Tag
This research paper introduces a framework for zero-shot respiratory sound classification by aligning audio encoders with medical terminology through LLM-synthesized reports, outperforming models like CLAP and Qwen2-Audio in clinical diagnostic tasks.
Holtercare-Bench is a multimodal benchmark introduced to evaluate long-term dynamic ECG analysis using the Holtercare-23K dataset, revealing performance gaps in current MLLMs and providing improvements through fine-tuning for clinical applications.
MedFocusLeak introduces the first transferable black-box adversarial attack on medical vision-language models, using imperceptible background perturbations to mislead clinical diagnoses across six imaging modalities.