X-Rays are a form of electromagnetic radiation with wavelengths shorter than visible light but longer than gamma rays. They are capable of penetrating various materials, making them useful for medical imaging, such as detecting fractures or tumors. X-rays are generated by high-energy electron interactions with matter, typically in an X-ray tube. In medical and industrial applications, they create images by passing through the body or objects, with denser materials (like bones) absorbing more X-rays and appearing white, while less dense materials (like tissues) allow more X-rays to pass through and appear darker. X-ray technology is critical for diagnosis and non-destructive testing.

Posts

Reducing Hallucinations of Medical Multimodal Large Language Models with Visual Retrieval-Augmented Generation

/in /by

Multimodal Large Language Models (MLLMs) have shown impressive performance in vision and text tasks. However, hallucination remains a major challenge, especially in fields like healthcare where details are critical. In this work, we show how MLLMs may be enhanced to support Visual RAG (V-RAG), a retrieval-augmented generation framework that incorporates both text and visual data from retrieved images. On the MIMIC-CXR chest X-ray report generation and Multicare medical image caption generation datasets, we show that Visual RAG improves the accuracy of entity probing, which asks whether a medical entities is grounded by an image. We show that the improvements extend both to frequent and rare entities, the latter of which may have less positive training data. Downstream, we apply V-RAG with entity probing to correct hallucinations and generate more clinically accurate X-ray reports, obtaining a higher RadGraph-F1 score.

Read more