Search Results (5,739)

The tumor microenvironment, characterized by higher acidity, hypoxia, and dense cellular structures, plays a pivotal role in cancer progression, therapeutic resistance, and treatment response. Nanoparticle-based contrast agents enable the precise delineation of solid regions within heterogeneous tumors through advanced molecular imaging techniques. Since 1956, ultrasound (US) medical imaging has provided essential anatomical and functional insights about internal organs. More recently, magnetomotive ultrasound (MMUS) has emerged as a promising imaging modality, using a modulated magnetic field to exert force on superparamagnetic iron oxide nanoparticles (SPIONs), inducing motion in the surrounding tissues through mechanical coupling. In parallel, magnetic hyperthermia (MH), which employs localized heating by alternating magnetic fields, has demonstrated significant potential in selectively destroying cancer cells while sparing healthy tissues. This review summarizes the current state of IONP-based contrast agents, with particular emphasis on their use in MH for cancer treatment, as well as their potential in multimodal imaging, including MMUS, and photoacoustic (PA) imaging. The advantages and limitations of IONPs in tumor detection and characterization are discussed, examining the development of surface-functionalized MNPs, and analyzing how material properties and environmental factors affect their diagnostic and therapeutical performance. Finally, strategies for combining MMUS and PA modalities for pre-clinical cancer imaging are proposed. Full article

Malignancy-related gastrointestinal bleeding (GIB) remains a significant clinical challenge, contributing substantially to morbidity, mortality, and healthcare utilization in patients with cancer. Up to 10% of individuals with advanced malignancies develop GIB during their disease, and these episodes are frequently characterized by a high risk of rebleeding and poor long-term hemostatic control. Tumor-associated bleeding typically arises from friable, infiltrative, and highly vascular lesions that respond suboptimally to conventional endoscopic techniques such as thermal coagulation or mechanical clipping. These limitations underscore the need for improved diagnostic accuracy and more reliable therapeutic options. Recent advances in imaging modalities, including contrast-enhanced CT studies, have enhanced the ability to localize and characterize bleeding sources in complex oncologic cases. Parallel developments in endoscopic hemostasis—such as over-the-scope clips and contact-free coagulation devices—have expanded the therapeutic armamentarium for managing malignant bleeding. Clinically, topical hemostatic powders—particularly TC-325—represent a highly effective option for achieving rapid endoscopic hemostasis, supported by the strongest comparative evidence and the highest rates of immediate bleeding control among currently available technologies. In this review, we synthesize contemporary diagnostic approaches to GIB and place particular emphasis on the evolving and emerging therapeutic strategies for malignancy-related bleeding. We also highlight innovative technologies that are reshaping clinical practice and improving management options in this challenging clinical domain. Full article

Boron neutron capture therapy (BNCT) is experiencing a global resurgence driven by advances in boron pharmacology, accelerator-based neutron sources, and molecular imaging-guided theranostics. BNCT produces high linear energy transfer particles with micrometer-range energy deposition, enabling cell-selective irradiation confined to boron-enriched tumor cells in a geometrically targeted region by the neutron beam. This mechanism offers the potential for exceptionally high therapeutic ratios, provided two core requirements are met: sufficient differential tumor uptake of ¹⁰B and a neutron beam with appropriate energy and penetration. After early clinical attempts in the mid-20th century were hindered by inadequate boron agents and reactor-based neutron beams, recent technological breakthroughs have made BNCT clinically viable. The development of hospital-compatible accelerator neutron sources, next-generation boron delivery systems (such as receptor-targeted compounds and nanoparticles), advanced theranostic approaches (such as ¹⁸F-BPA positron emission tomography and boron-sensitive magnetic resonance imaging), and AI-driven biodistribution modeling now support personalized treatment planning and patient selection. These innovations have catalyzed modern clinical implementation, exemplified by Japan’s regulatory approval of BNCT for recurrent head and neck cancer and the rapid expansion of clinical programs across Asia, Europe, and South America. Building on these foundations, BNCT has transitioned from a predominantly academic experimental modality into an increasingly commercialized and industrially supported therapeutic platform. The emergence of dedicated BNCT companies, international collaborations between accelerator manufacturers and hospitals, and pharmaceutical development pipelines for next-generation boron carriers has accelerated clinical translation. Moreover, BNCT now occupies a unique position among radiation modalities due to its hybrid nature, namely combining the biological targeting of radiopharmaceutical therapy with the external-beam controllability of radiotherapy, thereby offering new therapeutic opportunities where competitive approaches fall short. Emerging evidence suggests therapeutic promise in glioblastoma, recurrent head and neck cancers, melanoma, meningioma, lung cancer, sarcomas, and other difficult-to-treat malignancies. Looking ahead, continued innovation in compact neutron source engineering, boron nanocarriers, multimodal theranostics, microdosimetry-guided treatment planning, and combination strategies with systemic therapies such as immunotherapy will be essential for optimizing outcomes. Together, these converging developments position BNCT as a biologically targeted and potentially transformative modality in the era of precision oncology. Full article

The detection of sensitive content in online videos is a key challenge for ensuring digital safety and effective content moderation. This work proposes the Multimodal Audiovisual Attention (MAV-Att), a multimodal deep learning framework that jointly exploits audio and visual cues to improve detection accuracy. The model was evaluated on the LSPD dataset, comprising 52,427 video segments of 20 s each, with optimized keyframe extraction. MAV-Att consists of dual audio and image branches enhanced by attention mechanisms to capture both temporal and cross-modal dependencies. Trained using a joint optimisation loss, the system achieved F1-scores of 94.9% on segments and 94.5% on entire videos, surpassing previous state-of-the-art models by 6.75%. Full article

Large volumes of images shared on social media have made image captioning an important tool for social hotspot identification and public opinion monitoring, where accurate visual–language alignment is essential for reliable analysis. However, existing image captioning models based on BLIP-2 (Bootstrapped Language–Image Pre-training) often struggle with complex, context-rich, and socially meaningful images in real-world social media scenarios, mainly due to insufficient cross-modal interaction, redundant visual token representations, and an inadequate ability to capture multi-scale semantic cues. As a result, the generated captions tend to be incomplete or less informative. To address these limitations, this paper proposes ECMA (Enhanced Cross-Modal Attention), a lightweight module integrated into the Querying Transformer (Q-Former) of BLIP-2. ECMA enhances cross-modal interaction through bidirectional attention between visual features and query tokens, enabling more effective information exchange, while a multi-scale visual aggregation strategy is introduced to model semantic representations at different levels of abstraction. In addition, a semantic residual gating mechanism is designed to suppress redundant information while preserving task-relevant features. ECMA can be seamlessly incorporated into BLIP-2 without modifying the original architecture or fine-tuning the vision encoder or the large language model, and is fully compatible with OPT (Open Pre-trained Transformer)-based variants. Experimental results on the COCO (Common Objects in Context) benchmark demonstrate consistent performance improvements, where ECMA improves the CIDEr (Consensus-based Image Description Evaluation) score from 144.6 to 146.8 and the BLEU-4 score from 42.5 to 43.9 on the OPT-6.7B model, corresponding to relative gains of 1.52% and 3.29%, respectively, while also achieving competitive METEOR (Metric for Evaluation of Translation with Explicit Ordering) scores. Further evaluations on social media datasets show that ECMA generates more coherent, context-aware, and socially informative captions, particularly for images involving complex interactions and socially meaningful scenes. Full article

During on-orbit service, spacecraft are subjected to hypervelocity impacts (HVIs) from micrometeoroids and space debris, causing diverse damage types that challenge structural health assessment. Unimodal approaches often struggle with similar damage patterns due to mechanical noise and imaging distance variations. To overcome these physical limitations, this study proposes a physics-informed multimodal fusion framework. Innovatively, we integrate a distance-aware infrared enhancement strategy with vibration spectral subtraction to align heterogeneous data qualities while employing a dual-stream ResNet coupled with Dempster–Shafer (D-S) evidence theory to rigorously resolve inter-modal conflicts at the decision level. Experimental results demonstrate that the proposed strategy achieves a mean accuracy of 99.01%, significantly outperforming unimodal baselines (92.96% and 97.11%). Notably, the fusion mechanism corrects specific misclassifications in micro-cracks and perforation, ensuring a precision exceeding 96.9% across all categories with high stability (standard deviation 0.74%). These findings validate the efficacy of multimodal fusion for precise on-orbit damage assessment, offering a robust solution for spacecraft structural health monitoring. Full article

Background/Objectives: Hydroxychloroquine (HCQ) is widely used in the treatment of autoimmune rheumatologic diseases due to its immunomodulatory and anti-inflammatory properties. However, long-term HCQ therapy carries a risk of irreversible retinal toxicity caused by drug accumulation in the retinal pigment epithelium. The early identification of preclinical retinal changes is essential to prevent permanent visual impairment. Optical coherence tomography (OCT) and OCT-angiography (OCT-A) have emerged as key imaging modalities for the detection of structural and microvascular biomarkers of HCQ retinopathy. A narrative review of the literature was conducted using the PubMed database, focusing on studies published between January 2017 and February 2025. Search terms included “hydroxychloroquine” and “optical coherence tomography.” Eligible studies evaluated HCQ-related retinal toxicity using OCT and/or OCT-A in human subjects. Data were extracted regarding study population characteristics, treatment duration, cumulative HCQ dose, daily dose normalized to real body weight, and reported imaging findings. Results: We identified 223 scientific papers of which 88 studies met the inclusion criteria. Structural OCT parameters—particularly alterations in the ellipsoid zone, outer nuclear layer, and retinal pigment epithelium—were consistently associated with early HCQ toxicity, often preceding functional impairment. OCT-A studies demonstrated microvascular alterations, including reduced vessel density and foveal avascular zone enlargement, though interpretation may be confounded by underlying autoimmune-disease-related vasculopathy. Conclusions: HCQ retinopathy is a potentially vision-threatening condition associated with the cumulative dose, treatment duration, and patient-specific risk factors. OCT and OCT-A provide complementary structural and vascular biomarkers that aid in the detection of subclinical retinal toxicity. The integration of quantitative and automated OCT-derived metrics may improve screening strategies, facilitate early diagnosis, and support personalized care in patients receiving long-term HCQ therapy. Full article

AI-driven imaging is becoming central to crop monitoring, with proximal and unmanned aerial vehicle (UAV) platforms now routinely used for disease and stress detection, yield estimation, canopy structure, and fruit counting. Yet, as these models move from plots to farms, the main bottleneck is no longer raw accuracy but robustness under distribution shift. Systems trained in one field, season, cultivar, or sensor often fail when the scene, sensor, protocol, or timing changes in realistic ways. This review synthesizes recent advances on robustness and transferability in proximal and UAV imaging, drawing on a corpus of 42 core studies across field crops, orchards, greenhouse environments, and multi-platform phenotyping. Shift types are organized into four axes, namely scene, sensor, protocol, and time. The article also maps the empirical evidence on when RGB imaging alone is sufficient and when multispectral, hyperspectral, or thermal modalities can potentially improve robustness. This serves as a basis to synthesize acquisition and evaluation practices that often matter more than architectural tweaks, which include phenology-aware flight planning, radiometric standardization, metadata logging, and leave-one-field/season-out splits. Adaptation options are consolidated into a practical symptom/remedy roadmap, ranging from lightweight normalization and small target-set fine-tuning to feature alignment, unsupervised domain adaptation, style translation, and test-time updates. Finally, a benchmark and dataset agenda are outlined with emphasis on object-oriented splits, cross-sensor and cross-scale collections, and longitudinal datasets where the same fields are followed across seasons under different management regimes. The goal is to outline practices and evaluation protocols that support progress toward deployable and auditable systems, noting that such claims require standardized out-of-distribution testing and transparent reporting as emphasized in the benchmark specification and experiment suite proposed here. Full article

As a vital component of urban tourism, urban theme parks increasingly face experience homogenization and intensifying competition. Accordingly, the implementation of refined digital marketing and operational strategies based on visitor digital behavior has become increasingly essential. In this context, tourists’ social media sharing has become a crucial link between destination marketing and visitors’ experience construction. Within the SOBC (Stimulus–Organism–Behavior–Consequence) framework, this study examines how theme park servicescapes (S) shape sharing motivations (O), which, in turn, influence multimodal sharing intentions (B—text, image + text, video) and subsequently contribute to memorable theme park experience (C). A two-stage, mixed-method design was employed, and the study considered visitors to Beijing Universal Studios and Shanghai Disney Resort. Semi-structured interviews and grounded analysis identified five motivations: altruism, self-presentation, affective expression, hedonic motivation, and community identification. Testing was performed using a survey (N = 604), along with structural equation modeling. The findings indicate that the staff-related social environment exerts significant positive effects on all five motivations, whereas the effects of the physical environment are more selective. Motivations differentially predict modal intentions: text aligns with altruism and affective expression; image + text aligns with altruism, community identification, and self-presentation; and video aligns with self-presentation, hedonism, community identification, and affective expression. All three intentions positively affect memorable theme park experience. These results clarify how motivations map onto content forms and validate a support SOBC framework from servicescapes to memorable experience, offering actionable implications for experience design and digital marketing. Full article

Water resources are of critical importance across all ecological, social, and economic realms. Accurate extraction of water bodies is of significance to estimate the spatial coverage of water resources and to mitigate water-related disasters. Single-modal remote sensing images are often insufficient for accurate water body extraction due to limitations in spectral information, weather conditions, and speckle noises. Furthermore, state-of-the-art deep learning models may be constrained by data extensibility, feature transferability, model scalability, and task producibility. This manuscript presents an integrated GeoAI framework that enhances foundation models for efficient water body extraction with multi-modal remote sensing images. The proposed framework consists of a data augmentation module tailored for optical and synthetic aperture radar (SAR) remote sensing images, as well as extraction modules augmented by three popular foundation models, namely SAM, SAMRS, and CROMA. Specifically, optical and SAR images are preprocessed and augmented independently, encoded through foundation model backbones, and subsequently decoded to generate water body segmentation masks under single-modal and multi-modal settings. Full article

Osteoarthritis (OA) is a prevalent joint disorder characterized by symptoms such as pain and stiffness, often leading to loss of function and disability. Knee osteoarthritis (KOA) represents the most prevalent type of osteoarthritis. KOA is usually detected using X-ray radiographs of the knee; however, the classification of disease severity remains subjective and varies among clinicians, motivating the need for automated assessment methods. In recent years, deep learning–based approaches have shown promising performance for KOA classification tasks, particularly when applied to structured imaging datasets. This review analyzes convolution neural network (CNN)-based approaches reported in the literature and compares their performance across multiple criteria. Studies were identified through systematic searches of IEEE Xplore, SpringerLink, Elsevier (ScienceDirect), Wiley Online Library, ACM Digital Library, and other sources such as PubMed and arXiv, with the last search conducted in March 2025. The review examines datasets used (primarily X-ray and MRI), preprocessing strategies, segmentation techniques, and deep learning architectures. Reported classification accuracies range from 61% to 98%, depending on the dataset, imaging modality, and task formulation. Finally, this paper highlights key methodological limitations in existing studies and outlines future research directions to improve the robustness and clinical applicability of deep learning–based KOA classification systems. Full article

Background: Sentinel lymph node (SLN) biopsy has emerged as a cornerstone in melanoma staging, offering targeted evaluation of regional lymphatic spread and guiding therapeutic decision-making. Traditionally, SLN mapping relies on lymphoscintigraphy using technetium-99m (Tc-99m) radiocolloid, but in recent years, indocyanine green (ICG) fluorescence imaging has emerged as a promising alternative. The aim of this review is to evaluate the diagnostic accuracy of ICG–near-infrared (NIR) imaging compared to standard Tc-99m lymphoscintigraphy in SLN biopsy (SLNB). Methods: A systematic review and meta-analysis were conducted, including 12 studies. The primary outcome was the false-negative rate; secondary outcomes included the total number of sentinel lymph nodes (SLNs) identified by ICG–NIR imaging and Tc-99m lymphoscintigraphy, the number of metastatic SLNs detected by each method, and the number of patients with metastatic disease. The statistical analysis for dichotomous variables was performed using the “Odds Ratio” (O.R.) calculated with the Mantel–Haenszel method. For continuous variables, the analysis utilized the “Mean Difference” calculated by the inverse variance method. All data are presented with a 95% confidence interval (CI). Results: ICG was associated with a significantly higher number of SLNs identified compared to Tc-99m (O.R.: 0.41, 95% CI: 0.34–0.49; p < 0.00001), while no significant differences were found in the detection of metastatic nodes, either as a proportion of total SLNs (O.R.: 1.04, 95% CI: 0.86–1.25; p = 0.68) or relative to total positive nodes (O.R.: 0.36, 95% CI: 0.16–0.81; p = 0.01). No statistically significant differences between the two techniques were found in the detection of metastatic patients (OR: 0.80, 95% CI: 0.31–2.03, p = 0.33) and in the total number of false-negative patients missed (risk difference (RD): 0.03, 95% CI: −0.04 to 0.09, p = 0.93). Conclusions: While ICG identifies a higher number of SLNs compared to Tc-99m, its ability to detect metastatic involvement is comparable between the two modalities. No significant differences were observed in the proportion of metastatic SLNs, the total number of positive nodes detected, the number of metastatic patients identified, and the false-negative rate. Given its favorable profile, ICG could represent a reliable alternative or adjunct to Tc-99 in SLNB. However, prospective studies are warranted to validate its standalone diagnostic role. Full article

Earth Observation (EO) and Remote Sensing (RS) data are widely used in various fields, including weather, environment, and natural disaster modeling and prediction. EO and RS done through geostationary satellite constellations in fields such as these are limited to a smaller region, while sun synchronous satellite constellations have discontinuous spatial and temporal coverage. This limits the ability of EO and RS data for near-real-time weather, environment, and natural disaster applications. To address these limitations, we introduce Now Observation Assemble Horizon (NOAH), a multi-modal, sensor fusion dataset that combines Ground-Based Sensors (GBS) of weather stations with topography, vegetation (land cover, biomass, and crown cover), and fuel types data from RS data sources. NOAH is collated using publicly available data from Environment and Climate Change Canada (ECCC), Spatialized CAnadian National Forest Inventory (SCANFI) and United States Geological Survey (USGS), which are well-maintained, documented, and reliable. Applications of the NOAH dataset include, but are not limited to, expanding RS data tiles, filling in missing data, and super-resolution of existing data sources. Additionally, Generative Artificial Intelligence (GenAI) or Generative Modeling (GM) can be applied for near-real-time model-generated or synthetic estimate data for disaster modeling in remote locations. This can complement the use of existing observations by field instruments, rather than replacing them. UNet backbone with Feature-wise Linear Modulation (FiLM) injection of GBS data was used to demonstrate the initial proof-of-concept modeling in this research. This research also lists ideal characteristics for GM or GenAI datasets for RS. The code and a subset of the NOAH dataset (NOAH mini) are made open-sourced. Full article

Objectives: Artificial intelligence (AI) is a transformative development in the field of medicine. In the field of musculoskeletal radiology, agentic AI is a technology that could flourish, but currently, the limited evidence base is fragmented and sparse, and we present a scoping review of it. Methods: Parallel searches were conducted in four databases: PubMed, Embase, Scopus, and Web of Science. Search terms included all agentic AI and autonomous AI agents, as well as radiology. All papers underwent screening by two independent reviewers, with conflicts resolved through consensus. Initially, inclusion criteria involved all papers on general radiology, which were later stratified for musculoskeletal radiology and applicable papers to ensure inclusion of all suitable studies. A thematic analysis was undertaken by two independent reviewers. Results: Eleven studies met the inclusion criteria, comprising two MSK (musculoskeletal)-specific and nine general radiology papers applicable to MSK workflows. Four key themes emerged. Agentic decision support was demonstrated across five studies, showing improved diagnostic coordination, pathway navigation, and reduced clinician workload. Workflow optimisation was highlighted in four studies, with agentic systems enhancing administrative efficiency, modality selection, and overall radiology throughput. Image analysis and reconstruction were improved in three studies, with multi-agent systems enabling enhanced image quality and automated interpretation. Finally, four studies addressed conceptual, ethical, and governance considerations, emphasising the need for transparency, safety frameworks, and clinician oversight. Conclusion: Agentic AI shows considerable promise for enhancing MSK radiology through improved decision support, image analysis, and workflow efficiency; however, the current evidence remains limited and largely theoretical. Full article

Bariatric surgery is an effective treatment for morbid obesity but is frequently complicated by anastomotic leaks, fistulas, and strictures, which can significantly impair patient outcomes. Optimal management of these complications relies on a timely and accurate diagnostic assessment; however, effective treatment strategies are central to improving clinical recovery. This review primarily focuses on the endoscopic management of post-bariatric surgery complications, while providing a concise overview of the diagnostic imaging modalities that guide therapeutic decision-making. Contrast-enhanced imaging techniques, including computed tomography (CT) and fluoroscopy, as well as endoscopic ultrasound (EUS), are briefly discussed in relation to their role in identifying complications, defining their extent, and selecting the most appropriate endoscopic intervention. The core of this review is dedicated to current endoscopic treatment approaches, including endoscopic internal drainage with double pigtail plastic stents, self-expanding metal stents (SEMSs), endoscopic vacuum therapy (EVT), and EUS-guided drainage of fluid collections. Particular emphasis is placed on indications, technical considerations, and outcomes of these therapies. Finally, this review highlights emerging endoscopic technologies that may further optimize the management of post-bariatric surgery complications and improve patient outcomes, underscoring the evolving role of minimally invasive endoscopic treatment within a multidisciplinary framework. Full article