Any-to-Any Vision-Language Model for Multimodal X-ray Imaging and Radiological Report Generation

TL;DR

This paper presents a specialized multimodal generative framework for medical imaging and report synthesis, demonstrating high-quality image and report generation that benefits clinical tasks and advances AI in healthcare.

Contribution

The work introduces a domain-specific multimodal generative model tailored for medical data, achieving superior image and report synthesis for radiology applications.

Findings

High-fidelity image generation with low FID scores

Semantically coherent report generation with high BLEU scores

Comparable or better disease classification performance using generated data

Abstract

Generative models have revolutionized Artificial Intelligence (AI), particularly in multimodal applications. However, adapting these models to the medical domain poses unique challenges due to the complexity of medical data and the stringent need for clinical accuracy. In this work, we introduce a framework specifically designed for multimodal medical data generation. By enabling the generation of multi-view chest X-rays and their associated clinical report, it bridges the gap between general-purpose vision-language models and the specialized requirements of healthcare. Leveraging the MIMIC-CXR dataset, the proposed framework shows superior performance in generating high-fidelity images and semantically coherent reports. Our quantitative evaluation reveals significant results in terms of FID and BLEU scores, showcasing the quality of the generated data. Notably, our framework achieves comparable or even superior performance compared to real data on downstream disease classification tasks, underlining its potential as a tool for medical research and diagnostics. This study highlights the importance of domain-specific adaptations in enhancing the relevance and utility of generative models for clinical applications, paving the way for future advancements in synthetic multimodal medical data generation.