Search Results (146)

Thyroid nodules, prevalent in 2% to 65% of the general population depending on diagnostic methodology, represent a significant clinical concern despite a low malignancy rate, typically 1% to 5%. A substantial proportion of thyroid cancers are small, indolent lesions, allowing for conservative management with favorable prognoses. Nodule detection commonly occurs via palpation, clinical examination, or incidental radiological findings. Established risk factors include advanced age, female gender, obesity, metabolic syndrome, and estrogen dominance. Despite conservative management potential, a considerable number of thyroid nodules in Europe are unnecessarily referred for surgery, incurring unfavorable risk-to-benefit ratios and increased costs. Minimally invasive techniques (MITs), encompassing ethanol and thermal ablation modalities (e.g., laser, radiofrequency, microwave), offer outpatient, nonsurgical management for symptomatic or cosmetically concerning thyroid lesions. These procedures, performed under ultrasound guidance without general anesthesia, are associated with low complication rates. MITs effectively achieve substantial and sustained nodule volume reduction (57–77% at 5 years), correlating with improved local symptoms. Thermal ablation (TA) is particularly favored for solid thyroid lesions due to its precise and predictable tissue destruction. Optimal TA balances near-complete nodule eradication to prevent recurrence with careful preservation of adjacent anatomical structures to minimize complications. Radiofrequency ablation (RFA) is widely adopted, while microwave ablation (MWA) presents a promising alternative addressing RFA limitations. Percutaneous laser ablation (LA), an early image-guided thyroid ablation technique, remains a viable option for benign, hyperfunctioning, and malignant thyroid pathologies. This review comprehensively evaluates RFA, MWA, and LA for thyroid nodule treatment, assessing current evidence regarding their efficacy, safety, comparative outcomes, side effects, and outlining future research directions. Full article

This study investigates the comparative performance of foundational models, advanced large-kernel architectures, and traditional deep learning approaches for hyperpolarized gas MRI segmentation across progressive data reduction scenarios. Chronic obstructive pulmonary disease (COPD) remains a leading global health concern, and advanced imaging techniques are crucial for its diagnosis and management. Hyperpolarized gas MRI, utilizing helium-3 (³He) and xenon-129 (¹²⁹Xe), offers a non-invasive way to assess lung function. We evaluated foundational models (Segment Anything Model and MedSAM), advanced architectures (UniRepLKNet and TransXNet), and traditional deep learning models (UNet with VGG19 backbone, Feature Pyramid Network with MIT-B5 backbone, and DeepLabV3 with ResNet152 backbone) using four data availability scenarios: 100%, 50%, 25%, and 10% of the full training dataset (1640 2D MRI slices from 205 participants). The results demonstrate that foundational and advanced models achieve statistically equivalent performance across all data scenarios (p > 0.01), while both significantly outperform traditional architectures under data constraints (p < 0.001). Under extreme data scarcity (10% training data), foundational and advanced models maintained DSC values above 0.86, while traditional models experienced catastrophic performance collapse. This work highlights the critical advantage of architectures with large effective receptive fields in medical imaging applications where data collection is challenging, demonstrating their potential to democratize advanced medical imaging analysis in resource-limited settings. Full article

Arrhythmias are a common and potentially life-threatening category of cardiac disorders, making accurate and early detection crucial for improving clinical outcomes. Electrocardiograms are widely used to monitor heart rhythms, yet their manual interpretation remains prone to inconsistencies due to the complexity of the signals. This research investigates the effectiveness of machine learning and deep learning techniques for automated arrhythmia classification using ECG signals from the MIT-BIH dataset. We compared Gradient Boosting Machine (GBM) and Multilayer Perceptron (MLP) as traditional machine learning models with a hybrid deep learning model combining one-dimensional convolutional neural networks (1D-CNNs) and long short-term memory (LSTM) networks. Furthermore, the Grey Wolf Optimizer (GWO) was utilized to automatically optimize the hyperparameters of the 1D-CNN-LSTM model, enhancing its performance. Experimental results show that the proposed 1D-CNN-LSTM model achieved the highest accuracy of 97%, outperforming both classical machine learning and other deep learning baselines. The classification report and confusion matrix confirm the model’s robustness in identifying various arrhythmia types. These findings emphasize the possible benefits of integrating metaheuristic optimization with hybrid deep learning. Full article

Indoor scene recognition is a computer vision task that identifies various indoor environments, such as offices, libraries, kitchens, and restaurants. This research area is particularly significant for applications in robotics, security, and assistance for individuals with disabilities, as it enables the categorization of spaces and the provision of contextual information. Convolutional Neural Networks (CNNs) are commonly employed in this field. While CNNs perform well in outdoor scene recognition by focusing on global features such as mountains and skies, they often struggle with indoor scenes, where local features like furniture and objects are more critical. In this study, the “MIT 67 Indoor Scene” dataset is used to extract and combine features from both a CNN and a text-based model utilizing object recognition outputs, resulting in a two-channel hybrid model. The experimental results demonstrate that this hybrid approach, which integrates natural language processing and image processing techniques, improves the test accuracy of the image processing model by 8.3%, achieving a notable success rate. Furthermore, this study offers contributions to new application areas in remote sensing, particularly in indoor scene understanding and indoor mapping. Full article

Ventricular arrhythmias such as ventricular fibrillation (VF) and ventricular tachycardia (VT) are among the leading causes of sudden cardiac death worldwide, making their timely and accurate detection a critical task in modern cardiology. This study presents an advanced framework for the automatic detection of critical cardiac arrhythmias—specifically ventricular fibrillation (VF) and ventricular tachycardia (VT)—by integrating deep learning techniques with neuro-fuzzy systems. Electrocardiogram (ECG) signals from the MIT-BIH and AHA databases were preprocessed through denoising, alignment, and segmentation. Convolutional neural networks (CNNs) were employed for deep feature extraction, and the resulting features were used as input for various fuzzy classifiers, including Fuzzy ARTMAP and the Adaptive Neuro-Fuzzy Inference System (ANFIS). Among these classifiers, ANFIS demonstrated the best overall performance. The combination of CNN-based feature extraction with ANFIS yielded the highest classification accuracy across multiple cardiac rhythm types. The classification performance metrics for each rhythm type were as follows: for Normal Sinus Rhythm, precision was 99.09%, sensitivity 98.70%, specificity 98.89%, and F1-score 98.89%. For VF, precision was 95.49%, sensitivity 96.69%, specificity 99.10%, and F1-score 96.09%. For VT, precision was 94.03%, sensitivity 94.26%, specificity 99.54%, and F1-score 94.14%. Finally, for Other Rhythms, precision was 97.74%, sensitivity 97.74%, specificity 99.40%, and F1-score 97.74%. These results demonstrate the strong generalization capability and precision of the proposed architecture, suggesting its potential applicability in real-time biomedical systems such as Automated External Defibrillators (AEDs), Implantable Cardioverter Defibrillators (ICDs), and advanced cardiac monitoring technologies. Full article

Pumping station structures are widely employed to supply circulating cooling water systems in nuclear power plants (NPPs) throughout China. Investigating their seismic performance under complex heterogeneous site conditions and load scenarios is paramount to meeting nuclear safety design requirements. This study proposes and implements a novel, efficient, and accurate viscous-spring boundary methodology within the ANSYS 19.1 finite element software to assess the seismic safety of NPP pumping station structures. The Maximum Initial Time-step (MIT) method, based on Newmark’s integration scheme, is employed for nonlinear analysis under coupled static–dynamic excitation. To account for radiation damping in the infinite foundation, a Compact Viscous-Spring (CVs) element is developed. This element aggregates stiffness and damping contributions to interface nodes defined at the outer border of the soil domain. Implementation leverages of ANSYS User Programmable Features (UPFs), and a comprehensive static–dynamic coupled analysis toolkit is developed using APDL scripting and the GUI. Validation via two examples confirms the method’s accuracy and computational efficiency. Finally, a case study applies the technique to an NPP pumping station under actual complex Chinese site conditions. The results demonstrate the method’s capability to provide objective seismic response and stability indices, enabling a more reliable assessment of seismic safety during a Safety Shutdown Earthquake (SSE). Full article

Accurate classification of cardiac arrhythmias remains a crucial task in biomedical signal processing. This study proposes a hybrid deep learning approach called 1D CNN-eGRU that integrates one-dimensional convolutional neural network models (1D CNN) and a gated recurrent unit (GRU) architecture with an attention mechanism for the precise classification of cardiac arrhythmias based on ECG Lead II signals. To enhance the classification of cardiac arrhythmias, we also address data imbalances in the MIT-BIH arrhythmia dataset by introducing a hybrid data balancing method that blends resampling and class-weight learning. Additionally, we apply Sig-LIME, a refined variant of LIME tailored for signal datasets, to provide comprehensive insights into model decisions. The suggested hybrid 1D CNN-eGRU approach, a fusion of 1D CNN-GRU along with an attention mechanism, is designed to acquire intricate temporal and spatial dependencies in ECG signals. It aims to distinguish between four distinct arrhythmia classes from the MIT-BIH dataset, addressing a significant challenge in medical diagnostics. Demonstrating strong performance, the proposed hybrid 1D CNN-eGRU model achieves an overall accuracy of 0.99, sensitivity of 0.93, and specificity of 0.99. Per-class evaluation shows precision ranging from 0.80 to 1.00, sensitivity from 0.83 to 0.99, and F1-scores between 0.82 and 0.99 across four arrhythmia types (normal, supraventricular, ventricular, and fusion). The model also attains an AUC of 1.00 on average, with a final test loss of 0.07. These results not only demonstrate the model’s effectiveness in arrhythmia classification but also underscore the added value of interpretability enabled through the use of the Sig-LIME technique. Full article

Rapid urbanization has intensified global settlement density, significantly increasing the importance of urban street environmental quality, which profoundly affects residents’ physical and psychological well-being. Traditional methods for evaluating urban environmental quality have largely overlooked dynamic perceptual changes occurring throughout the day, resulting in incomplete assessments. To bridge this methodological gap, this study presents an innovative approach combining advanced deep learning techniques with time-series street view imagery (SVI) analysis to systematically quantify spatio-temporal variations in the perceived environmental quality of pedestrian-oriented streets. It further addresses two central questions: how perceived environmental quality varies spatially across sections of a pedestrian-oriented street and how these perceptions fluctuate temporally throughout the day. Utilizing Golden Street, a representative living street in Shanghai’s Changning District, as the empirical setting, street view images were manually collected at 96 sampling points across multiple time intervals within a single day. The collected images underwent semantic segmentation using the DeepLabv3+ model, and emotional scores were quantified through the validated MIT Place Pulse 2.0 dataset across six subjective indicators: “Safe,” “Lively,” “Wealthy,” “Beautiful,” “Depressing,” and “Boring.” Spatial and temporal patterns of these indicators were subsequently analyzed to elucidate their relationships with environmental attributes. This study demonstrates the effectiveness of integrating deep learning models with time-series SVI for assessing urban environmental perceptions, providing robust empirical insights for urban planners and policymakers. The results emphasize the necessity of context-sensitive, temporally adaptive urban design strategies to enhance urban livability and psychological well-being, ultimately contributing to more vibrant, secure, and sustainable pedestrian-oriented urban environments. Full article

Background/Objectives: Accurate segmentation of brain stroke lesions from MRI images is a critical task in medical image analysis that is essential for timely diagnosis and treatment planning. Methods: This paper presents a novel approach for segmenting brain stroke lesions using a deep learning model based on the U-Net neural network architecture. We enhanced the traditional U-Net by integrating a transformer-based backbone, specifically the Mix Vision Transformer (MiT), and compared its performance against other commonly used backbones such as ResNet and EfficientNet. Additionally, we implemented a 2.5D method, which leverages 2D networks to process three-dimensional data slices, effectively balancing the rich spatial context of 3D methods and the simplicity of 2D methods. The 2.5D approach captures inter-slice dependencies, leading to improved lesion delineation without the computational complexity of full 3D models. Utilizing the 2015 ISLES dataset, which includes MRI images and corresponding lesion masks for 20 patients, we conducted our experiments with 4-fold cross-validation to ensure robustness and reliability. To evaluate the effectiveness of our method, we conducted comparative experiments with several state-of-the-art (SOTA) segmentation models, including CNN-based UNet, nnU-Net, TransUNet, and SwinUNet. Results: Our proposed model outperformed all competing methods in terms of Dice Coefficient and Intersection over Union (IoU), demonstrating its robustness and superiority. Our extensive experiments demonstrate that the proposed U-Net with the MiT Backbone, combined with 2.5D data preparation, achieves superior performance metrics, specifically achieving DICE and IoU scores of 0.8153 ± 0.0101 and 0.7835 ± 0.0079, respectively, outperforming other backbone configurations. Conclusions: These results indicate that the integration of transformer-based backbones and 2.5D techniques offers a significant advancement in the accurate segmentation of brain stroke lesions, paving the way for more reliable and efficient diagnostic tools in clinical settings. Full article

Medical Infrared Thermography (MIT) is a safe, non-invasive technique for assessing temperature changes on the skin’s surface that may reflect pathological processes in the underlying tissues. In temporomandibular joint disorders (TMDs), which are often associated with reduced mobility and muscle overactivity, tissue metabolism and blood flow may be diminished, resulting in localized hypothermia. Aim: The purpose of this study was to evaluate muscle tone in the masseter, suprahyoid, and sternocleidomastoid muscles following the application of two types of occlusal splints, a Michigan splint and a double repositioning splint, based on temperature changes recorded using a Fluke Ti401 PRO thermal imaging camera. Materials and Methods: Sixty dental students diagnosed with TMDs were enrolled in this study. After applying the inclusion and exclusion criteria, participants were randomly assigned to one of two groups. Group M received a Michigan splint, while group D was treated with a double repositioning splint. Results: The type of occlusal splint influenced both temperature distribution and muscle tone. In the double repositioning splint group, temperature decreased by approximately 0.8 °C between T1 and T3, whereas in the Michigan splint group, temperature increased by approximately 0.7 °C over the same period. Conclusions: Occlusal splint design has a measurable impact on temperature distribution and muscle activity. The double repositioning splint appears to be more effective in promoting short-term muscle relaxation and may provide relief for patients experiencing muscular or myofascial TMD symptoms. Full article

Accurate classification of electrocardiogram (ECG) signals is vital for reliable arrhythmia diagnosis and informed clinical decision-making, yet real-world datasets often suffer severe class imbalance that degrades recall and F1-score. To address these limitations, we introduce MAK-Net, a hybrid deep learning framework that combines: (1) a four-branch multiscale convolutional module for comprehensive feature extraction across diverse waveform morphologies; (2) an efficient channel attention mechanism for adaptive weighting of clinically salient segments; (3) bidirectional gated recurrent units (BiGRU) to capture long-range temporal dependencies; and (4) Kolmogorov–Arnold Network (KAN) layers with learnable spline activations for enhanced nonlinear representation and interpretability. We further mitigate imbalance by synergistically applying focal loss and the Synthetic Minority Oversampling Technique (SMOTE). On the MIT-BIH arrhythmia database, MAK-Net attains state-of-the-art performance—0.9980 accuracy, 0.9888 F1-score, 0.9871 recall, 0.9905 precision, and 0.9991 specificity—demonstrating superior robustness to imbalanced classes compared with existing methods. These findings validate the efficacy of multiscale feature fusion, attention-guided learning, and KAN-based nonlinear mapping for automated, clinically reliable arrhythmia detection. Full article

As technology advances, the services provided by domain servers require new innovative techniques that can be optimized for frequent changes. Man-in-the-Middle (MitM) attacks on Domain Name Servers (DNS) pose a security threat, enabling attackers to intercept, modify, and redirect network traffic to malicious sites or users. This study designed an anomaly-based detection scheme that identifies and mitigates MitM attacks on DNS. The proposed model utilizes machine learning algorithms and statistical analysis techniques to ensure that the analysis of DNS query patterns can efficiently detect anomalies associated with the MitM. By integrating the Cuckoo Search Algorithm, the scheme minimizes false positives while improving the detection rate. The Proposed scheme was evaluated using the Internet of Things Intrusion Detection (IoTID) and Intrusion Detection System (IDS) datasets, achieving a detection accuracy of 99.6% and demonstrating its effectiveness in minimizing the MitM attacks on DNS. Full article

With the widespread application of machine learning techniques in time series analysis, the interpretability of models trained on time series data has attracted increasing attention. Most existing explanation methods are based on time-domain features, making it difficult to reveal how complex models focus on time–frequency information. To address this, this paper proposes a time–frequency domain-based time series interpretation method aimed at enhancing the interpretability of models at the time–frequency domain. This method extends the traditional LIME algorithm by combining the ideas of short-time Fourier transform (STFT), inverse STFT, and local interpretable model-agnostic explanations (LIME), and introduces a self-designed TFHS (time–frequency homogeneous segmentation) algorithm. The TFHS algorithm achieves precise homogeneous segmentation of the time–frequency matrix through peak detection and clustering analysis, incorporating the distribution characteristics of signals in both frequency and time dimensions. The experiment verified the effectiveness of the TFHS algorithm on Synthetic Dataset 1 and the effectiveness of the TF-LIME algorithm on Synthetic Dataset 2, and then further evaluated the interpretability performance on the MIT-BIH dataset. The results demonstrate that the proposed method significantly improves the interpretability of time-series models in the time–frequency domain, exhibiting strong generalization capabilities and promising application prospects. Full article

Atrial fibrillation (AF) is a type of cardiac arrhythmia with a worldwide prevalence of more than 37 million among the adult population. This elusive disease is a major risk factor for ischemic stroke, along with increased rates of significant morbidity and eventual mortality. It is clinically diagnosed using medical-grade electrocardiogram (ECG) sensors in ambulatory settings. The recent emergence of consumer-grade wearables equipped with photoplethysmography (PPG) sensors has exhibited considerable promise for non-intrusive continuous monitoring in free-living conditions. However, the scarcity of large-scale public PPG datasets acquired from wearable devices hinders the development of intelligent automatic AF detection algorithms unaffected by motion artifacts, saturated ambient noise, inter- and intra-subject differences, or limited training data. In this work, we present a deep learning framework that leverages convolutional layers with a bidirectional long short-term memory (CNN-BiLSTM) network and an attention mechanism for effectively classifying raw AF rhythms from normal sinus rhythms (NSR). We derive and feed heart rate variability (HRV) and pulse rate variability (PRV) features as auxiliary inputs to the framework for robustness. A larger teacher model is trained using the MIT-BIH Arrhythmia ECG dataset. Through transfer learning (TL), its learned representation is adapted to a compressed student model (32x smaller) variant by using knowledge distillation (KD) for classifying AF with the UMass and MIMIC-III datasets of PPG signals. This results in the student model yielding average improvements in accuracy, sensitivity, F1 score, and Matthews correlation coefficient of 2.0%, 15.05%, 11.7%, and 9.85%, respectively, across both PPG datasets. Additionally, we employ Gradient-weighted Class Activation Mapping (Grad-CAM) to confer a notion of interpretability to the model decisions. We conclude that through a combination of techniques such as TL and KD, i.e., pre-trained initialization, we can utilize learned ECG concepts for scarcer PPG scenarios. This can reduce resource usage and enable deployment on edge devices. Full article

Epilepsy is a neurologic condition characterized by recurring seizures resulting from aberrant brain activity. It is crucial to promptly and precisely detect epileptic seizures to ensure efficient treatment. The gold standard electroencephalography (EEG) accurately records the brain’s electrical activity in real time. The intent of this study is to precisely detect epileptic episodes by leveraging machine learning and deep learning algorithms on EEG inputs. The proposed approach aims to evaluate the feasibility of developing a novel technique that utilizes the Hurst exponent to identify EEG signal properties that could be crucial for classification. The idea posits that the prolonged duration of EEG in epileptic patients and those who are not experiencing seizures can differentiate between the two groups. To achieve this, we analyzed the long-term memory characteristics of EEG by employing time-dependent Hurst analysis. Together, the Hurst exponent and the Daubechies 4 discrete wavelet transformation constitute the basis of this unique feature extraction. We utilize the ANOVA test and random forest regression as feature selection techniques. Our approach creates and evaluates support vector machine, random forest classifier, and long short-term memory network machine learning models to classify seizures using EEG inputs. The highlight of our research approach is that it examines the efficacy of the aforementioned models in classifying seizures utilizing single-channel EEG with minimally handcrafted features. The random forest classifier outperforms other options, with an accuracy of 97% and a sensitivity of 97.20%. Additionally, the proposed model’s capacity to generalize unobserved data is evaluated on the CHB-MIT scalp EEG database, showing remarkable outcomes. Since this framework is computationally efficient, it can be implemented on edge hardware. This strategy can redefine epilepsy diagnoses and hence provide individualized regimens and improve patient outcomes. Full article