RepoMicrosoftMicrosoftpublished Oct 7, 2026seen 1w

microsoft/healthcare-models-and-agents-workshop

Python

Open original ↗

Captured source

source ↗
GH
GitHub/github.com/microsoft/healthcare-models-and-agents-workshop
microsoft/healthcare-models-and-agents-workshop repository metadata
Source ↗
published Oct 7, 2026seen 1wcaptured 1whttp 200method plain

microsoft/healthcare-models-and-agents-workshop

Description: Build Healthcare Agents with Foundation and Reasoning Models

Language: Python

License: MIT

Stars: 0

Forks: 0

Open issues: 0

Created: 2026-10-07T06:25:54Z

Pushed: 2026-10-17T01:05:20Z

Default branch: main

Fork: no

Archived: no

README:

Build Healthcare Agents with Foundation and Reasoning Models

Hands-on workshop. This repository supports a hands-on workshop on building radiology AI agents in VS Code with GitHub Copilot, grounded in MedImageParse — a foundation model that segments medical images from simple text prompts. The lab follows one brain MRI case from a bare LLM to a measured, context-aware report, and is organized into three chapters, each in its own folder under [chapters/](chapters/).

Budget about 30 min setup (do this before arriving) + 60 min content across the three chapters.

What you'll build

1. Chapter 1 — Simple agent + skill ([chapters/chapter1-simple-agent/](chapters/chapter1-simple-agent/)): use a general-purpose LLM with a prompt-based skill to draft structured brain MRI reports — and see where it falls short. 2. Chapter 2 — Using foundation models with agents ([chapters/chapter2-foundation-models/](chapters/chapter2-foundation-models/)): wrap MedImageParse lesion segmentation, plus a measurement tool that turns masks into millimeters, in an MCP server the agent can call. 3. Chapter 3 — Patient context ([chapters/chapter3-knowledge-sources/](chapters/chapter3-knowledge-sources/)): ground agent outputs in a (synthetic) patient history and a prior report, so the agent reports interval change.

Workshop layout

  • [chapters/](chapters/) — one folder per chapter. Each has a README.md, a starter/ skeleton, and an answer-key/ reference.
  • [samples/](samples/) — de-identified post-contrast brain MRI volumes (NIfTI) you can hand to the agent. See [samples/README.md](samples/README.md).
  • [docs/](docs/) — troubleshooting, Codespaces, and no-admin setup guides.

> The data and patient records in this repo are synthetic or de-identified and are not for clinical use. The patient charts in Chapter 3 are synthetic. MedImageParse is provided for research and model development exploration; it is not designed or intended to be deployed in clinical settings as-is.

Prerequisites

Install and verify the following before the workshop. Expect about 30 minutes of setup. Do this before arriving — Wi-Fi and time will be tight on the day.

  • VS Code (latest stable): https://code.visualstudio.com/
  • GitHub Copilot and GitHub Copilot Chat extensions, signed in with an account that has Copilot access.
  • Git with Git LFS (https://git-lfs.com/), and a local clone of this repository opened as your VS Code workspace. The sample scans are stored with Git LFS: run git lfs install once before cloning, or git lfs pull in a clone that has small text files in place of the .nii.gz scans.
  • uv (https://docs.astral.sh/uv/) — Python package manager. Install user-scope (no admin required):
  • macOS / Linux: curl -LsSf https://astral.sh/uv/install.sh | sh
  • Windows (PowerShell): powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

Then run uv sync from the repo root.

Can't install locally? See [docs/no-admin.md](docs/no-admin.md) or run the whole lab in a [GitHub Codespace](docs/codespaces.md).

MedImageParse credentials

Chapter 2 calls a shared MedImageParse endpoint. Credentials (MIP_MODEL_ENDPOINT and MIP_MODEL_API_KEY) are distributed at the start of the session. Copy .env.example to .env at the repository root and fill them in; the quick check below and the Chapter 2 MCP server both read that file.

Quick check

The workshop/ directory at repo root holds shared Python utilities for the workshop, including a small script to verify your env is healthy.

uv --version # 0.x.x
uv sync # one-time, ~1–2 min on a good connection
uv run workshop/check_env.py # expected: "Workshop env OK — Python 3.11; endpoint OK (mip3d-mri-brain-lesion)"

If any command above fails, resolve it before arriving.