BIMCV-RG

数据集说明

BIMCV-RG 对应论文数据集（arXiv 预印本）。

数据获取指引

1. 打开论文页面获取作者与项目信息：https://arxiv.org/abs/2406.07146v1
2. 论文 Data Availability / Code Availability 章节标注了数据实际托管位置；
3. 获取到实际数据链接后，按对应平台标准方式下载。

论文摘要：Abstract: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].

论文页面：https://arxiv.org/abs/2406.07146v1