Search Results (9,733)

With the rapid development of China’s tourism industry, the homogenization of regional tourism images has become a growing concern. To address this, this study quantifies the similarities and differences in tourism image perception across China’s 31 provinces, focusing on 350 5A-level destinations, analyzing 757,046 tourist reviews collected from Ctrip.com in 2024. Using a three-dimensional framework (cognitive, affective, and overall image), we analyze social media data through natural language processing, random forest regression, and social network analysis. Key findings include the following: (1) most comments are positive, with Jiangsu and Chongqing showing high cognitive image similarity but low overall similarity; (2) cognitive image significantly impacts affective image, especially through unique tourism resources; (3) an inter-provincial similarity–difference matrix reveals significant perceptual differences among provinces. This study provides a novel methodological approach for multidimensional image evaluation and offers crucial empirical insights for regional policy-making aimed at optimizing land and tourism resource allocation, balancing regional disparities, and promoting sustainable land use and development across China. Full article

This paper presents an automatic system for the classification of musical instruments from audio recordings. The project leverages deep learning (DL) techniques to achieve its objective, exploring three different classification approaches based on distinct input representations. The first method involves the extraction of Mel-Frequency Cepstral Coefficients (MFCCs) from the audio files, which are then fed into a two-dimensional convolutional neural network (Conv2D). The second approach makes use of mel-spectrogram images as input to a similar Conv2D architecture. The third approach employs conventional machine learning (ML) classifiers, including Logistic Regression, K-Nearest Neighbors, and Random Forest, trained on MFCC-derived feature vectors. To gain insight into the behavior of the DL model, explainability techniques were applied to the Conv2D model using mel-spectrograms, allowing for a better understanding of how the network interprets relevant features for classification. Additionally, t-distributed stochastic neighbor embedding (t-SNE) was employed on the MFCC vectors to visualize how instrument classes are organized in the feature space. One of the main challenges encountered was the class imbalance within the dataset, which was addressed by assigning class-specific weights during training. The results, in terms of classification accuracy, were very satisfactory across all approaches, with the convolutional models and Random Forest achieving around 97–98%, and Logistic Regression yielding slightly lower performance. In conclusion, the proposed methods proved effective for the selected dataset, and future work may focus on further improving class balance techniques. Full article

Background: Multiple high-powered magnet ingestion is a surgical emergency due to inter-loop attraction leading to ischemia, necrosis, perforation, and fistula formation. While well documented in children, adult cases—particularly those complicated by entero-enteric fistula—remain rare, and management is largely extrapolated from pediatric guidelines. Objective: To present a rare case of adult entero-enteric fistula following multiple neodymium magnet ingestion, we review the literature and propose an adapted management algorithm for adults. Methods: A narrative PubMed review was performed to identify pediatric and adult cases of magnet ingestion complicated by gastrointestinal fistula. Search terms included magnet ingestion, entero-enteric fistula, neodymium, and adult. Reported case characteristics, diagnostic modalities, treatments, and outcomes were analyzed. Results: A 38-year-old male with schizophrenia presented with small bowel obstruction five days after ingesting multiple magnets. Abdominal radiography revealed clustered radiopaque bodies in the distal ileum. Emergency laparotomy identified an entero-enteric fistula caused by pressure necrosis from inter-loop magnetic attraction. Segmental enterectomy with side-to-side anastomosis was performed, with uneventful recovery. The literature review identified only a few adult cases, which showed similar pathophysiology but frequent diagnostic delays and higher complication rates compared with pediatric cases. Conclusions: This case adds to the scarce adult literature on magnet-induced entero-enteric fistula and supports the adaptation of pediatric-based protocols for adults, with attention paid to psychiatric comorbidity and delayed presentation. Early imaging, timely intervention, and multidisciplinary care are essential to prevent severe gastrointestinal injury. Full article

Fractional-order chaotic systems have emerged as powerful tools in secure communications and multimedia protection owing to their memory-dependent dynamics, large key spaces, and high sensitivity to initial conditions. However, most existing fractional-order image encryption schemes rely on fixed-order chaos and conventional solvers, which limit their complexity and reduce unpredictability, while also neglecting the potential of variable fractional-order (VFO) dynamics. Although similar phenomena have been reported in some fractional-order systems, the coexistence of hidden attractors and stable equilibria has not been extensively investigated within VFO frameworks. To address these gaps, this paper introduces a novel discrete variable fractional-order dark matter–dark energy (VFODM-DE) chaotic system. The system is discretized using the piecewise constant argument discretization (PWCAD) method, enabling chaos to emerge at significantly lower fractional orders than previously reported. A comprehensive dynamic analysis is performed, revealing rich behaviors such as multistability, symmetry properties, and hidden attractors coexisting with stable equilibria. Leveraging these enhanced chaotic features, a pseudorandom number generator (PRNG) is constructed from the VFODM-DE system and applied to grayscale image encryption through permutation–diffusion operations. Security evaluations demonstrate that the proposed scheme offers a substantially large key space (approximately $2^{249}$) and exceptional key sensitivity. The scheme generates ciphertexts with nearly uniform histograms, extremely low pixel correlation coefficients (less than 0.04), and high information entropy values (close to 8 bits). Moreover, it demonstrates strong resilience against differential attacks, achieving average NPCR and UACI values of about 99.6% and 33.46%, respectively, while maintaining robustness under data loss conditions. In addition, the proposed framework achieves a high encryption throughput, reaching an average speed of 647.56 Mbps. These results confirm that combining VFO dynamics with PWCAD enriches the chaotic complexity and provides a powerful framework for developing efficient and robust chaos-based image encryption algorithms. Full article

Background: Amino acid tracer positron emission tomography–magnetic resonance imaging (PET-MRI) was shown to be superior to MRI alone for evaluating central nervous system (CNS) tumours in adults. This study aimed to investigate the utility of amino acid PET-MRI in children with CNS tumours. Methods: We reviewed the amino acid PET-MRI findings of children with suspected or confirmed CNS neoplasms managed in a territory-wide referral centre in Hong Kong from 2022 to 2025. Maximal standardized uptake values (SUVmax) were captured, and tumour-to-background SUVmax ratios (TBRmax) were measured with reference to adjacent or contralateral normal brain structures. Comparisons were made among patients with clinical high-grade and low-grade/non-neoplastic lesions. Results: Thirty-seven patients were included, with 63 PET-MRIs performed. PET-MRI was performed as part of initial diagnostics in 41% of the cases, for response assessment in 48%, and evaluation of residual/relapsed disease in 11%. High-grade lesions had a significantly higher SUVmax and TBRmax compared to low-grade/non-malignant lesions (median SUVmax 3.7 vs. 1.6, p = 0.00006; median TBRmax 2.06 vs. 0.91, p = 0.00002). Optimal SUVmax and TBRmax cut-offs by ROC analysis were 2.38 and 1.62, respectively. Similar performance was reproduced by focusing on the subset of patients with suspected CNS germ cell tumours (CNS-GCT). The impact of amino acid PET availability is considerable, as clinical management was modified in 65% of patients. Conclusions: Our study demonstrates the performance and clinical utility of amino acid PET-MRI in the management of children with CNS pathologies. Amino acid PET-MRI contributes to the diagnosis, monitoring, and treatment guidance of these patients, providing crucial information for decision-making. Full article

Coastal debris is a global environmental issue that requires systematic monitoring strategies based on reliable statistical data. Recent advances in remote sensing and deep learning-based object detection have enabled the development of efficient coastal debris monitoring systems. In this study, two state-of-the-art object detection models—RT-DETR and YOLOv10—were applied to UAV-acquired images for coastal debris detection. Their false positive characteristics were analyzed to provide guidance on model selection under different coastal environmental conditions. Quantitative evaluation using mean average precision (mAP@0.5) showed comparable performance between the two models (RT-DETR: 0.945, YOLOv10: 0.957). However, bounding box label accuracy revealed a significant gap, with RT-DETR achieving 80.18% and YOLOv10 only 53.74%. Class-specific analysis indicated that both models failed to detect Metal and Glass and showed low accuracy for fragmented debris, while buoy-type objects with high structural integrity (Styrofoam Buoy, Plastic Buoy) were consistently identified. Error analysis further revealed that RT-DETR tended to overgeneralize by misclassifying untrained objects as similar classes, whereas YOLOv10 exhibited pronounced intra-class confusion in fragment-type objects. These findings demonstrate that mAP alone is insufficient to evaluate model performance in real-world coastal monitoring. Instead, model assessment should account for training data balance, coastal environmental characteristics, and UAV imaging conditions. Future studies should incorporate diverse coastal environments and apply dataset augmentation to establish statistically robust and standardized monitoring protocols for coastal debris. Full article

Current deep learning-based dense target detection models face dual challenges in industrial scenarios: high computational complexity leading to insufficient inference efficiency on mobile devices, and missed/false detections caused by dense small targets, high inter-class similarity, and complex background interference. To address these issues, this paper proposes DBA-YOLO, a lightweight model based on YOLOv10, which significantly reduces computational complexity through model compression and algorithm optimization while maintaining high accuracy. Key improvements include the following: (1) a C2f PA module for enhanced feature extraction, (2) a parameter-refined BIMAFPN neck structure to improve small target detection, and (3) a DyDHead module integrating scale, space, and task awareness for spatial feature weighting. To validate DBA-YOLO, we constructed a real-world dataset from cigarette package images. Experiments on SKU-110K and our dataset show that DBA-YOLO achieves 91.3% detection accuracy (1.4% higher than baseline), with mAP and mAP75 improvements of 2–3%. Additionally, the model reduces parameters by 3.6%, balancing efficiency and performance for resource-constrained devices. Full article

In existing non-satellite navigation systems, visual localization is widely adopted for its high precision. However, in scenarios with highly similar building structures, traditional visual localization methods that rely on direct coordinate prediction often suffer from decreased accuracy or even failure. Moreover, as scene complexity increases, their robustness tends to decline. To address these challenges, this paper proposes a Sketch Line Information Consistency Generation (SLIC) model for indirect building localization. Instead of regressing geographic coordinates, the model retrieves candidate building images that correspond to hand-drawn sketches, and these retrieved results serve as proxies for localization in satellite-denied environments. Within the model, the Line-Attention Block and Relation Block are designed to extract fine-grained line features and structural correlations, thereby improving retrieval accuracy. Experiments on multiple architectural datasets demonstrate that the proposed approach achieves high precision and robustness, with mAP@2 values ranging from 0.87 to 1.00, providing a practical alternative to conventional coordinate-based localization methods. Full article

The proposed study explores the consistency of the geometrical character of surfaces under scaling, rotation and translation. In addition to its mathematical significance, it also exhibits advantages over image processing and economic applications. In this paper, the authors used partition-based principal component analysis similar to two-dimensional Sub-Image Principal Component Analysis (SIMPCA), along with a suitably modified atypical wavelet transform in the classification of 2D images. The proposed framework is further extended to three-dimensional objects using machine learning classifiers. To strengthen fairness, we benchmarked against both Random Forest (RF) and Support Vector Machine (SVM) classifiers using nested cross-validation, showing consistent gains when TIFV is included. In addition, we carried out a robustness analysis by introducing Gaussian noise to the intensity channel, confirming that TIFV degrades much more gracefully compared to traditional descriptors. Experimental results demonstrate that the method achieves improved performance compared to traditional hand-crafted descriptors such as measured values and histogram of oriented gradients. In addition, it is found to be useful that this proposed algorithm is capable of establishing consistency locally, which is never possible without partition. However, a reasonable amount of computational complexity is reduced. We note that comparisons with deep learning baselines are beyond the scope of this study, and our contribution is positioned within the domain of interpretable, affine-invariant descriptors that enhance classical machine learning pipelines. Full article

(1) Background: The extracellular matrix (ECM) is a natural scaffold for cells, creating a three-dimensional architecture composed of fibrous proteins (mainly collagen) and proteoglycans, which are synthesized by resident cells. In this study, a physiological hypoxic environment was utilized to enhance ECM production by human mesenchymal stem cells (hMSCs), a process relevant to tissue engineering and regenerative medicine. (2) Methods: hMSCs were treated with deferoxamine (DFO), a pharmaceutical hypoxia-mimetic agent that induces cellular responses similar to low-oxygen conditions through stabilization of hypoxia inducible factor-1α (HIF-1α). The time points 0 h 24 h, 3 h 24 h, and 24 h 24 h refer to DFO being added immediately after cell seeding (before cells adhesion), 3 h after cell seeding (during initial cells attachment), and 24 h after cell seeding (after focal adhesions formation and actin organization), respectively, to evaluate the influence of cell adhesion on ECM deposition. hMSCs incubated in culture media were subsequently exposed to DFO for 24 h. Samples were then subjected to cell viability tests, scanning electron microscopy (SEM), atomic force microscopy (AFM) and laser scanning confocal microscopy (CLSM) assessments. (3) Results: Viability tests indicated that DFO concentrations in the range of 0–300 µM were non-toxic over 24 h. The presence of collagen fibers in the DFO-derived ECM was confirmed with anti-collagen antibodies under CLSM. Increased ECM secretion was observed under the following conditions: 3 μM DFO (24 h 24 h), 100 μM DFO (0 h 24 h) and 300 μM DFO (3 h 24 h). SEM and AFM images revealed the morphology of various stages of collagen formation with both collagen fibrils and fibers identified. (4) Conclusions: Our preliminary study demonstrated enhanced ECM secretion by hMSC treated with DFO at concentrations of 3, 100, and 300 µM within a short cultivation period of 24–48 h without significant affecting cell viability. By mimicking physiological processes, it may be possible to stimulate endogenous tissue regeneration, for example, at an injury site. Full article

Unmanned aerial vehicles (UAVs) have become a tool for solving numerous practical tasks. UAV sensors provide images and videos for on-line or off-line data processing for object localization, classification, and tracking due to the use of trained convolutional neural networks (CNNs) and artificial intelligence. However, quality of images acquired by UAV-based sensors is not always perfect due to many factors. One of them could be noise arising because of several reasons. Its presence, especially if noise is intensive, can make significantly worse the performance characteristics of CNN-based techniques of object localization and classification. We analyze such degradation for a set of eleven modern CNNs for additive white Gaussian noise model and study when (for what noise intensity and for what CNN) the performance reduction becomes essential and, thus, special means to improve it become desired. Representatives of two most popular families, namely the block matching 3-dimensional (BM3D) filter and DRUNet denoiser, are employed to enhance images under condition of a priori known noise properties. It is shown that, due to preliminary denoising, the CNN performance characteristics can be significantly improved up to almost the same level as for the noise-free images without CNN retraining. Performance is analyzed using several criteria typical for image denoising, object localization and classification. Examples of object localization and classification are presented demonstrating possible object missing due to noise. Computational efficiency is also taken into account. Using a large set of test data, it is demonstrated that: (1) the best results are usually provided for SSD Mobilenet V2 and VGG16 networks; (2) the performance characteristics for cases of applying BM3D filter and DRUNet denoiser are similar but the use of DRUNet is preferable since it provides slightly better results. Full article

Background/Objectives: Preclinical chest computed tomography (CT) imaging in small animals is often limited by low resolution due to scan time and dose constraints, which hinders accurate detection of subtle lesions. Traditional super-resolution (SR) metrics, such as peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM), may not adequately reflect clinical interpretability. We aimed to evaluate whether deep learning-based SR models could enhance image quality and lesion detectability in rat chest CT, balancing quantitative metrics with radiologist assessment. Methods: We retrospectively analyzed 222 chest CT scans acquired from polyhexamethylene guanidine phosphate (PHMG-p) exposure studies in Sprague Dawley rats. Three SR models were implemented and compared: single-image SR (SinSR), segmentation-guided SinSR with lung cropping (SinSR3), and omni-super-resolution (OmniSR). Models were trained on rat CT data and evaluated using PSNR and SSIM. Two board-certified thoracic radiologists independently performed blinded evaluations of lesion margin clarity, nodule detectability, image noise, artifacts, and overall image quality. Results: SinSR1 achieved the highest PSNR (33.64 ± 1.30 dB), while SinSR3 showed the highest SSIM (0.72 ± 0.08). Despite lower PSNR (29.21 ± 1.46 dB), OmniSR received the highest radiologist ratings for lesion margin clarity, nodule detectability, and overall image quality (mean score 4.32 ± 0.41, κ = 0.74). Reader assessments diverged from PSNR and SSIM, highlighting the limited correlation between conventional metrics and clinical interpretability. Conclusions: Deep learning-based SR improved visualization of rat chest CT images, with OmniSR providing the most clinically interpretable results despite modest numerical scores. These findings underscore the need for reader-centered evaluation when applying SR techniques to preclinical imaging. Full article

Background: Bladder cancer (BLCA) is a malignant growth that originates from the urothelial lining of the urinary bladder. Diagnosing BLCA is complex due to the variety of tumor features and its heterogeneous nature, which leads to significant morbidity and mortality. Understanding tumor histopathology is crucial for developing tailored therapies and improving patient outcomes. Objectives: Early diagnosis and treatment are essential to lower the mortality rate associated with bladder cancer. Manual classification of muscular tissues by pathologists is labor-intensive and relies heavily on experience, which can result in interobserver variability due to the similarities in cancerous cell morphology. Traditional methods for analyzing endoscopic images are often time-consuming and resource-intensive, making it difficult to efficiently identify tissue types. Therefore, there is a strong demand for a fully automated and reliable system for classifying smooth muscle images. Methods: This paper proposes a deep learning (DL) technique utilizing the EfficientNet-B3 model and a five-fold cross-validation method to assist in the early detection of BLCA. This model enables timely intervention and improved patient outcomes while streamlining the diagnostic process, ultimately reducing both time and costs for patients. We conducted experiments using the Endoscopic Bladder Tissue Classification (EBTC) dataset for multiclass classification tasks. The dataset was preprocessed using resizing and normalization methods to ensure consistent input. In-depth experiments were carried out utilizing the EBTC dataset, along with ablation studies to evaluate the best hyperparameters. A thorough statistical analysis and comparisons with five leading DL models—ConvNeXtBase, DenseNet-169, MobileNet, ResNet-101, and VGG-16—showed that the proposed model outperformed the others. Conclusions: The EfficientNet-B3 model achieved impressive results: accuracy of 99.03%, specificity of 99.30%, precision of 97.95%, recall of 96.85%, and an F1-score of 97.36%. These findings indicate that the EfficientNet-B3 model demonstrates significant potential in accurately and efficiently diagnosing BLCA. Its high performance and ability to reduce diagnostic time and cost make it a valuable tool for clinicians in the field of oncology and urology. Full article

Background/Objectives: The spinal cord is a critical component of the central nervous system that transmits neural signals between the brain and the body’s peripheral regions through its nerve roots. Despite being partially protected by the vertebral column, the spinal cord remains highly vulnerable to trauma, tumors, infections, and degenerative or inflammatory disorders. These conditions can disrupt neural conduction, resulting in severe functional impairments, such as paralysis, motor deficits, and sensory loss. Therefore, accurate and comprehensive spinal cord segmentation is essential for characterizing its structural features and evaluating neural integrity. Methods: In this study, we propose a fully automated method for segmentation of the cervical spinal cord in sagittal magnetic resonance (MR) images. This method facilitates rapid clinical evaluation and supports early diagnosis. Our approach uses a Swin-Unet architecture, which integrates vision transformer blocks into the U-Net framework. This enables the model to capture both local anatomical details and global contextual information. This design improves the delineation of the thin, curved, low-contrast cervical cord, resulting in more precise and robust segmentation. Results: In experimental studies, the proposed Swin-Unet model (SWU1), which uses transformer blocks in the encoder layer, achieved Dice Similarity Coefficient (DSC) and Hausdorff Distance 95 (HD95) scores of 0.9526 and 1.0707 mm, respectively, for cervical spinal cord segmentation. These results confirm that the model can consistently deliver precise, pixel-level delineations that are structurally accurate, which supports its reliability for clinical assessment. Conclusions: The attention-enhanced Swin-Unet architecture demonstrated high accuracy in segmenting thin and complex anatomical structures, such as the cervical spinal cord. Its ability to generalize with limited data highlights its potential for integration into clinical workflows to support diagnosis, monitoring, and treatment planning. Full article

To explore the coupling between agricultural farming models and surface water environmental in central China’s irrigation districts, this study focuses on the Four Lakes Basin within Jianghan Plain, a key grain-producing and ecological protection area. Integrating remote sensing images, statistical yearbooks, and on-site monitoring data, the study analyzed the phased characteristics of the basin’s agricultural pattern transformation, the changes in non-point source nitrogen and phosphorus loads, and the responses of water quality in main canals and Honghu Lake to agricultural adjustments during the period 2010~2023. The results showed that the basin underwent a significant transformation in agricultural patterns from 2016 to 2023: the area of rice-crayfish increased by 14%, while the areas of dryland crops and freshwater aquaculture decreased by 11% and 4%, respectively. Correspondingly, the non-point source nitrogen and phosphorus loads in the Four Lakes Basin decreased by 11~13%, and the nitrogen and phosphorus concentrations in main canals decreased slightly by approximately 2 mg/L and 0.04 mg/L, respectively; however, the water quality of Honghu Lake continued to deteriorate, with nitrogen and phosphorus concentrations increasing by approximately 0.46 mg/L and 0.06 mg/L, respectively. This indicated that the adjustment of agricultural farming models was beneficial to improving the water quality of main canals, but it did not bring about a substantial improvement in the sustainable development of Honghu Lake. This may be related to various factors that undermine the sustainability of the lake’s aquatic ecological environment, such as climate change, natural disasters, internal nutrient release from sediments, and the decline in water environment carrying capacity. Therefore, to advance sustainability in this basin and similar irrigation districts, future efforts should continue optimizing agricultural models to reduce nitrogen/phosphorus inputs, while further mitigating internal nutrient release and climate disaster risks, restoring aquatic vegetation, and enhancing water environment carrying capacity. Full article