Neuropathic pain (NeuP), defined as pain arising from lesions or disease of the somatosensory system, remains difficult to manage due to limited treatment efficacy and frequent side effects. As a neurosteroid with anti-inflammatory properties, vitamin D 3 may offer additional benefits in NeuP therapy. This study evaluated the effectiveness of combining vitamin D 3 with gabapentin in a rat model of chronic constriction injury (CCI). Adult Wistar rats were assigned to seven groups: normal, sham, negative control (CCI), positive control (gabapentin), and three intervention groups receiving gabapentin plus vitamin D 3 at 500, 1,000, or 4,000 IU for 28 days. Combination therapy significantly reduced hyperalgesia ( p < 0.05), but not allodynia, in a dose-dependent manner, which corresponded with decreased transient receptor potential vanilloid 1 (TRPV1) expression in peripheral nerves. Gabapentin alone and combination therapy reduced inflammatory cell infiltration. These findings suggest that vitamin D 3 supplementation in gabapentin-treated rats was associated with improved antihyperalgesic outcomes, possibly through TRPV1 modulation.
This study presents a keyword-guided cross-attention framework for automated radiological report generation from 3D FLAIR MRI brain tumor images. The architecture integrates M3D-CLIP image encoder with hierarchical keyword extraction using fine-tuned KeyBERT and BioBERT semantic embeddings in a 768-dimensional space. Six cross-attention layers fuse visual features with clinical keywords extracted across four hierarchical levels: abnormality type, lesion characteristics, anatomical location, and lateralization. A four-layer transformer decoder generates captions autoregressively. The BraTS2020 dataset containing 369 glioma patients paired with TextBraTS radiological descriptions was preprocessed with center-focused slice selection of 32 from 155 slices and spatial interpolation to 256×256 resolution. Training on NVIDIA RTX 3050 GPU for 15 epochs using AdamW optimizer achieved loss reduction from 4.16 to 1.33. Evaluation on 20 test samples demonstrated BLEU-1 of 0.5359, BLEU-2 of 0.3969, and ROUGE-L of 0.5051, with generated captions accurately capturing clinical information for decision support applications.• Multi-modal fusion through keyword-guided cross-attention integrating visual MRI features with hierarchical clinical terminology• Transformer-based autoregressive generation conditioned on enriched image-keyword representations• Comprehensive evaluation using BLEU and ROUGE metrics on brain tumor caption generation task