Argus: Benchmarking and Enhancing Vision-Language Models for 3D Radiology Report Generation
This work addresses the problem of automating report generation for 3D radiology to assist radiologists, but it is incremental as it builds on existing vision-language models with domain-specific optimizations.
The paper tackled the lack of benchmarks and optimal training strategies for vision-language models in generating reports from 3D radiology images like CT scans, resulting in the Argus model family that achieves state-of-the-art performance across various sizes and resolutions, efficiently handling images up to 512x512x256.
Automatic radiology report generation holds significant potential to streamline the labor-intensive process of report writing by radiologists, particularly for 3D radiographs such as CT scans. While CT scans are critical for clinical diagnostics, they remain less explored compared to 2D radiographs. To date, there has been no comprehensive benchmark for 3D radiograph report generation (3DRRG), nor sufficient investigation into the optimal training strategies for Vision Language Models (VLMs) in this context, particularly with respect to vision encoder choices, visual token compression, and model scaling. In this work, we make three key contributions. We curate **CT-3DRRG**, the largest **publicly** available 3D CT-report dataset, establishing a robust and diverse benchmark for evaluating VLM performance on 3DRRG. Furthermore, we propose a comprehensive training recipe for building high-performing VLMs for 3DRRG, exploring key factors such as vision encoder pretraining strategies, visual token compression, and the impact of data & model scale. Guided by these findings, we introduce **Argus**, a state-of-the-art family of VLMs that achieve superior performance across different model sizes and input 3D medical image resolutions, efficiently processing high-resolution 3D images up to $512 \times 512 \times 256$[^1].