Scan-do Attitude: Towards Autonomous CT Protocol Management using a Large Language Model Agent

2025-09-24

AI Summary

CT scanning protocol configuration—encompassing acquisition/reconstruction parameters and post-processing selections—is highly dependent on expert radiologic technologist experience, time-consuming, and increasingly challenged by workforce shortages. Method: We propose the first large language model (LLM)-based agent framework for CT protocol management, integrating in-context learning, instruction following, and structured tool-calling mechanisms. It accepts either natural-language queries or structured inputs to autonomously generate device-compatible, patient-specific protocol definition files. Contribution/Results: The agent accurately retrieves protocol components, generates regulatory-compliant configurations, and faithfully executes user requests. Experimental evaluation across diverse clinical scenarios demonstrates its technical feasibility and translational potential. It significantly enhances radiology workflow efficiency and reduces reliance on manual expertise, thereby addressing critical operational bottlenecks in modern imaging departments.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Agent Communication
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work

Abstract

Managing scan protocols in Computed Tomography (CT), which includes adjusting acquisition parameters or configuring reconstructions, as well as selecting postprocessing tools in a patient-specific manner, is time-consuming and requires clinical as well as technical expertise. At the same time, we observe an increasing shortage of skilled workforce in radiology. To address this issue, a Large Language Model (LLM)-based agent framework is proposed to assist with the interpretation and execution of protocol configuration requests given in natural language or a structured, device-independent format, aiming to improve the workflow efficiency and reduce technologists' workload. The agent combines in-context-learning, instruction-following, and structured toolcalling abilities to identify relevant protocol elements and apply accurate modifications. In a systematic evaluation, experimental results indicate that the agent can effectively retrieve protocol components, generate device compatible protocol definition files, and faithfully implement user requests. Despite demonstrating feasibility in principle, the approach faces limitations regarding syntactic and semantic validity due to lack of a unified device API, and challenges with ambiguous or complex requests. In summary, the findings show a clear path towards LLM-based agents for supporting scan protocol management in CT imaging.

Problem

• Automating CT scan protocol management to reduce manual workload
• Addressing skilled workforce shortage in radiology through AI assistance
• Translating natural language requests into device-compatible protocol configurations

Innovation

• LLM-based agent framework for protocol management
• Combines in-context-learning and structured toolcalling
• Generates device-compatible protocol definition files