lablab-ai-amd-developer-hackathon / MediAgent

huggingface.co
Total runs: 0
24-hour runs: 0
7-day runs: 0
30-day runs: 0
Model's Last Updated: May 04 2026
image-to-text

Introduction of MediAgent

Model Details of MediAgent

🏥 MediAgent

Autonomous Multi-Agent Medical Imaging Analysis — AMD Instinct MI300X

AMD Developer Hackathon 2026 · Vision & Multimodal AI Track Built by Ramyar — Sulaymaniyah, Iraq


What It Does

MediAgent runs a 5-agent AI pipeline that analyzes medical images (X-ray, MRI, CT, DICOM) and generates formal radiology reports with differential diagnoses, ICD-10 codes, and FHIR R4 export — entirely on AMD hardware.

No cloud APIs. No OpenAI. No Nvidia. Pure AMD MI300X + ROCm + vLLM.


⚠️ Demo Mode

This Space runs in demo mode — the full pipeline UI works and all 5 agents animate live, but no real inference is performed since the AMD Instinct MI300X backend is not available on HuggingFace's free hardware.

See the video demo for live inference on real AMD hardware.

Live inference requires: AMD Instinct MI300X · ROCm · vLLM · Qwen multimodal

https://youtu.be/MAd9t_Q7fq0


The 5-Agent Pipeline
Agent Role
INTAKE Validates input, normalizes clinical language, safety triage
VISION Multimodal image analysis via Qwen on AMD MI300X
RESEARCH KB cross-reference, differential diagnoses, ICD-10 codes
REPORT ACR/NICE format radiology report synthesis
CRITIC QA peer-review, quality scoring, disclaimer enforcement

INTAKE + VISION run in parallel to minimize latency.


Key Features
  • Real-time SSE streaming pipeline with per-agent timers
  • DICOM (.dcm) file support with metadata extraction
  • 15-condition medical knowledge base with ICD-10 mapping
  • FHIR R4 DiagnosticReport export
  • Client-side PDF export
  • Post-report clinical Q&A (ClinicalAdvisorAgent)
  • Live AMD GPU metrics (util, VRAM, temp, power)
  • Hard-enforced clinical safety rules

Tech Stack
  • GPU: AMD Instinct MI300X
  • GPU Software: ROCm
  • Inference: vLLM (ROCm build) + Qwen multimodal
  • Backend: FastAPI + Uvicorn
  • Frontend: Vanilla JS + Tailwind CSS + Chart.js + SSE

GitHub

Full source code, architecture docs, and README: https://github.com/Ramyar2007/mediagent


This system is a decision support tool. All outputs must be reviewed by a licensed radiologist before any clinical decisions are made.

Runs of lablab-ai-amd-developer-hackathon MediAgent on huggingface.co

0
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
0
30-day runs

More Information About MediAgent huggingface.co Model

More MediAgent license Visit here:

https://choosealicense.com/licenses/mit

MediAgent huggingface.co

MediAgent huggingface.co is an AI model on huggingface.co that provides MediAgent's model effect (), which can be used instantly with this lablab-ai-amd-developer-hackathon MediAgent model. huggingface.co supports a free trial of the MediAgent model, and also provides paid use of the MediAgent. Support call MediAgent model through api, including Node.js, Python, http.

lablab-ai-amd-developer-hackathon MediAgent online free

MediAgent huggingface.co is an online trial and call api platform, which integrates MediAgent's modeling effects, including api services, and provides a free online trial of MediAgent, you can try MediAgent online for free by clicking the link below.

lablab-ai-amd-developer-hackathon MediAgent online free url in huggingface.co:

https://huggingface.co/lablab-ai-amd-developer-hackathon/MediAgent

MediAgent install

MediAgent is an open source model from GitHub that offers a free installation service, and any user can find MediAgent on GitHub to install. At the same time, huggingface.co provides the effect of MediAgent install, users can directly use MediAgent installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

Url of MediAgent

Provider of MediAgent huggingface.co

lablab-ai-amd-developer-hackathon
ORGANIZATIONS

Other API from lablab-ai-amd-developer-hackathon