Cycle-VQA: A Cycle-Consistent Framework for Robust Medical Visual Question Answering

Abstract

Medical Visual Question Answering (Med-VQA) presents greater challenges than traditional Visual Question Answering (VQA) due to the diversity of clinical questions and the complexity of visual reasoning. To address these challenges, we propose Cycle-VQA, a unified framework designed to enhance the reliability and robustness of Med-VQA systems. The framework leverages cycle consistency to establish bidirectional information flow among questions, answers, and visual features, strengthening reasoning stability and ensuring accurate feature integration. Inspired by clinical diagnostic processes, Cycle-VQA incorporates key pathological attributes and introduces a novel multi-modal attribute cross-fusion strategy designed to effectively capture shared and unique features across modalities. Experimental results on Gastrointestinal Stromal Tumors (GISTs) and public Med-VQA datasets diagnosis validate the effectiveness of Cycle-VQA, demonstrating its potential to advance medical image analysis and support reliable clinical decision-making.