P = 0.006), and non-medical massage (OR = 0.3, 95% CI 0.2-0.4, P < 0.001) were the effective independent influencing factors for the maximum breast abscess diameter > 5 cm. CONCLUSION: Low education, non-exclusive breastfeeding, fever > 37.5 â„ƒ, inverted or flat nipples, antibiotic used, and non-medical massage history have adverse effects on the severity of breast abscess during lactation.

Efficacy of Tounongsan decoction on pyogenic liver abscess: network pharmacology and clinical trial validation.

OBJECTIVE: To elucidate the molecular mechanisms governing the effect of Tounongsan decoction (, TNS) on the pyogenic liver abscess. METHODS: Based on oral bioavailability and drug-likeness, the main active components of TNS were screened using the Traditional Chinese Medicine Systems Pharmacology platform. The GeneCard and UniProt databases were used to establish a database of pyogenic liver abscess targets. The interactive network map of drug-ingredients-target-disease was constructed using Cytoscape software (Version 3.7.2). A protein-protein interaction network was constructed using the STRING database, and the related protein interaction relationships were analyzed. biological process of gene ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analyses were performed for the core targets. Finally, a clinical trial was performed to verify the reliability of the network pharmacology. RESULTS: Forty active components of TNS decoction were obtained, and 61 potential targets and 11 proteins were identified. Pathways involved in the treatment of pyogenic liver abscess include the phosphatidylinositide 3-kinases-protein kinase B (PI3K-AKT), advanced glycation end products-receptor for advanced glycation end products (AGE-RAGE), and tumor necrosis factor (TNF) signaling pathways. The results of network pharmacology analysis combined with clinical trials validated that TNS decoction could alleviate the inflammatory response of pyogenic liver abscesses by decreasing interleukin 6 (IL-6) levels. CONCLUSIONS: TNS decoction has the characteristics of being multi-system, multi-component, and multi-target. Active ingredients in TNS, such as quercetin, kaempferol, fisetin, and ß-sitosterol, have strong potential to be candidate drugs for treating pyogenic liver abscesses. The possible mechanism of TSN decoction includes regulating immune and inflammatory responses and reducing IL-6 production to control inflammatory development.

Hsa_circ_0013561 promotes progression of nasopharyngeal carcinoma by activating JAK2/STAT3 signaling pathway.

OBJECTIVE: Nasopharyngeal Carcinoma (NPC) is a malignancy of epithelium of epithelium of the nasopharynx, with the highest incidence of otolaryngeal malignancies. A growing number of studies confirm that Circular RNA (circRNA) plays an important role in tumor development, including Hsa_circ_0013561. This study aims to elucidate the process and mechanism of NPC regulation hsa_circ_0013561. METHODS: In this study, circRNA expression nodes and subcellular localization in NPC tissues were analyzed by fluorescence in situ hybridization. The expression of hsa_circ_0013561 in NPC cells was further clarified by RT-qPCR. At the same time, the lentivirus vector interfered by hsa_circ_0013561 was constructed and transfected. The cell proliferation was detected by CCK-8 method, EdU assay and plate cloning assay. The cell cycle and apoptosis were detected by flow cytometry, and the cell migration ability was detected by wound healing assay and Transwell assay. Western blotting examined the expression of apoptosis, Epithelial-Mesenchymal Transition (EMT)-associated proteins, and Janus Kinase/Signal Transductor and Activator of Transcription (JAK/STAT) signaling pathway-related proteins. RESULTS: The results showed that the expression of hsa_circ_0013561 in NPC samples was significantly upregulated and hsa_circ_0013561 localized in the cytoplasm. After down-regulating hsa_circ_0013561 expression, it significantly inhibited the proliferation and metastasis ability of NPC, inhibited EMT progression, and promoted apoptosis. Further studies showed that interference hsa_circ_0013561 significantly inhibited JAK2/STAT3 signaling pathway activation and induced the expression of apoptosis-related proteins. CONCLUSION: In summary, we found that hsa_circ_0013561 is a pro-tumor circRNA in NPC, which can reduce the activation of JAK2/STAT3 pathway by knocking down hsa_circ_0013561, thereby slowing down the malignant progression of NPC. OXFORD CENTRE FOR EVIDENCE-BASED MEDICINE 2011 LEVELS OF EVIDENCE: Level 4.

Honeybee symbiont Bombella apis could restore larval-to-pupal transition disrupted by antibiotic treatment.

Numerous studies have demonstrated the vital roles of gut microbes in the health, immunity, nutrient metabolism, and behavior of adult worker honeybees. However, a few studies have been conducted on gut microbiota associated with the larval stage of honeybees. In the present study, we explored the role of a gut bacterium in larval development and larval-pupal transition in the Asian honeybee, Apis cerana. First, our examination of gut microbial profiling showed that Bombella apis, a larvae-associated bacterium, was the most dominant bacterium colonized in the fifth instar larvae. Second, we demonstrated that tetracycline, an antibiotic used to treat a honeybee bacterial brood disease, could cause the complete depletion of gut bacteria. This antibiotic-induced gut microbiome depletion in turn, significantly impacted the survivorship, pupation rate and emergence rate of the treated larvae. Furthermore, our analysis of gene expression pattens revealed noteworthy changes in key genes. The expression of genes responsible for encoding storage proteins vitellogenin (vg) and major royal jelly protein 1 (mrjp1) was significantly down-regulated in the tetracycline-treated larvae. Concurrently, the expression of krüppel homolog 1(kr-h1), a pivotal gene in endocrine signaling, increased, whilethe expression of broad-complex (br-c) gene that plays a key role in the ecdysone regulation decreased. These alterations indicated a disruption in the coordination of juvenile hormone and ecdysteroid synthesis. Finally, we cultivated B. apis isolated from the fifth instar worker larval of A. cerana and fed tetracycline-treated larvae with a diet replenished by B. apis. This intervention resulted in a significant improvement in the pupation rate, emergence rate, and overall survival rate of the treated larvae. Our findings demonstrate the positive impact of B. apis on honeybee larvae development, providing new evidence of the functional capacities of gut microbes in honeybee growth and development.

Hsa_circ_0013561 promotes progression of nasopharyngeal carcinoma by activating JAK2/STAT3 signaling pathway

Abstract Objective Nasopharyngeal Carcinoma (NPC) is a malignancy of epithelium of epithelium of the nasopharynx, with the highest incidence of otolaryngeal malignancies. A growing number of studies confirm that Circular RNA (circRNA) plays an important role in tumor development, including Hsa_circ_0013561. This study aims to elucidate the process and mechanism of NPC regulation hsa_circ_0013561. Methods In this study, circRNA expression nodes and subcellular localization in NPC tissues were analyzed by fluorescence in situ hybridization. The expression of hsa_circ_0013561 in NPC cells was further clarified by RT-qPCR. At the same time, the lentivirus vector interfered by hsa_circ_0013561 was constructed and transfected. The cell proliferation was detected by CCK-8 method, EdU assay and plate cloning assay. The cell cycle and apoptosis were detected by flow cytometry, and the cell migration ability was detected by wound healing assay and Transwell assay. Western blotting examined the expression of apoptosis, Epithelial-Mesenchymal Transition (EMT)-associated proteins, and Janus Kinase/Signal Transductor and Activator of Transcription (JAK/STAT) signaling pathway-related proteins. Results The results showed that the expression of hsa_circ_0013561 in NPC samples was significantly upregulated and hsa_circ_0013561 localized in the cytoplasm. After down-regulating hsa_circ_0013561 expression, it significantly inhibited the proliferation and metastasis ability of NPC, inhibited EMT progression, and promoted apoptosis. Further studies showed that interference hsa_circ_0013561 significantly inhibited JAK2/STAT3 signaling pathway activation and induced the expression of apoptosis-related proteins. Conclusion In summary, we found that hsa_circ_0013561 is a pro-tumor circRNA in NPC, which can reduce the activation of JAK2/STAT3 pathway by knocking down hsa_circ_0013561, thereby slowing down the malignant progression of NPC. Oxford Centre for Evidence-Based Medicine 2011 Levels of Evidence Level 4.

Study on the preparation and properties of Sn-0.7Cu-xBi alloy.

This study investigated the impact of different bismuth (Bi) contents on the mechanical properties, melting point, and corrosion resistance of tin-copper (Sn-Cu) series alloys (Sn-0.7Cu). Furthermore, Sn-0.7Cu-xBi alloys with different Bi contents (x = 0, 3, 6, 9, 12, 15 wt%) were prepared through a traditional casting process. The composition and microstructure of the alloy were characterized via X-ray diffraction (XRD) and Scanning electron microscopy (SEM). The impact of Bi on the mechanical properties, melting point, and corrosion resistance of Sn-0.7Cu alloy was analyzed, reaching a peak at 12 wt% Bi. Furthermore, beyond this concentration, the mechanical properties of the alloy exhibited a decline. The corrosion resistance of Sn-0.7Cu-xBi alloys increased with increasing Bi content. However, when the Bi content was >12 wt%, owing to the aggregation of Bi in the alloy, the corrosion resistance of the alloy decreased.

Enhancing Robustness of Medical Image Segmentation Model with Neural Memory Ordinary Differential Equation.

Deep neural networks (DNNs) have emerged as a prominent model in medical image segmentation, achieving remarkable advancements in clinical practice. Despite the promising results reported in the literature, the effectiveness of DNNs necessitates substantial quantities of high-quality annotated training data. During experiments, we observe a significant decline in the performance of DNNs on the test set when there exists disruption in the labels of the training dataset, revealing inherent limitations in the robustness of DNNs. In this paper, we find that the neural memory ordinary differential equation (nmODE), a recently proposed model based on ordinary differential equations (ODEs), not only addresses the robustness limitation but also enhances performance when trained by the clean training dataset. However, it is acknowledged that the ODE-based model tends to be less computationally efficient compared to the conventional discrete models due to the multiple function evaluations required by the ODE solver. Recognizing the efficiency limitation of the ODE-based model, we propose a novel approach called the nmODE-based knowledge distillation (nmODE-KD). The proposed method aims to transfer knowledge from the continuous nmODE to a discrete layer, simultaneously enhancing the model's robustness and efficiency. The core concept of nmODE-KD revolves around enforcing the discrete layer to mimic the continuous nmODE by minimizing the KL divergence between them. Experimental results on 18 organs-at-risk segmentation tasks demonstrate that nmODE-KD exhibits improved robustness compared to ODE-based models while also mitigating the efficiency limitation.