Governance-Ready Small Language Models for Medical Imaging: Prompting, Abstention, and PACS Integration
This provides a practical, incremental framework for deploying SLMs in medical imaging workflows to address privacy, latency, and cost concerns, without over-claiming clinical validation.
The paper tackled the problem of deploying small language models (SLMs) for medical imaging tasks like AP/PA view tagging in chest radiographs, by developing a governance-ready framework that integrates prompting, abstention, and PACS standards, with illustrative evidence showing that reflection-oriented prompts benefit lighter models.
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.