Inventions

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.

Dual-target drug design addresses complex diseases and drug resistance, yet existing computational approaches struggle with simultaneous multi-protein optimization. This study presents SFG-Drug, a novel dual-target molecular generation model combining Monte Carlo tree search with gated recurrent unit neural networks for simultaneous MEK1 and mTOR targeting. The methodology employed DigFrag digital fragmentation on ZINC-250k dataset, integrated low-frequency masking techniques for enhanced diversity, and utilized molecular docking scores as reward functions. Comprehensive evaluation on MOSES benchmark demonstrated superior performance compared to state-of-the-art methods, achieving perfect validity (1.000), uniqueness (1.000), and novelty (1.000) scores with highest internal diversity indices (0.878 for IntDiv1, 0.860 for IntDiv2). Over 90% of generated molecules exhibited favorable binding affinity with both targets, showing optimal drug-like properties including QED values in [0.2, 0.7] range and high synthetic accessibility scores. Generated compounds demonstrated structural novelty with Tanimoto coefficients below 0.25 compared to known inhibitors while maintaining dual-target binding capability. The SFG-Drug model successfully bridges the gap between computational prediction and practical drug discovery, offering significant potential for developing new dual-target therapeutic agents and advancing AI-driven pharmaceutical research methodologies.

Gadolinium-based contrast agents (GBCAs) are vital for glioma imaging yet pose safety, cost, and accessibility issues; predicting contrast enhancement from non-contrast MRI via machine learning (ML) provides a safer, economical alternative, as enhancement indicates tumor aggressiveness and informs treatment planning. However, scanner and population variability hinder robust model selection. To overcome this, a stability-aware framework was developed to identify reproducible ML pipelines for predicting glioma contrast enhancement across multicenter cohorts. A total of 1367 glioma cases from four TCIA datasets (UCSF-PDGM, UPENN-GB, BRATS-Africa, BRATS-TCGA-LGG) were analyzed, using non-contrast T1-weighted images as input and deriving enhancement status from paired post-contrast T1-weighted images; 108 IBSI-standardized radiomics features were extracted via PyRadiomics 3.1, then systematically combined with 48 dimensionality reduction algorithms and 25 classifiers into 1200 pipelines, evaluated through rotational validation (training on three datasets, external testing on the fourth, repeated across rotations) incorporating five-fold cross-validation and a composite score penalizing instability via standard deviation. Cross-validation accuracies spanned 0.91–0.96, with external testing yielding 0.87 (UCSF-PDGM), 0.98 (UPENN-GB), and 0.95 (BRATS-Africa), averaging ~0.93; F1, precision, and recall remained stable (0.87–0.96), while ROC-AUC varied (0.50–0.82) due to cohort heterogeneity, with the MI + ETr pipeline ranking highest for balanced accuracy and stability. This framework enables reliable, generalizable prediction of contrast enhancement from non-contrast glioma MRI, minimizing GBCA dependence and offering a scalable template for reproducible ML in neuro-oncology.