用视觉语言模型闭环检测心电图数字化质量，显著提升真实图像处理效果。
VLM-in-the-Loop: A Plug-In Quality Assurance Module for ECG Digitization Pipelines
- 通过信号分析工具锚定视觉判断，实现可量化的质量评估
- 在200份数据上使判断一致性提升至89%，信噪比区分度翻倍
- 适配多种数字化工具，适合临床真实场景的自动化质检
心电图数字化可激活数十亿存档病历，但现有方法在真实图像上表现不佳。我们提出「VLM-in-the-Loop」，一个无需修改底层模块的插件式质量保障组件，通过标准化接口实现视觉语言模型的闭环反馈。核心是「工具锚定」机制：将VLM评估建立在领域专用信号分析工具提供的量化证据基础上。在200条带真值记录的对照实验中，该机制使判断一致性从71%提升至89%，信噪比分离度提升一倍（ΔPCC 0.03 → 0.08），且在三个VLM（Claude Opus 4、GPT-4o、Gemini 2.5 Pro）上均复现此效果，表明为模式级提升而非模型特异性。部署于四个后端系统中，全部表现改善：29.4%的临界导联得到修复；ECG-Digitiser中41.2%的失败肢体导联被恢复；Open-ECG-Digitizer每图有效导联数从2.5增至5.8。在428张真实临床肥厚型心肌病图像上，集成系统达到98.0%优秀质量。该插件架构与工具锚定机制具领域参数化特性，适用于所有质量标准可客观衡量的场景。
原文摘要 · Abstract (English)
ECG digitization could unlock billions of archived clinical records, yet existing methods collapse on real-world images despite strong benchmark numbers. We introduce \textbf{VLM-in-the-Loop}, a plug-in quality assurance module that wraps any digitization backend with closed-loop VLM feedback via a standardized interface, requiring no modification to the underlying digitizer. The core mechanism is \textbf{tool grounding}: anchoring VLM assessment in quantitative evidence from domain-specific signal analysis tools. In a controlled ablation on 200 records with paired ground truth, tool grounding raises verdict consistency from 71\% to 89\% and doubles fidelity separation ($Δ$PCC 0.03 $\rightarrow$ 0.08), with the effect replicating across three VLMs (Claude Opus~4, GPT-4o, Gemini~2.5 Pro), confirming a pattern-level rather than model-specific gain. Deployed across four backends, the module improves every one: 29.4\% of borderline leads improved on our pipeline; 41.2\% of failed limb leads recovered on ECG-Digitiser; valid leads per image doubled on Open-ECG-Digitizer (2.5 $\rightarrow$ 5.8). On 428 real clinical HCM images, the integrated system reaches 98.0\% Excellent quality. Both the plug-in architecture and tool-grounding mechanism are domain-parametric, suggesting broader applicability wherever quality criteria are objectively measurable.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。