通用医学短语定位
Generalised Medical Phrase Grounding
AI总结：
针对现有医学短语定位方法无法处理多区域、非诊断性及不可定位短语的问题，提出通用医学短语定位任务及MedGrounder模型，采用两阶段训练策略，在零样本迁移和多区域/不可定位短语上优于基线方法。
摘要：
医学短语定位（MPG）将放射学发现的文本描述映射到相应的图像区域。这些定位报告更易于解释，尤其是对于非专家而言。现有的MPG系统大多遵循指代表达理解（REC）范式，每个短语返回恰好一个边界框。实际报告往往违反这一假设，包含多区域发现、非诊断性文本以及不可定位短语（如否定或正常解剖描述）。受此启发，我们将任务重新定义为通用医学短语定位（GMPG），其中每个句子映射到零个、一个或多个带评分的区域。为实现这一公式，我们引入了第一个GMPG模型：MedGrounder。我们采用两阶段训练方案：在报告句子-解剖框对齐数据集上预训练，然后在报告句子-人工标注框数据集上微调。在PadChest-GR和MS-CXR上的实验表明，MedGrounder实现了强大的零样本迁移，在多区域和不可定位短语上优于REC风格和定位报告生成基线，同时使用更少的人工框标注。最后，我们展示了MedGrounder可以与现有报告生成器组合，无需重新训练生成器即可生成定位报告。
英文摘要：
Medical phrase grounding (MPG) maps textual descriptions of radiological findings to corresponding image regions. These grounded reports are easier to interpret, especially for non-experts. Existing MPG systems mostly follow the referring expression comprehension (REC) paradigm and return exactly one bounding box per phrase. Real reports often violate this assumption. They contain multi-region findings, non-diagnostic text, and non-groundable phrases, such as negations or descriptions of normal anatomy. Motivated by this, we reformulate the task as generalised medical phrase grounding (GMPG), where each sentence is mapped to zero, one, or multiple scored regions. To realise this formulation, we introduce the first GMPG model: MedGrounder. We adopted a two-stage training regime: pre-training on report sentence--anatomy box alignment datasets and fine-tuning on report sentence--human annotated box datasets. Experiments on PadChest-GR and MS-CXR show that MedGrounder achieves strong zero-shot transfer and outperforms REC-style and grounded report generation baselines on multi-region and non-groundable phrases, while using far fewer human box annotations. Finally, we show that MedGrounder can be composed with existing report generators to produce grounded reports without retraining the generator.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
