Multi-modal Pre-training for Medical Vision-language Understanding and Generation: An Empirical Study with A New Benchmark
This work addresses the problem of limited pre-training resources and guidance for medical vision-language tasks, providing a new dataset and benchmarks for researchers, though it is incremental as it adapts existing methods to a specific domain.
The authors tackled the lack of vision-language pre-training studies in the medical domain by conducting an empirical analysis with a new benchmark dataset, RadioGraphy Captions, and developed key insights and strong baselines for tasks like medical report generation and image-text retrieval.
With the availability of large-scale, comprehensive, and general-purpose vision-language (VL) datasets such as MSCOCO, vision-language pre-training (VLP) has become an active area of research and proven to be effective for various VL tasks such as visual-question answering. However, studies on VLP in the medical domain have so far been scanty. To provide a comprehensive perspective on VLP for medical VL tasks, we conduct a thorough experimental analysis to study key factors that may affect the performance of VLP with a unified vision-language Transformer. To allow making sound and quick pre-training decisions, we propose RadioGraphy Captions (RGC), a high-quality, multi-modality radiographic dataset containing 18,434 image-caption pairs collected from an open-access online database MedPix. RGC can be used as a pre-training dataset or a new benchmark for medical report generation and medical image-text retrieval. By utilizing RGC and other available datasets for pre-training, we develop several key insights that can guide future medical VLP research and new strong baselines for various medical VL tasks.