Hierarchical Modeling for Medical Visual Question Answering with Cross-Attention Fusion

Medical Visual Question Answering (Med-VQA) is designed to accurately answer medical questions by analyzing medical images when given both a medical image and its corresponding clinical question. Designing the MedVQA system holds profound importance in assisting clinical diagnosis and enhancing diagnostic accuracy. Building upon this foundation, Hierarchical Medical VQA extends Medical VQA by organizing medical questions into a hierarchical structure and making level-specific predictions to handle fine-grained distinctions. Recently, many studies have proposed hierarchical Med-VQA tasks and established datasets. However, several issues still remain: (1) imperfect hierarchical modeling leads to poor differentiation between question levels, resulting in semantic fragmentation across hierarchies. (2) Excessive reliance on implicit learning in Transformer-based cross-modal self-attention fusion methods, which can obscure crucial local semantic correlations in medical scenarios. To address these issues, this study proposes a Hierarchical Modeling for Medical Visual Question Answering with Cross-Attention Fusion (HiCA-VQA) method. Specifically, the hierarchical modeling includes two modules: Hierarchical Prompting for fine-grained medical questions and Hierarchical Answer Decoders. The hierarchical prompting module pre-aligns hierarchical text prompts with image features to guide the model in focusing on specific image regions according to question types, while the hierarchical decoder performs separate predictions for questions at different levels to improve accuracy across granularities. The framework also incorporates a cross-attention fusion module where images serve as queries and text as key-value pairs. This approach effectively avoids the irrelevant signals introduced by global interactions while achieving lower computational complexity compared to global self-attention fusion modules. Experiments on the Rad-Restruct benchmark demonstrate that the HiCA-VQA framework outperforms existing state-of-the-art methods in answering hierarchical fine-grained questions, especially achieving an 18 percent improvement in the F1 score. This study provides an effective pathway for hierarchical visual question answering systems, advancing medical image understanding.