向大规模多模态模型选择作为医疗图像中已烧毁保护健康信息检测引擎的方向
Towards Selection of Large Multimodal Models as Engines for Burned-in Protected Health Information Detection in Medical Images
AI总结：
本文研究了如何利用大规模多模态模型进行医疗图像中保护健康信息的检测，通过对比三种主流模型在不同流程配置下的表现，发现大规模多模态模型在OCR性能上优于传统方法，但整体检测准确性提升不显著，尤其在复杂印模模式测试中表现更优，并提出了针对特定操作约束的模型选择建议和部署策略。
摘要：
在医疗影像中检测保护健康信息（PHI）对于保障患者隐私和确保符合监管框架至关重要。传统检测方法主要利用光学字符识别（OCR）模型结合命名实体识别。然而，近年来大规模多模态模型（LMM）的进步为增强文本提取和语义分析提供了新机会。在本研究中，我们系统地评估了三种主要的闭源和开源LMM，即GPT-4o、Gemini 2.5 Flash和Qwen 2.5 7B，使用两种不同的流程配置：一种专注于文本分析，另一种整合OCR和语义分析。我们的结果显示，LMM在OCR性能（WER: 0.03-0.05，CER: 0.02-0.03）上优于传统模型如EasyOCR。然而，这种OCR性能的提升并不总是与整体PHI检测准确性提升相关联。在测试案例中具有复杂印模模式时，表现最强。在文本区域易于阅读且对比度足够的情况下，使用强LMM进行OCR后文本分析，不同流程配置的结果相似。此外，我们为特定操作约束提供了基于实证的LMM选择建议，并提出了一种利用可扩展和模块化基础设施的部署策略。
英文摘要：
The detection of Protected Health Information (PHI) in medical imaging is critical for safeguarding patient privacy and ensuring compliance with regulatory frameworks. Traditional detection methodologies predominantly utilize Optical Character Recognition (OCR) models in conjunction with named entity recognition. However, recent advancements in Large Multimodal Model (LMM) present new opportunities for enhanced text extraction and semantic analysis. In this study, we systematically benchmark three prominent closed and open-sourced LMMs, namely GPT-4o, Gemini 2.5 Flash, and Qwen 2.5 7B, utilizing two distinct pipeline configurations: one dedicated to text analysis alone and another integrating both OCR and semantic analysis. Our results indicate that LMM exhibits superior OCR efficacy (WER: 0.03-0.05, CER: 0.02-0.03) compared to conventional models like EasyOCR. However, this improvement in OCR performance does not consistently correlate with enhanced overall PHI detection accuracy. The strongest performance gains are observed on test cases with complex imprint patterns. In scenarios where text regions are well readable with sufficient contrast, and strong LMMs are employed for text analysis after OCR, different pipeline configurations yield similar results. Furthermore, we provide empirically grounded recommendations for LMM selection tailored to specific operational constraints and propose a deployment strategy that leverages scalable and modular infrastructure.
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。
