NA-MIC Project Weeks

Back to Projects List

Local AI-Copilot for Slicer medical imaging workflows

Key Investigators

• Paul Dumont (University of North Carolina at Chapel Hill, USA)
• Alexandre Buisson (University of North Carolina at Chapel Hill, USA)
• Juan Carlos Prieto (University of North Carolina at Chapel Hill, USA)
• Lucia Cevidanes (University of North Carolina at Chapel Hill, USA)
• Steve Pieper (Isomics, USA)

Project Description

This project will attempt to build a free, confidential, and fully local alternative to cloud-based LLMs for medical imaging workflows. To bypass expensive and non-private cloud models, we will attempt to create an AI Agent for 3D Slicer designed to run entirely offline. We aim to enable private models powered by Ollama to accurately query the Slicer API without relying on external cloud infrastructure.

Objective

1. Build a private MCP pipeline linking Ollama to 3D Slicer for secure, context-aware API scripting.
2. Benchmark local model performance (Llama-3, DeepSeek) against cloud baselines for accuracy and cost.

Approach and Plan

Connect a local LLM client to existing Slicer MCP execution servers to enable code execution. Evaluate zero-shot coding accuracy on multi-step Slicer workflows using purely local inference

Progress and Next Steps

Progress: Reviewed current cloud-reliant MCP integrations (slicer-skill, mcp-slicer) and local LLM baselines (SlicerChat).

Illustrations

No response

Background and References

• slicerClaw: https://github.com/jumbojing/slicerClaw
• mcp-slicer: https://github.com/zhaoyouj/mcp-slicer
• slicer-skill: https://github.com/pieper/slicer-skill
• SlicerChat: https://arxiv.org/abs/2407.11987