MCP-MedImg: Enabling Standardized PACS-AI Integration through the Model Context Protocol

License DOI

Reference implementation for the paper:
"MCP-MedImg: Enabling Standardized PACS-AI Integration through the Model Context Protocol"
Author: Xiong Shi (ORCID: 0009-0006-2745-491X)

Architecture

MCP-MedImg extends the Model Context Protocol (MCP) with a four-layer protocol stack specifically designed for medical imaging workflows:

L1 Transport: DICOMweb / DICOM C-MOVE / dicom-mcp compatibility wrapper
L2 Security & Compliance: Hierarchical PHI de-identification + 14-column cryptographic audit trail
L3 AI Orchestration: Model registry, inspection-type routing, version management, result formatting
L4 Application Semantics: Lesion encoding (RADS/BI-RADS), conditional verification state machine

Quick Start

Prerequisites

Ubuntu 22.04 (recommended) / macOS / Windows WSL2
Python 3.10+
Docker & Docker Compose
NVIDIA GPU with CUDA 12.1+ (optional; Mock engine available for CPU-only environments)

1. Clone & Install

git clone https://github.com/Xiong-Shi/MCP-MedImg.git
cd MCP-MedImg
pip install -r requirements.txt

2. Start Orthanc PACS

docker-compose -f config/orthanc/docker-compose.yml up -d

3. Run Unit Tests (Protocol Validation)

pytest tests/ -v --tb=short
# Expected: 132 passing, 3 skipped across 10 validation scenarios

4. Run Benchmarks

bash scripts/reproduce_lidc_benchmark.sh      # Table 18: LIDC-IDRI inference latency (n=200)
bash scripts/reproduce_heart_benchmark.sh     # Table 19, 22: MSD Heart 5-fold validation
bash scripts/reproduce_protocol_overhead.sh   # Table 20, 21: Protocol overhead decomposition (n=98)

Datasets & Model Weights

Due to file size limits, pretrained model weights and full preprocessed datasets are available via separate download:

Asset	Size	Description
nnU-Net 5-fold ensemble (MSD Heart)	~1.2 GB	Trained weights, mean Dice 0.9324±0.0062
LIDC-IDRI preprocessed (n=200)	~8 GB	HU-normalized, resampled CT volumes (inference uses randomly initialized model, not trained weights)
MSD Heart preprocessed (n=20)	~1 GB	nnU-Net v2 auto-preprocessed
Benchmark logs	~50 MB	Table 18-21 original timing logs

Download instructions:

bash scripts/download_pretrained_weights.sh

Key Experimental Results

Metric	Value	Details
MSD Heart 5-fold Dice	0.9324 ± 0.0062	nnU-Net v2, 1000 epochs per fold
LIDC Inference (n=200)	5.40s mean end-to-end	RTX 4090D, 22.58M params
Protocol Overhead	567.47ms (99.8% L1 Transport)	n=98, 3.41% measurement error
Unit Tests	132 passing, 3 skipped	10 validation scenarios

Analysis Figures: Detailed analysis charts (LIDC bimodal distribution, PROTO error robustness) are available in the Zenodo dataset: DOI

This implementation addresses the MCP-38 threat taxonomy for medical imaging:

Hierarchical PHI de-identification (Patient / Department / System level)
Cryptographic audit trails with SHA-256 hashing
Containerized sandbox execution
Input sanitization against indirect prompt injection

Reproducibility

All experimental results from the paper can be reproduced via the scripts in scripts/.

Paper Table/Figure	Reproduce Script	Expected Runtime
Table 16 (134 tests)	`pytest tests/`	~5 min (CPU)
Table 18 (LIDC, n=200)	`scripts/reproduce_lidc_benchmark.sh`	~20 min (RTX 4090D)
Table 19 (Heart, n=20)	`scripts/reproduce_heart_benchmark.sh`	~12 min (RTX 4090D)
Table 20-21 (Overhead)	`scripts/reproduce_protocol_overhead.sh`	~15 min (RTX 4090D)
Table 22 (Dice)	Included in Heart script	--

Citation

If you use this code, please cite:

@article{mcp_medimg_2026,
  title={MCP-MedImg: Enabling Standardized PACS-AI Integration through the Model Context Protocol},
  author={[Author Names]},
  journal={[Journal Name]},
  year={2026}
}

License

This project is licensed under the Apache License 2.0 - see LICENSE file.

Disclaimer

This is a research prototype for protocol validation and reproducibility. Not for clinical use without appropriate regulatory approval (FDA/NMPA/CE).