研究人员推出CORTEX，这是一个旨在提高多模态大型语言模型（MLLMs）在3D胸部CT分析中可信度的基准。现有的数据集通常将复杂的放射学报告简化为简单的问答对，忽略了临床医生使用的关键推理过程。CORTEX通过提供结构化的四阶段诊断追踪，模拟放射科医生的工作流程，从视觉观察到答案综合，从而解决了这一问题。该基准建立在CT-RATE数据集之上，并经过临床医生验证，包含超过76,000个推理追踪，以支持能够提供可追溯和可验证诊断的MLLMs的开发和评估。 AI
影响 该基准可能带来更可靠、更具可解释性的医学影像AI诊断工具。
排序理由 该集群描述了一个用于AI研究的新学术基准和数据集。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
Reasoning in multimodal large language models (MLLMs) has shown strong promise in medical imaging. However, this reasoning is usually free-form text judged only by its final answer, making it hard to interpret and verify, especially in 3D radiology, where a diagnosis should be tr…
arXiv:2606.27264v1 Announce Type: new Abstract: Reasoning in multimodal large language models (MLLMs) has shown strong promise in medical imaging. However, this reasoning is usually free-form text judged only by its final answer, making it hard to interpret and verify, especially…
Reasoning in multimodal large language models (MLLMs) has shown strong promise in medical imaging. However, this reasoning is usually free-form text judged only by its final answer, making it hard to interpret and verify, especially in 3D radiology, where a diagnosis should be tr…