MAIRA-2: Grounded Radiology Report Generation
This addresses the problem of generating verifiable and useful radiology reports for clinical practice, though it is incremental in enhancing performance with context and localization.
The paper tackles automated radiology report generation by introducing grounded reporting that localizes findings on images, and develops MAIRA-2, a model that achieves state-of-the-art on existing benchmarks and establishes this new task.
Radiology reporting is a complex task requiring detailed medical image understanding and precise language generation, for which generative multimodal models offer a promising solution. However, to impact clinical practice, models must achieve a high level of both verifiable performance and utility. We augment the utility of automated report generation by incorporating localisation of individual findings on the image - a task we call grounded report generation - and enhance performance by incorporating realistic reporting context as inputs. We design a novel evaluation framework (RadFact) leveraging the logical inference capabilities of large language models (LLMs) to quantify report correctness and completeness at the level of individual sentences, while supporting the new task of grounded reporting. We develop MAIRA-2, a large radiology-specific multimodal model designed to generate chest X-ray reports with and without grounding. MAIRA-2 achieves state of the art on existing report generation benchmarks and establishes the novel task of grounded report generation.