Search Results (5,614)

Multimodal studies of prostate cancer typically report aggregate fusion gains from histology and transcriptomics but rarely characterize when each modality is informative. We asked whether morphology and transcriptomics contribute differently to distinct clinical endpoints, using Gleason grading and nodal status prediction. On 401 TCGA-PRAD patients with matched whole-slide images, bulk RNA sequencing, and clinical data, we evaluated 45 morphological configurations, seven RNA configurations, and six fusion strategies across four grading formulations, T-stage, and N-stage. To avoid per-task model selection, morphology used a single fixed configuration (gated ABMIL on UNI features). Contribution estimates used repeated stratified five-fold cross-validation, with a locked conformal-prediction protocol and gene set enrichment analysis. The two endpoints showed opposite modality dependence. For Gleason grade, the fixed morphological model exceeded the best RNA configuration across all 45 configurations (five-class macro-F1: 0.445 versus 0.398). For nodal status, no morphological configuration exceeded AUROC 0.62, whereas transcriptomics reached 0.68 (permutation p = 0.037); a direct interaction test confirmed the reversal (bootstrap 95% CI excluding zero). Fusion gains were modest and task-dependent; enrichment analysis linked the nodal signal to loss of smooth muscle programs, consistent with established dedifferentiation biology. The informative modality is task-dependent: morphology predicts grade, transcriptomics predicts nodal status. Full article

Transferring unmanned surface vehicle (USV) algorithms from simulation to physical vessels is constrained by heterogeneous hardware interfaces, degraded wireless links, and ambiguous boundaries between human and autonomous control. This study designs and implements a ship–shore cooperative experimental platform comprising a shore control station, a portable control terminal, and an onboard system. The platform integrates multimodal sensing, private-radio and 4G/5G communication, an independent short-range remote-control (RC) path, and hardware arbitration. Small, safety-relevant commands are transmitted redundantly over the heterogeneous links using a shared application protocol with sequence-based deduplication. A two-dimensional control-authority model separates the authorized control source (shore, portable terminal, or short-range RC) from the active onboard behavior (path following, local collision avoidance, or safety protection) to organize fail-safe degradation and control transfer. Geometric light detection and ranging (LiDAR) obstacle detection and optimal reciprocal collision avoidance provide a representative onboard avoidance workflow. Full-scale vessel tests closed the loop from mission dispatch and command parsing to actuation and status feedback and demonstrated autonomous navigation, human takeover, and local collision avoidance. Across four water environments, the platform recorded 5.39 h of multimodal data over 18.26 km of valid trajectories. The results establish a physical testbed for ship–shore cooperative control, algorithm transfer, and multimodal data acquisition. Full article

Accurate and efficient early pregnancy diagnosis (EPD) in livestock is crucial for optimizing breeding management and enhancing productivity in modern animal husbandry. Over the past century, EPD technology has evolved from empirical methods to sophisticated techniques, encompassing biochemical marker detection, ultrasonic imaging, and further extending to emerging non-invasive approaches such as infrared thermography (IRT) and spectroscopic analysis. These advancements have not only improved diagnostic accuracy but also broadened the research scope to include small livestock and multiple species. This review critically examines the historical evolution, current methodologies, and applications of EPD technology, with a focus on analyzing the advantages and limitations of both traditional and emerging techniques. Additionally, it explores the potential of multimodal fusion strategies and artificial intelligence (AI) in EPD. At present, machine vision, wearable monitoring, and several AI applications remain prospective approaches rather than validated tools for routine EPD. The conclusion highlights that, despite significant progress, current technologies still face limitations in achieving in situ, non-contact, and high-throughput detection. Looking ahead, the integration of cutting-edge technologies, such as AI, small wearable sensors, and physiological time-series data analysis, holds promise for overcoming these bottlenecks, enabling more intelligent and efficient pregnancy diagnosis, and providing scientific support for modern animal husbandry. Full article

Tabletop role-playing game (TTRPG) research increasingly produces complex multimodal and multimedia evidence, including speech, audiovisual recordings, character sheets, maps, platform traces, session notes, game-state data, and retrospective documentation. However, the field lacks a stable methodological infrastructure for organizing, comparing, retrieving, and reusing these heterogeneous forms of play-derived evidence. This article presents a scoping review of 35 studies on computational, multimodal, multimedia, and knowledge-organization approaches to TTRPG-derived data. The findings show that this research is fragmented across publication venues, data types, analytical aims, and levels of formalization. Existing studies combine qualitative interpretation, discourse and conversation analysis, player-experience evaluation, structured datasets, natural language processing, semantic annotation, AI-assisted generation, and controlled vocabularies, but these approaches remain weakly coordinated across disciplinary vocabularies, data models, and formalization practices. To address this gap, the article proposes a Polyvocal Semantic Infrastructure for TTRPG research. Structured through a semantic atlas and scope ladder, this framework addresses persistent ambiguity in how objects and terms are defined across communities, systems, and disciplines while preserving interpretive plurality and supporting comparison, retrieval, provenance tracking, and future AI-assisted analysis of TTRPG-derived multimedia play data. Full article

Maxillary expansion combines sutural skeletal displacement with variable alveolar, dental, and periodontal responses. Because these effects are often reported as a single transverse outcome, their biological contributions are difficult to separate. We reviewed clinical, histological, and experimental evidence on midpalatal and circummaxillary sutural remodeling, alveolar deformation, anchorage-related periodontal loading, and used this evidence to formulate a three-compartment model. The sutural skeletal domain is the intended orthopedic target; the alveolar and dentoalveolar domain describes adaptive load transfer; and the anchorage-related periodontal domain captures non-target tissue responses. These labels describe treatment roles and do not imply a fixed sequence or biological independence. Experimental studies report overlapping mechanosensing, cellular recruitment, osteoclast-related margin turnover, immune and vascular activity, and osteogenesis within expanded sutures. Direct longitudinal molecular data in humans remain scarce, and the order of these events is unresolved. Clinical imaging also shows that comparable transverse corrections can contain different proportions of sutural opening, alveolar bending, dental tipping, and buccal cortical change. The model distinguishes skeletal correction from accompanying dentoalveolar and periodontal effects and yields testable predictions for multimodal imaging, tissue-specific biological measurements, histology, and patient-specific computational modeling. We present it as a provisional analytic model, not as a validated biological classification or clinical prediction rule. Full article

Accurate prediction of critical temperature, pressure, and volume is essential for thermodynamic modeling and process safety design, yet remains challenging for complex molecules under data-scarce conditions. Here, we develop a multimodal GNN-BERT framework that integrates SMILES-based chemical semantics with two-dimensional topology and three-dimensional molecular geometry for critical property prediction. BERT captures molecular sequence information, while graph neural networks learn topology- and geometry-aware representations through message passing. Evaluation on 913 chemical compounds demonstrates that the proposed framework consistently outperforms conventional machine-learning models and single-modality baselines. Importantly, comparative analyses among BERT, BERT+2D-GNN, and BERT+3D-GNN reveal that incorporating three-dimensional molecular geometry provides a consistent 5–10% improvement across critical temperature, pressure, and volume prediction. Additional validation using random forest and support vector regression further confirms that the predictive contribution of 3D molecular information is not architecture-dependent. These results highlight three-dimensional molecular geometry as an important structural parameter for data-driven critical property prediction and provide a reliable computational strategy for thermodynamic estimation and chemical process safety applications. Full article

This narrative review synthesizes a comprehensive multimodal characterization framework for atrial fibrillation (AF), tracing its progression from patient-specific anatomical reconstruction to electrophysiological phenotyping and standardized spatial mapping. The literature was identified through searches of PubMed, Web of Science, and Google Scholar, covering publications from January 2010 to June 2026, with additional studies identified from relevant references. Anatomical characterization leverages clinical imaging modalities alongside advanced deep learning models to execute precise whole-chamber, subregional, and tissue-level modeling. Electrophysiological profiling spans multi-scale modalities, including 12-lead electrocardiography (ECG), body surface potential mapping (BSPM), electrocardiographic imaging (ECGI), and electroanatomical mapping (EAM), complemented by wearable sensors for longitudinal rhythm surveillance. To bridge heterogeneous datasets across subjects and modalities, standardized coordinate systems and multimodal registration enable reproducible data integration. These integrated data parameterize patient-specific computational models to advance mechanistic insight, risk stratification, and personalized AF management. However, broad clinical translation remains constrained by imaging variability, reconstruction noise, registration uncertainty, and limited prospective multicenter validation. Future progress hinges on moving beyond technical accuracy toward prospective trials evaluating algorithm-guided clinical utility. Full article

Manual industrial patrol inspection relies heavily on on-site visual observation, while the visual attention of inspectors toward specific target equipment is difficult to quantify. This study proposes an industrial patrol inspection visual attention analysis method integrating eye tracking and deep learning-based object detection. A wearable eye-tracking device is used to acquire first-person inspection videos, eye-tracking data, and camera parameters. After temporal alignment of the multimodal data, the 3D gaze points are projected onto the corresponding 2D inspection video frames. YOLO12m is employed to detect target equipment, followed by frame-by-frame matching between the 2D gaze points and the equipment bounding boxes. Based on the matching results, seven visual attention metrics are calculated to quantitatively characterize visual attention during patrol inspection. On-site experiments with 10 participants yielded 21 inspection records, with overall visual attention scores ranging from 43.16 to 89.71 and averaging 75.99. Three experts independently rated the 21 records, and the system-generated ratings agreed with the majority expert ratings for 19 records. These results demonstrate that, under the present experimental conditions, the proposed method can quantify the visual attention of inspectors toward specific target equipment during industrial patrol inspection using multiple metrics and provide interpretable results. Full article

Background/Objectives: The accelerating integration of machine learning (ML) with molecular, imaging, and physiological data is transforming Alzheimer’s disease (AD) research. Methods & Results: Recent studies demonstrate that multimodal, AI-assisted platforms can enhance early diagnosis, predict biomarker trajectories, and identify novel therapeutic targets. This mini-review covers the evolving AD diagnostic and biomarker frameworks, current therapeutic strategies including recently approved anti-amyloid immunotherapies, and advances from contemporary studies employing ML across diverse data streams, ranging from cerebrospinal fluid (CSF) and plasma proteomics to Raman spectroscopy, neuroimaging, transcriptomics, and microbiome signatures. Conclusions: Collectively, they illustrate how artificial intelligence (AI) has shifted A biomarker discovery from univariate to network-based inference, achieving clinically relevant accuracy while emphasizing model interpretability. We discuss biological insights, translational implications, and persisting challenges related to validation, bias, and regulatory integration. Full article

Background: Vaccines for Group B Streptococcus (GBS) intended for pregnant women are currently in advanced stages of clinical trials. Conducting preparatory research now can help identify factors influencing GBS vaccine acceptance and potential challenges to future implementation. Methods: This qualitative study recruited participants nationally through social media and antenatal clinics of a maternity hospital in South Australia between December 2024 and August 2025. Eligible participants were pregnant women aged ≥18 years residing in Australia. Online interviews and focus group discussions (FGDs) were held to explore pregnant women’s knowledge and perceptions of GBS, experiences with current screening and management strategies, and views on future maternal GBS vaccination. Twenty-five women participated in FGDs and six in individual interviews; FGD group sizes ranged from two to five participants. Data were analysed using inductive content analysis. Results: A total of 31 pregnant women participated, aged 19–43 years. Most participants (51.6%) were from South Australia, 87.1% had tertiary education, and 51.6% were employed in the health sector. Five themes were identified: (1) infant wellbeing is the dominant driver of vaccine acceptance, (2) maternal vaccination is preferred over current antibiotic prophylaxis, (3) perceived uncertainty about vaccine safety and knowledge gaps fuel caution, (4) accessible and flexible vaccination delivery models are desired, and (5) multimodal, woman-centred communication delivered through trusted healthcare providers is required. Conclusions: Findings highlight the importance of addressing knowledge and safety concerns and incorporating accessible, flexible and woman-centred approaches into the planning of future maternal GBS vaccination programmes. Full article

Fisetin, a naturally occurring flavonoid, has garnered interest as a potential intervention for age-related diseases due to its anti-inflammatory, antioxidant, and senolytic properties, as demonstrated primarily in preclinical studies. We conducted a structured search and evaluated human translational and clinical studies that utilize fisetin to improve clinical markers associated with age-related low-grade inflammatory diseases. Building on preclinical work and observational studies in humans consuming flavonoid-rich diets or supplements, we evaluated 34 registered clinical trials on ClinicalTrials.gov and the WHO International Clinical Trials Registry Platform (ICTRP) with a focus on aging/frailty, metabolic diseases, cancer, cardiovascular diseases, neuroimmune/neurodegenerative diseases, and other chronic age-related diseases. We provide the status of the 34 registered trials and a synthesis and discussion of the 4 completed trials with available results that included fisetin, identifying gaps and areas for future investigation. Overall, the completed trials indicate that clinical evidence for fisetin remains limited and heterogeneous. While some studies reported favorable changes in metabolic or inflammatory outcomes, others found no clear or significant clinical benefit. Interpretation is further limited by small sample sizes, multimodal interventions, and uncontrolled or exploratory designs, making it difficult to establish fisetin efficacy in humans. Early findings in animal models and in human cell lines suggest that fisetin has the potential to mitigate age-related diseases by targeting chronic inflammation and oxidative stress driven by increased senescent cell burden, but more clinical data are needed. Full article

Short-term cross-border prediction is of significant importance for global supply-chain risk management, international trade decision-making, and stability. However, existing approaches mainly rely on individual price sequences or limited structured variables, making it difficult to effectively perceive complex external factors, including cross-border trade flows, logistics state variations, exchange-rate fluctuations, and policy-driven shocks. To address these challenges, an artificial intelligence-driven sensing-oriented reliability- and consistency-aware multimodal framework for short-term cross-border prediction is proposed. Market conditions, exchange rates, cross-border trade activities, logistics operations, and news–policy events are jointly modeled as multisource intelligent sensing signals. In the proposed framework, the reliability and cross-modal consistency perception module is first developed to dynamically evaluate the credibility of different data sources and suppress the interference caused by missing, delayed, and conflicting information. Subsequently, the asynchronous cross-border temporal interaction module is introduced to capture the time-dependent propagation relationships among trade, logistics, exchange rates, and states. Furthermore, the dynamic trade and policy event perception module is constructed to identify short-term disturbances induced by tariff adjustments, trade restrictions, port disruptions, and major international events, thereby enabling intelligent prediction under complex cross-border environments. Based on a multisource cross-border sensing dataset constructed from January 2022 to December 2025, the performance of the proposed framework is systematically evaluated through three tasks, including short-term direction prediction, volatility forecasting, and risk level prediction. Experimental results demonstrate that the proposed method achieves an accuracy of 0.842, precision of 0.836, recall of 0.829, macro-F1 of 0.832, and AUC of 0.913 in the short-term direction prediction task, significantly outperforming ARIMA, XGBoost, LSTM, TCN, Transformer, PatchTST, and existing multimodal fusion models. Ablation studies further verify the critical contributions of reliability modeling, consistency constraints, asynchronous temporal interaction, and dynamic event perception modules to improving prediction performance. Full article

Preeclampsia remains one of the leading causes of maternal and perinatal morbidity and mortality worldwide. Although current first-trimester screening strategies have improved risk assessment, their predictive performance remains limited by the biological complexity and heterogeneity of the disease. Artificial intelligence (AI) has emerged as a promising approach capable of integrating multidimensional clinical and biological data to improve early prediction. This review aims to summarize current evidence regarding AI-based prediction models for preeclampsia, compare their performance with conventional screening strategies, and discuss future directions for clinical implementation. A narrative review of published studies evaluating machine learning and deep learning models for first-trimester prediction of preeclampsia was performed. Studies incorporating maternal characteristics, hemodynamic variables, biochemical biomarkers, imaging, radiomics, and multi-omics data were reviewed. Diagnostic performance, predictor variables, and validation strategies were critically compared. Several studies have reported improved predictive performance of AI models compared with conventional statistical approaches, particularly when multimodal datasets were incorporated. High-performing models achieved area under the receiver operating characteristic curve (AUC) values ranging from 0.84 to 0.92. Across studies, maternal clinical characteristics, mean arterial pressure, uterine artery pulsatility index, placental growth factor, and pregnancy-associated plasma protein-A were the most consistently identified predictors. However, direct comparisons remain limited by methodological heterogeneity. Emerging approaches incorporating inflammatory biomarkers, cell-free nucleic acids, radiomics, and multi-omics technologies showed encouraging results but currently lack sufficient prospective multicenter validation for routine clinical implementation. AI has considerable potential to improve first-trimester prediction of preeclampsia, although prospective multicenter validation, standardized reporting, and implementation studies remain necessary before routine clinical adoption. Future research should prioritize prospective multicenter validation, standardized data collection, explainable AI, and seamless integration into clinical workflows to facilitate implementation in precision obstetric care. Full article

Multimodal large language models (MLLMs) and vision–language models (VLMs) have rapidly entered medicine, demonstrating promising performance in clinical reasoning, radiology report generation, and visual question answering (VQA). However, many current multimodal architectures and pretrained visual backbones remain fundamentally rooted in two-dimensional (2D) image processing, even though major clinical imaging modalities, including computed tomography (CT), magnetic resonance imaging (MRI), optical coherence tomography (OCT), and echocardiography, are inherently volumetric or temporal. This narrative review examines the transition from 2D vision–language systems to volumetric multimodal AI, tracing the evolution from 2D and slice- or projection-based approaches through sequential and video-like methods to three-dimensional (3D) vision foundation models and native 3D VLMs/MLLMs. We examine their representational and computational trade-offs, evaluation gaps, and clinically grounded benchmarks. Approaches differ substantially in how they represent and preserve 3D information. Slice- and projection-based methods offer computational efficiency but may discard spatial context, whereas sequential and native volumetric approaches increasingly model relationships across the full imaging study. Recent 3D foundation models and multimodal systems demonstrate the feasibility of reusable volumetric representations and language-enabled 3D image interpretation, but face barriers in computational cost, training-data scale, evaluation methodology, and clinical reliability. Only 53% of Med-Gemini-3D reports were judged clinically acceptable, and natural language processing (NLP) metrics such as BLEU and ROUGE correlate poorly with diagnostic correctness. True 3D multimodal medical intelligence remains in its early stages. Future progress requires efficient volumetric representation strategies, clinically grounded evaluation frameworks, standardized benchmarks, and robust cross-institution validation. Full article