RAPTOR+: 一种基于视觉的视觉-语言框架，用于提高自动化癌症转诊处理中的临床信任度和可审计性
RAPTOR+: A Visually Grounded Vision-Language Framework to Improve Clinical Trust and Auditability in Automated Cancer Referral Processing
AI总结：
提出RAPTOR+多模态框架，通过微调视觉-语言模型实现端到端转诊理解，在结直肠癌转诊表单上显著提升提取准确性和证据定位能力。
摘要：
紧急疑似结直肠癌（CRC）转诊会因半结构化临床文档通常需要人工审查和转录而造成操作瓶颈。原始的RAPTOR系统使用大型语言模型进行结构化提取，但依赖单独的OCR阶段，使其易受手写、布局变化和视觉证据链接丢失的影响。我们提出RAPTOR+，一种多模态扩展，使用视觉-语言模型（VLM）进行端到端转诊理解。我们在223份临床整理的CRC紧急转诊表单上评估了微调VLM、商业和开源零样本VLM以及基于OCR的原始流水线。我们还引入了一种基于定位的评估框架，同时衡量提取准确性和证据定位。结果显示零样本模型存在明显的定位差距。Gemini 2.5 Flash实现了92.6%的读取准确率，但严格安全性仅为1.2%。相比之下，微调的Qwen3-VL-8B实现了96.1%的读取准确率和60.6%的严格安全性，显著改善了可验证的证据定位。这些发现表明，任务特定的微调对于可靠、可审计的临床文档理解至关重要。RAPTOR+使得提取的转诊决策能够与视觉证据关联，支持更安全、更高效的癌症转诊分诊。
英文摘要：
Urgent suspected colorectal cancer (CRC) referrals create operational bottlenecks because semi-structured clinical documents often require manual review and transcription. The original RAPTOR system used Large Language Models for structured extraction but relied on a separate OCR stage, making it vulnerable to handwriting, layout variation, and loss of visual evidence linkage. We present RAPTOR+, a multimodal extension that uses Vision-Language Models (VLMs) for end-to-end referral understanding. We evaluate fine-tuned VLMs, commercial and open-source zero-shot VLMs, and the original OCR-based pipeline on 223 clinically curated CRC urgent referral forms. We also introduce a grounding-aware evaluation framework that measures both extraction accuracy and evidence localisation. Results show a clear grounding gap in zero-shot models. Gemini 2.5 Flash achieved 92.6% Reading Accuracy but only 1.2% Strict Safety. In contrast, fine-tuned Qwen3-VL-8B achieved 96.1% Reading Accuracy and 60.6% Strict Safety, substantially improving verifiable evidence grounding. These findings show that task-specific fine-tuning is essential for reliable, auditable clinical document understanding. RAPTOR+ enables extracted referral decisions to be linked to visual evidence, supporting safer and more efficient cancer referral triage.
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。
