MAIRA-Seg: Enhancing Radiology Report Generation with Segmentation-Aware Multimodal Large Language Models
This addresses the problem of generating more accurate radiology reports for clinicians, though it appears incremental as it builds on existing MAIRA architectures.
The paper tackled improving radiology report generation for chest X-rays by incorporating segmentation masks into multimodal large language models, finding that their MAIRA-Seg framework outperformed non-segmentation baselines on the MIMIC-CXR dataset.
There is growing interest in applying AI to radiology report generation, particularly for chest X-rays (CXRs). This paper investigates whether incorporating pixel-level information through segmentation masks can improve fine-grained image interpretation of multimodal large language models (MLLMs) for radiology report generation. We introduce MAIRA-Seg, a segmentation-aware MLLM framework designed to utilize semantic segmentation masks alongside CXRs for generating radiology reports. We train expert segmentation models to obtain mask pseudolabels for radiology-specific structures in CXRs. Subsequently, building on the architectures of MAIRA, a CXR-specialised model for report generation, we integrate a trainable segmentation tokens extractor that leverages these mask pseudolabels, and employ mask-aware prompting to generate draft radiology reports. Our experiments on the publicly available MIMIC-CXR dataset show that MAIRA-Seg outperforms non-segmentation baselines. We also investigate set-of-marks prompting with MAIRA and find that MAIRA-Seg consistently demonstrates comparable or superior performance. The results confirm that using segmentation masks enhances the nuanced reasoning of MLLMs, potentially contributing to better clinical outcomes.