Search Results (126)

Background: Significant progress has been made in the field of machine learning, enabling the development of methods for automatic interpretation of medical images that provide high-quality diagnostics. However, most of these methods require access to confidential data, making them difficult to apply under strict privacy requirements. Existing privacy-preserving approaches, such as federated learning and dataset distillation, have limitations related to data access, visual interpretability, etc. Methods: This study explores the use of generative models to create synthetic medical data that preserves the statistical properties of the original data while ensuring privacy. The research is carried out on the VinDr-Mammo dataset of digital mammography images. A conditional generative method using Latent Diffusion Models (LDMs) is proposed with conditioning on diagnostic labels and lesion information. Diagnostic utility and privacy robustness are assessed via cancer classification tasks and re-identification tasks using Siamese neural networks and membership inference. Results: The generated synthetic data achieved a Fréchet Inception Distance (FID) of 5.8, preserving diagnostic features. A model trained solely on synthetic data achieved comparable performance to one trained on real data (ROC-AUC: 0.77 vs. 0.82). Visual assessments showed that synthetic images are indistinguishable from real ones. Privacy evaluations demonstrated a low re-identification risk (e.g., mAP@R = 0.0051 on the test set), confirming the effectiveness of the privacy-preserving approach. Conclusions: The study demonstrates that privacy-preserving generative models can produce synthetic medical images with sufficient quality for diagnostic task while significantly reducing the risk of patient re-identification. This approach enables secure data sharing and model training in privacy-sensitive domains such as medical imaging. Full article

A high-order single-step implicit method, the Legendre–Darboux Method of order six (LDM6), is introduced for solving both linear and nonlinear initial value problems. Unlike classical Taylor expansions, LDM6 systematically constructs higher-order derivatives via the Darboux formula with Legendre polynomials, yielding a compact scheme of exceptional accuracy and strong stability. To the best of current knowledge, LDM6 is the only single-step method exhibiting spectral-like behavior, achieving near machine-precision global accuracy while retaining efficiency for large step sizes. Comparative experiments on nonlinear cooling problems and the logistic growth model demonstrate that LDM6 surpasses the classical eighth-stage Runge–Kutta method (RK6) in accuracy, stability, and robustness. It attains unprecedented global errors as low as ${10}^{-38}$ and maintains stability for large steps (e.g., $h=10$), whereas RK6 suffers significant error accumulation. These results establish LDM6 as a uniquely efficient, high-fidelity integrator and the first single-step method with spectral-like accuracy, offering a new paradigm for high-precision time integration. Full article

Background/Objectives: Bulking agents such as Bulkamid^® are well-established surgical options for the treatment of stress urinary incontinence (SUI). Pelvic floor sonographic imaging is readily accessible and may assist in identifying patients who are more likely to benefit from bulking therapies. Urethral mobility appears to significantly influence treatment outcomes and can be classified into hypo-, normo-, and hypermobility. The primary aim of this study was to evaluate the impact of sonographic urethral mobility on the success rate of Bulkamid^® injections. The secondary objective was to assess differences between pre- and postoperative urinary incontinence scores. Methods: In women with SUI, linear dorsocaudal movement (LDM) of the urethra was measured sonographically. The International Consultation on Incontinence Modular Questionnaire—Urinary Incontinence Short Form (ICIQ-UI SF) was completed prior to Bulkamid^® injection. Patients were categorized into hypo-, normo-, and hypermobility groups based on their LDM measurements. Results: A total of 130 patients participated, with 101 undergoing both pre- and postoperative sonographic assessment. The difference in LDM before and after treatment was calculated. Patients with normomobile urethras (n = 79) exhibited the greatest mean improvement in continence scores, with LDM changes ranging from 6 to 24 mm and an average ICIQ-UI SF score reduction of 3.8 points. Patients with hypomobile (n = 16) or hypermobile urethras (n = 6) also demonstrated improvements, but to a lesser extent than the normomobile group. Conclusions: This study indicates that patients with a normomobile urethra experience the most significant improvement in continence outcomes following Bulkamid^® injection. Urethral mobility assessment via sonography may serve as a valuable preoperative tool and appears to play a crucial role in predicting treatment success with bulking agents. Full article

Skeletal muscles, accounting for 40% of mammalian body mass, exhibit pronounced heterogeneity due to their distinct anatomical locations. Animal husbandry has focused excessively on longissimus dorsi (LDM) development while neglecting other muscles. In this study, we integrated Bulk RNA Sequencing (bulk RNA-seq) and Liquid Chromatography–Mass Spectrometry (LC-MS) analyses of Soleus (SOL), Gastrocnemius (GAS), and Psoas major muscles (PMM) across three key stages in Duroc pigs. We identified nine critical genes (S100A1, MBOAT2, CA3, GYG2, ACTN3, ENO3, SLC3A2, SLC16A10, and GAPDH) and eight metabolites potentially involved in regulating both skeletal muscle development and fiber-type transformation. The heterogeneity between SOL and GAS was low at birth but increased gradually during development. In contrast, PMM exhibited higher heterogeneity than SOL and GAS from birth. Notably, expression levels of MYH7, MYH1, and MYH4 displayed stage-specific and muscle type-dependent variations. Moreover, we observed a developmental shift from the MAPK signaling pathway (1–21 d) to the regulation of the actin cytoskeleton (21–120 d). Pairwise comparisons between the SOL, GAS, and PMM revealed that the signaling pathways were enriched in muscle fiber-type switching. Collectively, through the integration of bulk RNA-seq and LC-MS data, this study provides novel molecular breeding strategies for the genetic improvement of meat-producing animals. Full article

Extreme ultraviolet (EUV) photomask inspection is a critical step in semiconductor manufacturing, requiring high-resolution, high-throughput solutions to detect nanometer-scale defects. Traditional actinic imaging systems relying on complex optics have a high cost of ownership and require frequent upgrades. An alternative is lensless imaging techniques based on ptychography, which offer high-fidelity reconstruction but suffer from slow throughput and high data demands. In particular, the ptychographic standard solver—the iterative Difference Map (DifMap) algorithm—requires many measurements and iterations to converge. We propose Ptycho-LDM, a hybrid framework integrating DifMap with a conditional Latent Diffusion Model for rapid and accurate phase retrieval. Ptycho-LDM alleviates high data acquisition demand by leveraging data-driven priors while offering improved computational efficiency. Our method performs coarse object retrieval using a resource-constrained reconstruction from DifMap and refines the result using a learned prior over photomask patterns. This prior enables high-fidelity reconstructions even in measurement-limited regimes where DifMap alone fails to converge. Experiments on actinic patterned mask inspection (APMI) show that Ptycho-LDM recovers fine structure and defect details with far fewer probe positions, surpassing the DifMap in accuracy and speed. Furthermore, evaluations on both noisy synthetic data and real APMI measurements confirm the robustness and effectiveness of Ptycho-LDM across practical scenarios. By combining generative modeling with physics-based constraints, Ptycho-LDM offers a promising scalable, high-throughput solution for next-generation photomask inspection. Full article

The rapid response of emergency vehicles is crucial but often hindered because sirens lose effectiveness in modern traffic due to soundproofing, noise, and distractions. Automatic in-vehicle detection can help, but existing solutions struggle with efficiency, interpretability, and embedded suitability. This paper presents a hardware-constrained Simulink implementation of a yelp siren detector designed for embedded operation. Building on a MATLAB-based proof-of-concept validated in an idealized floating-point setting, the present system reflects practical implementation realities. Key features include the use of a realistically modeled digital-to-analog converter (DAC), filter designs restricted to standard E-series component values, interrupt service routine (ISR)-driven processing, and fixed-point data type handling that mirror microcontroller execution. For benchmarking, the dataset used in the earlier proof-of-concept to tune system parameters was also employed to train three representative machine learning classifiers (k-nearest neighbors, support vector machine, and neural network), serving as reference classifiers. To assess generalization, 200 test signals were synthesized with AudioLDM using real siren and road noise recordings as inputs. On this test set, the proposed system outperformed the reference classifiers and, when compared with state-of-the-art methods reported in the literature, achieved competitive accuracy while preserving low complexity. Full article

Network trace is a comprehensive record of data packets traversing a computer network, serving as a critical resource for analyzing network behavior. However, in practice, the limited availability of high-quality network traces, coupled with the presence of sensitive information such as IP addresses and MAC addresses, poses significant challenges to advancing network trace analysis. To address these issues, this paper focuses on network trace synthesis in two practical scenarios: (1) data expansion, where users create synthetic traces internally to diversify and enhance existing network trace utility; (2) data release, where synthesized network traces are shared externally. Inspired by the powerful generative capabilities of latent diffusion models (LDMs), this paper introduces NetSynDM, which leverages LDM to address the challenges of network trace synthesis in data expansion scenarios. To address the challenges in the data release scenario, we integrate differential privacy (DP) mechanisms into NetSynDM, introducing DPNetSynDM, which leverages DP Stochastic Gradient Descent (DP-SGD) to update NetSynDM, incorporating privacy-preserving noise throughout the training process. Experiments on five widely used network trace datasets show that our methods outperform prior works. NetSynDM achieves an average 166.1% better performance in fidelity compared to baselines. DPNetSynDM strikes an improved balance between privacy and fidelity, surpassing previous state-of-the-art network trace synthesis method fidelity scores of 18.4% on UGR16 while reducing privacy risk scores by approximately 9.79%. Full article

Recent advancements in generative artificial intelligence have significantly progressed the field of text-to-music generation, enabling users to create music from natural language descriptions. Despite the success of various models, such as MusicLM, MusicGen, and AudioLDM, the current approaches struggle to capture fine-grained genre-specific characteristics, precisely control musical attributes, and handle underrepresented cultural data. This paper introduces a novel, lightweight fine-tuning method for the AudioLDM framework using low-rank adaptation (LoRA). By updating only selected attention and projection layers, the proposed method enables efficient adaptation to musical genres with limited data and computational cost. The proposed method enhances controllability over key musical parameters such as rhythm, emotion, and timbre. At the same time, it maintains the overall quality of music generation. This paper represents the first application of LoRA in AudioLDM, offering a scalable solution for fine-grained, genre-aware music generation and customization. The experimental results demonstrate that the proposed method improves the semantic alignment and statistical similarity compared with the baseline. The contrastive language–audio pretraining score increased by 0.0498, indicating enhanced text-music consistency. The kernel audio distance score decreased by 0.8349, reflecting improved similarity to real music distributions. The mean opinion score ranged from 3.5 to 3.8, confirming the perceptual quality of the generated music. Full article

Traditional map style transfer methods are mostly based on GAN, which are either overly artistic at the expense of conveying information, or insufficiently aesthetic by simply changing the color scheme of the map image. These methods often struggle to balance style transfer with semantic preservation and lack consistency in their transfer effects. In recent years, diffusion models have made significant progress in the field of image processing and have shown great potential in image-style transfer tasks. Inspired by these advances, this paper presents a method for transferring real-world 3D scenes to a cartoon style without the need for additional input condition guidance. The method combines pre-trained LDM with LoRA models to achieve stable and high-quality style infusion. By integrating DDIM Inversion, ControlNet, and MultiDiffusion strategies, it achieves the cartoon style transfer of real-world 3D scenes through initial noise control, detail redrawing, and global coordination. Qualitative and quantitative analyses, as well as user studies, indicate that our method effectively injects a cartoon style while preserving the semantic content of the real-world 3D scene, maintaining a high degree of consistency in style transfer. This paper offers a new perspective for map style transfer. Full article

The worldwide increase in antifungal resistance, particularly in Candida sp., requires the exploration of novel therapeutic agents. Natural compounds have been a rich source of antimicrobial molecules, where peptides constitute the class of the most bioactive components. Therefore, this study looks into the target-specific binding efficacy of insect-derived antifungal peptides (n = 37) as possible alternatives to traditional antifungal treatments. Using computational methods, namely the HPEPDOCK and HDOCK platforms, molecular docking was performed to evaluate the interactions between selected key fungal targets, lanosterol 14-demethylase, or LDM (PDB ID: 5V5Z), secreted aspartic proteinase-5, or Sap-5 (PDB ID: 2QZX), N-myristoyl transferase, or NMT (PDB ID: 1NMT), and dihydrofolate reductase, or DHFR, of C. albicans. The three-dimensional peptide structure was modelled through the PEP-FOLD 3.5 tool. Further, we predicted the physicochemical properties of these peptides through the ProtParam and PEPTIDE 2.0 tools to assess their drug-likeness and potential for therapeutic applications. In silico results show that Blap-6 from Blaps rhynchopeter and Gomesin from Acanthoscurria gomesiana have the most antifungal potential against all four targeted proteins in Candida sp. Additionally, a molecular dynamics simulation study of LDM-Blap-6 was carried out at 100 nanoseconds. The overall predictions showed that both have strong binding abilities and are good candidates for drug development. In in vitro studies, Gomesin achieved complete biofilm eradication in three out of four Candida species, while Blap-6 showed moderate but consistent reduction across all species. C. tropicalis demonstrated relative resistance to complete eradication by both peptides. The present study provides evidence to support the antifungal activity of certain insect peptides, with potential to be used as alternative drugs or as a template for a new synthetic or modified peptide in pursuit of effective therapies against Candida spp. Full article

Canine morbillivirus (CDV), the cause of canine distemper, is a pathogen affecting many hosts. While modified live virus (MLV) vaccines are crucial for controlling the disease in dogs, cases of vaccine-related infections have been found in both domestic and wild animals. Specifically, the America-1 and Rockborn-like vaccine genotypes are concerning due to their spread and ability to transmit between different species. This study conducted a review and analysis of molecular detections of these strains in various carnivores (domestic, captive, synanthropic, and wild species). This study used a conceptual model considering host ecology and the domestic–wild interface to evaluate plausible transmission connections over time using Linear Directional Mean (LDM) and Weighted Mean Centre (WMC) methods. Statistical analyses examined the relationship between how likely a strain is to spread and factors like host type and vaccination status. The findings showed that the America-1 genotype spread in a more organised way, with domestic dogs being the main source and recipient, bridging different environments. Synanthropic mesocarnivores also played this same role, with less intensity. America-1 was most concentrated in the North Atlantic and Western Europe. In contrast, the Rockborn-like strain showed a more unpredictable and restricted spread, residual circulation from past use rather than ongoing spread. Species involved in vaccine-related infections often share characteristics like generalist behaviour, social living, and a preference for areas where domestic animals and wildlife interact. We did not find a general link between a host vaccination status and the likelihood of the strain spreading. The study emphasised the ongoing risk of vaccine-derived strains moving from domestic and synanthropic animals to vulnerable wild species, supporting the need for improved vaccination approaches. Mapping these plausible transmission routes can serve as a basis for targeted surveillance, not only of vaccine-derived strains, but of any other circulating genotype. Full article

Additive manufacturing (AM) has brought significant breakthroughs to the construction sector, such as the ability to fabricate complex geometries, enhance efficiency, and reduce both material usage and construction waste. However, several challenges must still be addressed to fully transition from conventional construction practices to innovative and sustainable green alternatives. This study investigates the use of non-cementitious traditional mixtures for green construction applications through 3D printing using Liquid Deposition Modeling (LDM) technology. To explore the development of mixtures with enhanced physical and mechanical properties, natural pine and cypress wood shavings were added in varying proportions (1%, 3%, and 5%) as sustainable additives. The aim of this study is twofold: first, to demonstrate the printability of these eco-friendly mortars that can be used for conservation purposes and overcome the challenges of incorporating bio-products in 3D printing; and second, to develop sustainable composites that align with the objectives of the European Green Deal, offering low-emission construction solutions. The proposed mortars use hydrated lime and natural pozzolan as binders, river sand as an aggregate, and a polycarboxylate superplasticizer. While most studies with bio-products focus on traditional methods, this research provides proof of concept for their use in 3D printing. The study results indicate that, at low percentages, both additives had minimal effect on the physical and mechanical properties of the tested mortars, whereas higher percentages led to progressively more significant deterioration. Additionally, compared to molded specimens, the 3D-printed mortars exhibited slightly reduced mechanical strength and increased porosity, attributable to insufficient compaction during the printing process. Full article

The development of Advanced Driver Assistance Systems (ADASs) has reached a stage where, in addition to the traditional challenges of path planning and control, there is an increasing focus on the behavior of these systems. Assistance functions shall be personalized to deliver a full user experience. Therefore, driver modeling is a key area of research for next-generation ADASs. One of the most common tasks in everyday driving is lane keeping. Drivers are assisted by lane-keeping systems to keep their vehicle in the center of the lane. However, human drivers often deviate from the center line. It has been shown that the driver’s choice to deviate from the center line can be modeled by a linear combination of preview curvature information. This model is called the Linear Driver Model. In this paper, we fit the LDM parameters to real driving data. The drivers are then clustered based on the individual parameters. It is shown that clusters are not only formed by the numerical similarity of the driver parameters, but the drivers in a cluster actually have similar behavior in terms of path selection. Finally, an Extended Kalman Filter (EKF) is proposed to learn the model parameters at run-time. Any new driver can be classified into one of the driver type groups. This information can be used to modify the behavior of the lane-keeping system to mimic human driving, resulting in a more personalized driving experience. Full article

Yunong Black (YN) pigs and Yunong Black × Landrace (YL) hybrid pigs exhibit significant differences in meat quality characteristics. Studies have suggested that extrachromosomal circular DNA (eccDNA) may play a regulatory role in muscle development. In order to study the differences in eccDNA between two groups with different meat quality traits and their potential biological significance, this study used the Circle-seq method to detect eccDNA in the longest dorsal muscle (LDM) of Yunong Black pigs (YN) (n = 3) and Yunong Black × Landrace hybrid pigs (YL) (n = 3). EccDNA-related differentially expressed genes (eccDEGs) were then analyzed in combination with RNA-seq to explore the mechanisms by which eccDNA affects meat quality. The results showed that 1325 and 1304 differentially expressed eccDNAs were identified in the YN and YL groups, varying in size and distributed across multiple genomic functional regions. These eccDNAs were also annotated according to several protein-coding genes. Combined analysis with RNA-seq results revealed 19 and 27 eccDEGs in the YN and YL groups. The Kyoto Encyclopedia of Genes and Genomes (KEGG) and Gene Ontology (GO) analysis enriched many lipid-related pathways, such as chemokine signals and ADP metabolic processes. By constructing a regulatory network, several potential regulatory networks that might be related to pork quality, for example, ecc_sus_8665/ssc-miR-212/ADAMTS16, were identified. In summary, we identified several potential eccDNAs that may regulate pig muscle, offering insights into the regulation of pig muscle traits for breeding. Full article

At the core of AI-driven electrocardiogram diagnosis lies the precise localization of the QRS complex. While QRS detection methods for multiple leads have been researched adequately in the last few decades, their multi-lead strategies still need to be designed manually. Therefore, a QRS detector that can fuse multiple leads automatically is still worth investigating. Methods: The proposed QRS detector comprises a leads-distillation module (LDM) and a QRS detection module. The LDM can distill multi-lead signals into single-lead ones. This procedure minimizes the weight proportions assigned to noisy leads, enabling the network to generate a novel signal that facilitates the recognition of QRS waves. The QRS detection module, utilizing U-Net, is capable of discerning QRS complexes from the novel signal. Results: Our method demonstrates outstanding performance with a parameter count of only 5216. It achieves an excellent F1 score of 99.83 on the MITBIHA database and 99.77 on the INCART database, specifically in the inter-patient pattern. In the cross-database pattern, our approach maintains a strong performance with an F1 score of 99.22 on the INCART database and an F1 score of 99.09 on the MITBIHA database. Conclusion: Our method provides a novel idea for universal multi-lead QRS detection. It possesses advantages, such as reduced computational parameters, enhanced precision, and heightened compatibility. Significance: Our method canceled the repeated deployment of the QRS detection function to different lead configurations in the electrocardiogram (ECG) diagnostic system. Moreover, the scaling operation may become a simple tool to decrease the computational load of the network. Full article