{"ID":2846067,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.02271","arxiv_id":"2511.02271","title":"Medical Report Generation: A Hierarchical Task Structure-Based Cross-Modal Causal Intervention Framework","abstract":"Medical Report Generation (MRG) is a key part of modern medical diagnostics, as it automatically generates reports from radiological images to reduce radiologists' burden. However, reliable MRG models for lesion description face three main challenges: insufficient domain knowledge understanding, poor text-visual entity embedding alignment, and spurious correlations from cross-modal biases. Previous work only addresses single challenges, while this paper tackles all three via a novel hierarchical task decomposition approach, proposing the HTSC-CIF framework. HTSC-CIF classifies the three challenges into low-, mid-, and high-level tasks: 1) Low-level: align medical entity features with spatial locations to enhance domain knowledge for visual encoders; 2) Mid-level: use Prefix Language Modeling (text) and Masked Image Modeling (images) to boost cross-modal alignment via mutual guidance; 3) High-level: a cross-modal causal intervention module (via front-door intervention) to reduce confounders and improve interpretability. Extensive experiments confirm HTSC-CIF's effectiveness, significantly outperforming state-of-the-art (SOTA) MRG methods. Code will be made public upon paper acceptance.","short_abstract":"Medical Report Generation (MRG) is a key part of modern medical diagnostics, as it automatically generates reports from radiological images to reduce radiologists' burden. However, reliable MRG models for lesion description face three main challenges: insufficient domain knowledge understanding, poor text-visual entity...","url_abs":"https://arxiv.org/abs/2511.02271","url_pdf":"https://arxiv.org/pdf/2511.02271v2","authors":"[\"Yucheng Song\",\"Yifan Ge\",\"Junhao Li\",\"Zhining Liao\",\"Zhifang Liao\"]","published":"2025-11-04T05:24:52Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Language Model\"]","has_code":false}