Search Results (367)

Background: Lung cancer ranks as the leading cause of cancer-related mortality worldwide. The complexity of tumor delineation, crucial for radiation therapy, requires expertise often unavailable in resource-limited settings. Artificial Intelligence (AI), particularly with advancements in deep learning (DL) and natural language processing (NLP), offers potential solutions yet is challenged by high false positive rates. Purpose: The Oncology Contouring Copilot (OCC) system is developed to leverage oncologist expertise for precise tumor contouring using textual descriptions, aiming to increase the efficiency of oncological workflows by combining the strengths of AI with human oversight. Methods: Our OCC system initially identifies nodule candidates from CT scans. Employing Language Vision Models (LVMs) like GPT-4V, OCC then effectively reduces false positives with clinical descriptive texts, merging textual and visual data to automate tumor delineation, designed to elevate the quality of oncology care by incorporating knowledge from experienced domain experts. Results: The deployment of the OCC system resulted in a 35.0% reduction in the false discovery rate, a 72.4% decrease in false positives per scan, and an F1-score of 0.652 across our dataset for unbiased evaluation. Conclusions: OCC represents a significant advance in oncology care, particularly through the use of the latest LVMs, improving contouring results by (1) streamlining oncology treatment workflows by optimizing tumor delineation and reducing manual processes; (2) offering a scalable and intuitive framework to reduce false positives in radiotherapy planning using LVMs; (3) introducing novel medical language vision prompt techniques to minimize LVM hallucinations with ablation study; and (4) conducting a comparative analysis of LVMs, highlighting their potential in addressing medical language vision challenges. Full article

Background: Vaginal intraepithelial neoplasia (VaIN) is a rare but potentially precancerous condition strongly associated with human papillomavirus (HPV) infection. Despite increased detection rates due to HPV screening and colposcopy, diagnosis and management remain challenging. This study aimed to evaluate the epidemiological characteristics, risk factors, and outcomes of VaIN in patients referred to a tertiary academic center. Methods: We conducted a retrospective analysis of 48 patients who underwent colposcopy-directed vaginal biopsies between January 2019 and June 2024 at the Medical University of Warsaw. Data collected included patient demographics, HPV status, cytology, histopathology, and treatment outcomes. Patients were grouped based on the presence and grade of VaIN (VaIN 1 vs. VaIN 2/3). Statistical analyses were performed using SPSS software. Results: VaIN was diagnosed in 24 patients (50%), VaIN was confirmed in half of the cohort, VaIN 2 in 30%, and VaIN 3 in 18% of cases. HPV infection and prior cervical pathology were significantly associated with VaIN diagnosis (P = 0.03 and P = 0.05, respectively), and high-risk HPV infection correlated with higher-grade lesions (P = 0.04). Among VaIN 2+ cases, most patients required laser ablation or surgical excision, while VaIN 1 often regressed spontaneously. Regression occurred in 11 cases, and high-risk HPV infection was inversely associated with spontaneous regression (P = 0.04). Conclusions: This study confirms the central role of HPV, particularly high-risk subtypes, in VaIN pathogenesis. Conservative management may be appropriate for VaIN 1, while VaIN 2+ requires active intervention. HPV genotyping should be integrated into diagnostic workups, and long-term follow-up is essential due to the risks of persistence and recurrence. Full article

Task-oriented medical dialogue systems face two fundamental challenges: the explosion of state-action space caused by numerous diseases and symptoms and the sparsity of informative signals during interactive diagnosis. These issues significantly hinder the accuracy and efficiency of automated clinical reasoning. To address these problems, we propose MA-HRL, a multi-agent hierarchical reinforcement learning framework that decomposes the diagnostic task into specialized agents. A high-level controller coordinates symptom inquiry via multiple worker agents, each targeting a specific disease group, while a two-tier disease classifier refines diagnostic decisions through hierarchical probability reasoning. To combat sparse rewards, we design an information entropy-based reward function that encourages agents to acquire maximally informative symptoms. Additionally, medical knowledge graphs are integrated to guide decision-making and improve dialogue coherence. Experiments on the SymCat-derived SD dataset demonstrate that MA-HRL achieves substantial improvements over state-of-the-art baselines, including +7.2% diagnosis accuracy, +0.91% symptom hit rate, and +15.94% symptom recognition rate. Ablation studies further verify the effectiveness of each module. This work highlights the potential of hierarchical, knowledge-aware multi-agent systems for interpretable and scalable medical diagnosis. Full article

Despite advances in surgery, chemotherapy, and radiation treatments for pancreatic ductal adenocarcinoma (PDAC), 5-year survival rates remain at nearly 11%. Cholangiocarcinoma, while not as severe, also possesses similar survival rates. Fewer than 20% of patients are surgical candidates at time of diagnosis; therefore, it is imperative that alternative therapies are effective for non-surgical patients. There are several thermal ablative techniques, including radiofrequency ablation (RFA), high-intensity focused ultrasound (HIFU), microwave ablation (MWA), alcohol ablation, stereotactic body radiotherapy (SBRT), cryoablation, irreversible electroporation (IRE), biliary intraluminal brachytherapy, and biliary photodynamic therapy (PDT). Emerging literature in animal models and human patients has demonstrated that endoscopic ultrasound (EUS)-guided RFA (EUS-RFA) prevents tumor progression through coagulative necrosis, protein denaturation, and activation of anticancer immunity in local and distant tumor tissue (abscopal effect). RFA treatment has been shown to not only reduce tumor-associated immunosuppressive cells but also increase functional T cells in distant tumor cells not treated with RFA. The remarkable ability to reduce tumor progression and promote tumor microenvironment (TME) remodeling makes RFA a very promising non-surgical therapy technique that has the potential to reduce mortality in this patient population. EUS-RFA offers superior precision and safety compared to other ablation techniques for pancreatic and biliary cancers, due to real-time imaging capabilities and minimally invasive nature. Future research should focus on optimizing RFA protocols, exploring combination therapies with chemotherapy or immunotherapy, and expanding its use in patients with metastatic disease. This review article will explore the current data and underlying pathophysiology of EUS-RFA while also highlighting the role of ablative therapies as a whole in immune activation response. Full article

Compressed sensing is widely used in modern resource-constrained sensor networks. However, achieving high-quality and robust signal reconstruction under low sampling rates and noise interference remains challenging. Traditional CS methods have limited performance, so many deep learning-based CS models have been proposed. Although these models show strong fitting capabilities, they often lack the ability to handle complex noise in sensor networks, which affects their performance stability. To address these challenges, this paper proposes SBCS-Net. This framework innovatively expands the iterative process of sparse Bayesian compressed sensing using convolutional neural networks and Transformer. The core of SBCS-Net is to optimize key SBL parameters through end-to-end learning. This can adaptively improve signal sparsity and probabilistically process measurement noise, while fully leveraging the powerful feature extraction and global context modeling capabilities of deep learning modules. To comprehensively evaluate its performance, we conduct systematic experiments on multiple public benchmark datasets. These studies include comparisons with various advanced and traditional compressed sensing methods, comprehensive noise robustness tests, ablation studies of key components, computational complexity analysis, and rigorous statistical significance tests. Extensive experimental results consistently show that SBCS-Net outperforms many mainstream methods in both reconstruction accuracy and visual quality. In particular, it exhibits excellent robustness under challenging conditions such as extremely low sampling rates and strong noise. Therefore, SBCS-Net provides an effective solution for high-fidelity, robust signal recovery in sensor networks and related fields. Full article

Point-of-care (POC) diagnostic technologies have become essential for the real-time monitoring and management of chronic wounds, where maintaining a moist environment and controlling pH levels are critical for effective healing. In this study, a flexible pH sensor based on a graphene/molybdenum disulfide (graphene/MoS₂) composite interdigitated electrode (IDE) structure was fabricated using pulsed laser ablation. The pH sensor, with an active area of 30 mm × 30 mm, exhibited good adhesion to the polyethylene terephthalate (PET) substrate and maintained structural integrity under repeated bending cycles. Precise ablation was achieved under optimized conditions of 4.35 J/cm² laser fluence, a repetition rate of 300 kHz, and a scanning speed of 500 mm/s, enabling the formation of defect-free IDE arrays without substrate damage. The influence of laser processing parameters on the surface morphology, electrical conductivity, and wettability of the composite thin films was systematically characterized. The fabricated pH sensor exhibited high sensitivity (~4.7% change in current per pH unit) across the pH 2–10 range, rapid response within ~5.2 s, and excellent mechanical stability under 100 bending cycles with negligible performance degradation. Moreover, the sensor retained > 95% of its stable sensitivity after 7 days of ambient storage. Furthermore, the pH response behavior was evaluated for electrode structures with different pitches, demonstrating that structural design parameters critically impact sensing performance. These results offer valuable insights into the scalable fabrication of flexible, wearable pH sensors, with promising applications in wound monitoring and personalized healthcare systems. Full article

Cotton leaf diseases can lead to substantial yield losses and economic burdens. Traditional detection methods are challenged by low accuracy and high labor costs. This research presents the ACURS-YOLO network, an advanced cotton leaf disease detection architecture developed on the foundation of YOLOv11. By integrating a medical image segmentation model, it effectively tackles challenges including complex background interference, the missed detection of small targets, and restricted generalization ability. Specifically, the U-Net v2 module is embedded in the backbone network to boost the multi-scale feature extraction performance in YOLOv11. Meanwhile, the CBAM attention mechanism is integrated to emphasize critical disease-related features. To lower the computational complexity, the SPPF module is substituted with SimSPPF. The C3k2_RCM module is appended for long–range context modeling, and the ARelu activation function is employed to alleviate the vanishing gradient problem. A database comprising 3000 images covering six types of cotton leaf diseases was constructed, and data augmentation techniques were applied. The experimental results show that ACURS-YOLO attains impressive performance indicators, encompassing a mAP_0.5 value of 94.6%, a mAP_0.5:0.95 value of 83.4%, 95.5% accuracy, 89.3% recall, an F1 score of 92.3%, and a frame rate of 148 frames per second. It outperforms YOLOv11 and other conventional models with regard to both detection precision and overall functionality. Ablation tests additionally validate the efficacy of each component, affirming the framework’s advantage in addressing complex detection environments. This framework provides an efficient solution for the automated monitoring of cotton leaf diseases, advancing the development of smart sensors through improved detection accuracy and practical applicability. Full article

Objective: Radical therapies are associated with significant morbidity in patients with localized prostate cancer (PCa). While advances in nuclear magnetic resonance techniques have enabled the development of focal ablation procedures that can selectively destroy tumors, preserve the gland and surrounding structures, and minimize side effects, existing vascular-targeted photodynamic therapy (VTP) and nanodrug therapies often face limitations, such as recurrence and insufficient drug concentration at the tumor site. This study investigated a novel approach that combines VTP with systemic treatment using drug-loaded nanoparticles in a murine model, demonstrating substantial advancements beyond current monotherapies. Methods: SCID (severe combined immunodeficiency) mice were engrafted with androgen-sensitive prostate tumor cells (LNCaP-AR) and treated with a combination of VTP and two different drugs linked to fucoidan nanoparticles (Enzalutamide and Paclitaxel). Experiments were performed using different cohorts: the evaluation of oncological effect, the administration time and concentration of systemic therapy, a comparison of efficacy between VTP and radiotherapy, and the induction of the abscopal effect in untreated synchronous tumors. Results: The groups that received combination therapy showed better tumor control. After eight weeks, the recurrence-free survival rates were 87.5%, 62.5%, and 50% in the VTP + N-PAC, VTP + N-ENZ, and VTP monotherapy groups, respectively (p < 0.05). There was a significant difference in the intra-tumoral concentration of nanodrugs between the groups with combined treatment and monotherapy. After two weeks, the monotherapy groups showed almost total elimination of the drugs, whereas in the combined therapy groups, this concentration remained high, starting to decrease after three weeks (p < 0.05). Treatment with nanodrugs associated with VTP showed superior oncological benefits compared to radiotherapy alone or in combination with other therapies. The abscopal effect on synchronous tumors was not demonstrated with VTP alone or in combination with nanodrugs. Conclusions: Combining vascular photodynamic therapy with nanodrugs was highly effective in treating a prostate tumor model, leading to increased survival and a reduced risk of tumor recurrence. This approach significantly advances beyond existing VTP and nanodrug therapies by improving tumor control, ensuring sustained intra-tumoral drug concentration, and yielding superior oncological outcomes. Our results suggest that this therapy is a potential treatment option for prostate tumors treated with VTP in future clinical trials. Full article

In the present study, the coaxial waterjet-assisted nanosecond laser drilling of micro-holes in C_f/SiC composites, coupled with nanosecond laser drilling in air for fabricating micro-holes with high aspect ratios, were investigated. The surface morphology, reaction products, and micro-hole shapes were thoroughly examined. The results reveal that, for the coaxial waterjet-assisted nanosecond laser drilling of micro-holes in the C_f/SiC composite, the increasing of waterjet velocity enhances the material removal rate and micro-hole depth, but reduces the micro-hole diameter and taper angle. The coaxial waterjet isolates the laser-ablated region and cools down the corresponding region rapidly, leading to the formation of a mixture of SiC, SiO₂, and Si on the surface. As the coaxial waterjet velocity increases, the morphology of residual surface products changes from a net-like structure to individual spheres. Coaxial waterjet-assisted nanosecond laser drilling, with a waterjet velocity of 9.61 m/s, achieves micro-holes with a good balance between efficiency and quality. For the fabrication of micro-holes with a high aspect ratio in C_f/SiC composites, micro-holes fabricated by nanosecond laser drilling in air exhibit obvious taper features, which should be ascribed to the combined effects of spattering slag, plasma, and energy dissipation. The application of coaxial waterjet-assisted nanosecond laser drilling on micro-holes fabricated by laser drilling in air effectively expands the hole diameter. The fabricated micro-holes have very small taper angles, with clean wall surfaces and almost no reaction products. This approach, combining nanosecond laser drilling in air followed by coaxial waterjet-assisted nanosecond laser drilling, offers a promising technique for fabricating high-quality micro-holes with high aspect ratios in C_f/SiC composites. Full article

Expressive imitation in the performing arts is typically trained through animal behavior imitation, aiming not only to reproduce action trajectories but also to recreate rhythm, style and emotional states. However, evaluation of such animal imitation behaviors relies heavily on teachers’ subjective judgments, lacking structured criteria, exhibiting low inter-rater consistency and being difficult to quantify. To enhance the objectivity and interpretability of the scoring process, this study develops a machine learning and structured pose data-based auxiliary evaluation framework for imitation quality. The proposed framework innovatively constructs three types of feature sets, namely baseline, ablation, and enhanced, and integrates recursive feature elimination with feature importance ranking to identify a stable and interpretable set of core structural features. This enables the training of machine learning models with strong capabilities in structured modeling and sensitivity to informative features. The analysis of the modeling results indicates that temporal–rhythm features play a significant role in score prediction and that only a small number of key feature values are required to model teachers’ ratings with high precision. The proposed framework not only lays a methodological foundation for standardized and AI-assisted evaluation in performing arts education but also expands the application boundaries of computer vision and machine learning in this field. Full article

The widespread rise of misinformation across digital platforms has increased the demand for accurate and efficient Fake News Detection (FND) systems. This study introduces an enhanced transformer-based architecture for FND, developed through comprehensive ablation studies and empirical evaluations on multiple benchmark datasets. The proposed model combines improved multi-head attention, dynamic positional encoding, and a lightweight classification head to effectively capture nuanced linguistic patterns, while maintaining computational efficiency. To ensure robust training, techniques such as label smoothing, learning rate warm-up, and reproducibility protocols were incorporated. The model demonstrates strong generalization across three diverse datasets, such as FakeNewsNet, ISOT, and LIAR, achieving an average accuracy of 79.85%. Specifically, it attains 80% accuracy on FakeNewsNet, 100% on ISOT, and 59.56% on LIAR. With just 3.1 to 4.3 million parameters, the model achieves an 85% reduction in size compared to full-sized BERT architectures. These results highlight the model’s effectiveness in balancing high accuracy with resource efficiency, making it suitable for real-world applications such as social media monitoring and automated fact-checking. Future work will explore multilingual extensions, cross-domain generalization, and integration with multimodal misinformation detection systems. Full article

To address the impact of insulation medium degradation in the arc quenching chambers of ultra-high-voltage SF₆ circuit breakers on phase-controlled switching accuracy caused by multiple operations throughout the service life, this paper proposes an adaptive switching algorithm. First, a modified formula for the breakdown voltage of mixed gases is derived based on the synergistic effect. Considering the influence of contact gap on electric field distortion, an adaptive switching strategy is designed to quantify the dynamic relationship among operation times, insulation strength degradation, and electric field distortion. Then, multi-round switching-on and switching-off tests are carried out under the condition of fixed single-arc ablation amount, and the laws of voltage–current, gas decomposition products, and pre-breakdown time are obtained. The test data are processed by the least squares method, adaptive switching algorithm, and machine learning method. The results show that the coincidence degree of the pre-breakdown time obtained by the adaptive switching algorithm and the test value reaches 90%. Compared with the least squares fitting, this algorithm achieves a reasonable balance between goodness of fit and complexity, with prediction deviations tending to be randomly distributed, no obvious systematic offset, and low dispersion degree. It can also explain the physical mechanism of the decay of insulation degradation rate with the number of operations. Compared with the machine learning method, this algorithm has stronger generalization ability, effectively overcoming the defects of difficult interpretation of physical causes and the poor engineering adaptability of the black box model. Full article

Background: Solid pseudopapillary neoplasm (SPN) is a rare pancreatic tumor with malignant potential. Its diagnosis has grown alongside increased use of abdominal imaging. SPN is suspected after classical findings in abdominal imaging studies; however, endoscopic ultrasound-guided (EUS) fine needle aspiration can support preoperative diagnosis. The treatment of choice is still surgical intervention, with an intent to reach curative resection. The prognosis is excellent. Recently, emerging data on EUS-guided radiofrequency ablation (RFA) suggest changing the choice of treatment for small SPN. Methods: We provide a comprehensive overview on pancreatic SPN with a focus on treatment, adverse events, recurrence rate, and outcomes. In addition, we provide a literature summary and pool data analysis. Results: Overall, 70 papers including 6651 patients were identified. The mean SPN size was 5.8 cm, metastasis rate was 1.9%, and recurrence rate was 3%. Moreover, the mortality rate was low at 0.2%, although high postoperative adverse events were reported (32.4%). Small SPN (<2 cm) was present in 4.1% of the studies. Two studies reported EUS-RFA for small SPN <2 cm, without recurrence at a median follow-up of 18.5 months. Conclusions: SPN still necessitates surgical intervention given its malignant potential. However, EUS-RFA can represent a promising and safe therapeutic option for SPN < 2 cm. Full article

To address the challenge of insufficient spatial resolution in remote sensing precipitation data, this paper proposes a novel Multi-Scale Residual Generative Adversarial Network (MSRGAN) for reconstructing high-resolution precipitation images. The model integrates multi-source meteorological information and topographic priors, and it employs a Deep Multi-Scale Perception Module (DeepInception), a Multi-Scale Feature Modulation Module (MSFM), and a Spatial-Channel Attention Network (SCAN) to achieve high-fidelity restoration of complex precipitation structures. Experiments conducted using Weather Research and Forecasting (WRF) simulation data over the continental United States demonstrate that MSRGAN outperforms traditional interpolation methods and state-of-the-art deep learning models across various metrics, including Critical Success Index (CSI), Heidke Skill Score (HSS), False Alarm Rate (FAR), and Jensen–Shannon divergence. Notably, it exhibits significant advantages in detecting heavy precipitation events. Ablation studies further validate the effectiveness of each module. The results indicate that MSRGAN not only improves the accuracy of precipitation downscaling but also preserves spatial structural consistency and physical plausibility, offering a novel technological approach for urban flood warning, weather forecasting, and regional hydrological modeling. Full article

Food pattern recognition plays a crucial role in modern healthcare by enabling automated dietary monitoring and personalised nutritional interventions, particularly for vulnerable populations with complex dietary needs. Current food recognition systems struggle to balance high accuracy with interpretability and computational efficiency when analysing complex meal compositions in real-world settings. We developed a novel self-explaining neural architecture that integrates specialised attention mechanisms with temporal modules within a streamlined framework. Our methodology employs hierarchical feature extraction through successive convolution operations, multi-head attention mechanisms for pattern classification, and bidirectional LSTM networks for temporal analysis. Architecture incorporates self-explaining components utilising attention-based mechanisms and interpretable concept encoders to maintain transparency. We evaluated our model on the FOOD101 dataset using 5-fold cross-validation, ablation studies, and comprehensive computational efficiency assessments. Training employed multi-objective optimisation with adaptive learning rates and specialised loss functions designed for dietary pattern recognition. Experiments demonstrate our model’s superior performance, achieving 94.1% accuracy with only 29.3 ms inference latency and 3.8 GB memory usage, representing a 63.3% parameter reduction compared to baseline transformers. The system maintains detection rates above 84% in complex multi-item recognition scenarios, whilst feature attribution analysis achieved scores of 0.89 for primary components. Cross-validation confirmed consistent performance with accuracy ranging from 92.8% to 93.5% across all folds. This research advances automated dietary analysis by providing an efficient, interpretable solution for food recognition with direct applications in nutritional monitoring and personalised healthcare, particularly benefiting vulnerable populations who require transparent and trustworthy dietary guidance. Full article