{"ID":2882752,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.09715","arxiv_id":"2508.09715","title":"NEURAL: Attention-Guided Pruning for Unified Multimodal Resource-Constrained Clinical Evaluation","abstract":"The rapid growth of multimodal medical imaging data presents significant storage and transmission challenges, particularly in resource-constrained clinical settings. We propose NEURAL, a novel framework that addresses this by using semantics-guided data compression. Our approach repurposes cross-attention scores between the image and its radiological report from a fine-tuned generative vision-language model to structurally prune chest X-rays, preserving only diagnostically critical regions. This process transforms the image into a highly compressed, graph representation. This unified graph-based representation fuses the pruned visual graph with a knowledge graph derived from the clinical report, creating a universal data structure that simplifies downstream modeling. Validated on the MIMIC-CXR and CheXpert Plus dataset for pneumonia detection, NEURAL achieves a 93.4-97.7\\% reduction in image data size while maintaining a high diagnostic performance of 0.88-0.95 AUC, outperforming other baseline models that use uncompressed data. By creating a persistent, task-agnostic data asset, NEURAL resolves the trade-off between data size and clinical utility, enabling efficient workflows and teleradiology without sacrificing performance. Our NEURAL code is available at https://github.com/basiralab/NEURAL.","short_abstract":"The rapid growth of multimodal medical imaging data presents significant storage and transmission challenges, particularly in resource-constrained clinical settings. We propose NEURAL, a novel framework that addresses this by using semantics-guided data compression. Our approach repurposes cross-attention scores betwee...","url_abs":"https://arxiv.org/abs/2508.09715","url_pdf":"https://arxiv.org/pdf/2508.09715v1","authors":"[\"Devvrat Joshi\",\"Islem Rekik\"]","published":"2025-08-13T11:08:09Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.LG\"]","methods":"[\"Language Model\"]","has_code":false,"code_links":[{"ID":610920,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2882752,"paper_url":"https://arxiv.org/abs/2508.09715","paper_title":"NEURAL: Attention-Guided Pruning for Unified Multimodal Resource-Constrained Clinical Evaluation","repo_url":"https://github.com/basiralab/NEURAL","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}