Problem
Research questions and friction points this paper is trying to address.
whole-body PET/CT
functional and structural reasoning
3D medical vision-language models
multimodal imaging
MetaStructAtlas: A Grounded 3D Vision-Language Dataset and Benchmark for Functional and Structural Reasoning in Whole-Body PET/CT
🤖 AI Summary
为解决全身PET/CT综合分析不足的问题，本文通过构建包含490个3D PET和CT影像及对应标注的MetaStructAtlas数据集，并开发了用于视觉问答的MetaStructVQA基准。
📝 Abstract
The joint interpretation of metabolic function and anatomical structure is essential for clinical diagnosis in whole-body PET/CT. Although recent advances in 3D medical vision-language models have demonstrated remarkable progress, current efforts are limited to regional CT imaging, leaving a critical void in comprehensive whole-body PET/CT analysis. In this work, we introduce MetaStructAtlas, a large-scale dataset for grounded whole-body PET/CT interpretation that synthesizes multimodal imaging with integrated anatomical, metabolic, and semantic annotations. MetaStructAtlas provides 490 co-registered 3D PET and CT volumes with 50,470 organ-level segmentation masks and grounded radiology reports. To facilitate interactive reasoning, we further developed MetaStructVQA, a standardized 3D grounded visual question-answering benchmark containing 100,565 QA pairs. This framework explicitly links diagnostic queries to visual evidence across modalities, encompassing anatomical, morphological, and metabolic characteristics. Finally, we evaluate state-of-the-art 3D medical VLMs on MetaStructVQA, establishing a robust foundation for multimodal representation learning and integrated whole-body reasoning in nuclear medicine.
Innovation
Methods, ideas, or system contributions that make the work stand out.
MetaStructAtlas
Whole-Body PET/CT
Multimodal Imaging
Visual Question Answering
Integrated Reasoning
🔎 Similar Papers
