Vision-Language Generative Model for View-Specific Chest X-ray Generation

TL;DR

ViewXGen is a novel vision-language generative model that produces realistic, view-specific chest X-rays by incorporating view tokens and multi-view data, improving the fidelity and clinical relevance of synthetic medical images.

Contribution

The paper introduces ViewXGen, a new approach that generates view-specific chest X-rays considering diverse view positions and multi-view information, surpassing existing report-based methods.

Findings

High realism in generated X-rays confirmed by human evaluation

Statistical analysis shows improved clinical efficacy metrics

Effective incorporation of multi-view data enhances abnormality representation

Abstract

Synthetic medical data generation has opened up new possibilities in the healthcare domain, offering a powerful tool for simulating clinical scenarios, enhancing diagnostic and treatment quality, gaining granular medical knowledge, and accelerating the development of unbiased algorithms. In this context, we present a novel approach called ViewXGen, designed to overcome the limitations of existing methods that rely on general domain pipelines using only radiology reports to generate frontal-view chest X-rays. Our approach takes into consideration the diverse view positions found in the dataset, enabling the generation of chest X-rays with specific views, which marks a significant advancement in the field. To achieve this, we introduce a set of specially designed tokens for each view position, tailoring the generation process to the user's preferences. Furthermore, we leverage multi-view chest X-rays as input, incorporating valuable information from different views within the same study. This integration rectifies potential errors and contributes to faithfully capturing abnormal findings in chest X-ray generation. To validate the effectiveness of our approach, we conducted statistical analyses, evaluating its performance in a clinical efficacy metric on the MIMIC-CXR dataset. Also, human evaluation demonstrates the remarkable capabilities of ViewXGen, particularly in producing realistic view-specific X-rays that closely resemble the original images.