This study introduces the Medical Vision Attention Generation (MedVAG) model, a novel framework designed to facilitate the automated generation of medical reports. MedVAG integrates Vision Transformer (ViT)-based visual feature extraction and GPT-2 language modeling, enhanced by graph-based feature fusion and multiple attention mechanisms (co-attention, cross-attention, memory-guided attention), to ensure semantic coherence and diagnostic accuracy. Evaluated on IU X-Ray and COV-CTR datasets, the model achieved state-of-the-art performance across natural language generation metrics (BLEU, METEOR, ROUGE, CIDEr) and clinical effectiveness measures. Ablation studies highlighted the critical role of attention mechanisms and feature fusion in aligning visual and textual features. MedVAG demonstrates strong potential as an assistive technology, aiming to support radiologists by reducing workload and enhancing diagnostic accuracy.
Accurate classification of cherry varieties is crucial for their economic value and market differentiation, yet their genetic diversity and visual similarity make manual identification challenging, hindering efficient agricultural and trade practices. This study addresses this issue by proposing a novel deep learning-based hybrid model that integrates BiFPN with the YOLOv8n-cls framework, enhanced by Swin Transformer and Deformable Attention Transformer (DAT) techniques. The model was trained and evaluated on a newly constructed dataset comprising cherry varieties from Turkey’s Western Mediterranean region. Experimental results demonstrated the effectiveness of the proposed approach, achieving a precision of 91.91%, recall of 92.0%, F1-score of 91.93%, and an overall accuracy of 91.714%. The findings highlight the model’s potential to optimize harvest timing, ensure quality control, and support export classification, thereby contributing to improved agricultural practices and economic outcomes.
26 November 2025 in International Journal of Environmental Science and Technology
Accurate predictive modeling is critical for enhancing patient outcomes and facilitating personalized care. This study introduces a hybrid modelling framework that combines deep learning, transformer-based architectures, and classical regression methods. The framework integrates multiple approaches, including Artificial Neural Networks, Long Short-Term Memory Networks, Convolutional Neural Networks, Random Forest, to model complex patterns in insulin biomarker data. By integrating these models into a unified framework, the approach enhances predictive accuracy while ensuring interpretability. Explainable AI techniques, including SHAP and LIME, are employed to identify key features influencing predictions, thereby promoting transparency and clinical trust. The proposed framework achieves superior performance on clinical datasets, with improved metrics such as MSE, MAE, and R², outperforming baseline models. Additionally, it identifies critical biomarkers associated with insulin regulation. Subgroup-level interpretations provide clinically relevant insights that inform personalized treatment strategies. This work demonstrates how advanced machine learning, coupled with explainability, establishes a robust foundation for clinical decision support systems to deliver effective and individualized patient care.