@article{jcsa20261414,
author={{Gupta, Dr. A.Shilpa and Reddy, M. Uday and Reddy, K. Jayanth Kumar and Goud, P. Medha and Reddy, T. Harshitha and Jopat, Aditi},
title={Improving Medical Multimodal Retrieval with Graph-Rag and Fusion Methods with Mmedrag++},
journal={Journal of Computer Sciences and Applications},
volume={14},
number={1},
pages={21--30},
year={2026},
url={https://pubs.sciepub.com/jcsa/14/1/4},
issn={2328-725X},
abstract={We introduce MMedRAG++,a medical multimodal retrieval system that uses fusion-based representation learning and graph-based reranking (Graph-RAG) to improve on conventional Retrieval-Augmented Generation (RAG). Unlike baseline systems, which do not incorporate fusion strategies or graph-based reranking, MMedRAG++ improves cross-modal embeddings and retrieval coherence. Experiments are conducted primarily on PMC-OA, a challenging dataset with only ~10% unique captions and many unrelated image-text pairs, and IU-Xray is used for modality- specific subtasks. Graph-RAG demonstrates improved retrieval centrality and diversity, and fusion strategies, including Cross- Attention and DeepSet Fusion, enhance embedding quality. Quantitative evaluation on PMC-OA and IU-Xray confirms improved retrieval coherence and cross-modal alignment over baseline configurations. Top-1 Accuracy: 18.7%, Top-10 Accuracy: 57.4%.},
doi={10.12691/jcsa-14-1-4}
publisher={Science and Education Publishing}
}