CCD
Verified Safeby X-iZhang
Overview
Mitigating hallucinations in radiology MLLMs by integrating structured clinical signals for chest X-ray report generation and analysis.
Installation
python -m ccd.appSecurity Notes
The project relies on direct installations from GitHub repositories (CCD and Libra), which can pose a supply chain risk if those repositories are compromised. It also downloads pre-trained models from Hugging Face, requiring trust in those external assets. No direct 'eval' or critical hardcoded secrets are visible in the provided code. The MedSigLip expert model might require external authorization/tokens, but the code doesn't explicitly manage them for the basic demo.
Similar Servers
mcp
Provides AI assistants with direct, real-time access to official Microsoft Learn documentation to prevent hallucinations and retrieve accurate technical information.
docs-mcp-server
The Documentation MCP Server indexes documentation from various sources (web, local files, registries) and makes it semantically searchable via vector embeddings, primarily for AI coding assistants.
hm_editor
Electronic Medical Record (EMR) Editor backend with AI integration for structured data management, document generation, and chart visualization.
vectara-mcp
Vectara MCP Server enables AI systems to interact seamlessly with Vectara's RAG platform for reduced hallucination, functioning as an open standard Model Context Protocol server.