English

VLM-in-the-Loop: A Plug-In Quality Assurance Module for ECG Digitization Pipelines

Computer Vision and Pattern Recognition 2026-04-02 v1

Abstract

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\DeltaPCC 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.

Keywords

Cite

@article{arxiv.2604.00396,
  title  = {VLM-in-the-Loop: A Plug-In Quality Assurance Module for ECG Digitization Pipelines},
  author = {Jiachen Li and Shihao Li and Soovadeep Bakshi and Wei Li and Dongmei Chen},
  journal= {arXiv preprint arXiv:2604.00396},
  year   = {2026}
}
R2 v1 2026-07-01T11:47:28.921Z