小模型赋能医学影像视图标签，兼顾隐私与可操作性。
Governance-Ready Small Language Models for Medical Imaging: Prompting, Abstention, and PACS Integration
- 用提示工程+校准拒答+PACS对接实现可治理部署
- 在NIH数据集上4个轻量模型均实现高精度视图识别
- 提供可审计的流程框架，适合临床试点落地
小型语言模型（SLMs）在医疗影像领域中因隐私、延迟和成本优势，成为特定工作流任务的理想选择。本文提出一套面向治理的部署方案，结合提示模板、校准后的拒答机制以及符合标准的PACS集成方式，聚焦于胸部X光片的前后位/正位视图自动标注。基于四款可部署的SLM（Qwen2.5-VL、MiniCPM-V、Gemma 7B、LLaVA 7B），在NIH Chest X-ray数据集上验证了该方法的有效性：反思型提示对轻量模型更有效，而强基线模型则不敏感。除准确率外，还量化了拒答策略、期望校准误差和人工监督负担，并将输出映射至DICOM标签、HL7 v2消息及FHIR ImagingStudy资源。贡献包括以提示为先的部署框架、校准、日志与变更管理的操作手册，以及从试点到读者研究的清晰路径，避免过度宣称临床验证。同时定义了人因角色分工（RACI）、针对数据分布偏移的分层校准策略，以及支持本地治理审查的可审计证据包。
原文摘要 · Abstract (English)
Small Language Models (SLMs) are a practical option for narrow, workflow-relevant medical imaging utilities where privacy, latency, and cost dominate. We present a governance-ready recipe that combines prompt scaffolds, calibrated abstention, and standards-compliant integration into Picture Archiving and Communication Systems (PACS). Our focus is the assistive task of AP/PA view tagging for chest radiographs. Using four deployable SLMs (Qwen2.5-VL, MiniCPM-V, Gemma 7B, LLaVA 7B) on NIH Chest X-ray, we provide illustrative evidence: reflection-oriented prompts benefit lighter models, whereas stronger baselines are less sensitive. Beyond accuracy, we operationalize abstention, expected calibration error, and oversight burden, and we map outputs to DICOM tags, HL7 v2 messages, and FHIR ImagingStudy. The contribution is a prompt-first deployment framework, an operations playbook for calibration, logging, and change management, and a clear pathway from pilot utilities to reader studies without over-claiming clinical validation. We additionally specify a human-factors RACI, stratified calibration for dataset shift, and an auditable evidence pack to support local governance reviews.
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。