Skip to main content

User-Friendly AI Software for Automated Quantitative CMR Reporting on Low-Cost, Energy-Efficient Devices

Project description

myopari

myopari is a napari plugin for cardiac MRI segmentation and report generation. It provides an interactive widget to:

  • select a 2D or 3D image layer,
  • run ONNX-based segmentation,
  • compute basic volumetric metrics,
  • optionally enrich the report with an LLM rewrite,
  • save a markdown report.

Main Features

  • Napari dock widget for interactive segmentation
  • Built-in segmentation models:
    • TIRAMISU_ACDC
    • TIRAMISU_EMIDEC
  • Works with both 2D images and 3D volumes
  • Optional myocardium-only segmentation mode
  • Markdown report generation with:
    • per-class volumes (mL)
    • myocardium mass estimate (g)
    • optional external patient info files (.cfg, .txt, .md)
  • Optional LLM-based report rewriting (via llama-cpp-python)

Installation with pip

pip install myopari

Quick Start in napari

  1. Launch napari.
  2. Load a cardiac image (2D or 3D).
  3. Open the widget:
    • Plugins -> myopari -> myopari
  4. In the widget:
    • Click Select image layer
    • Choose Edge device
    • Choose Segmentation model
    • (Optional) Enable Myocardium only
    • Click Segment
  5. A labels layer is added with a name like:
    • segmentation_<input_layer_name>_<count>

Report Workflow

After segmentation:

  1. (Optional) Click Choose patient info files and pick .cfg, .txt, or .md files.
  2. (Optional) Enable Use LLM for report.
  3. Click Create report.
  4. Click Save report to .md to export.

Notes:

  • The report includes per-label volumes in mL and myocardium mass estimate.
  • If a logo asset exists in Resources, it is embedded in the report and copied next to the saved markdown file.

Troubleshooting

  • Segmentation runtime/provider issues:
    • Check installed ONNX Runtime package (onnxruntime vs onnxruntime-gpu)
    • Ensure CUDA and driver versions match your onnxruntime-gpu build
  • LLM report generation fails:
    • Install llama-cpp-python
    • Ensure internet access for first model download
    • Disable Use LLM for report to keep standard report generation

License

MIT. See LICENSE.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

myopari-0.1.2.tar.gz (18.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

myopari-0.1.2-py3-none-any.whl (18.9 kB view details)

Uploaded Python 3

File details

Details for the file myopari-0.1.2.tar.gz.

File metadata

  • Download URL: myopari-0.1.2.tar.gz
  • Upload date:
  • Size: 18.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.10.13

File hashes

Hashes for myopari-0.1.2.tar.gz
Algorithm Hash digest
SHA256 f589e081022223dc05b0d5024fca2ad12b251a1a355a5d5b8d0f551625a2556b
MD5 a0281d6dc8023c379e0b299594dd1c29
BLAKE2b-256 73e5ca7c8d2e98a1932e7060de03583b26996026b0dd29a8afa2b35d3914e365

See more details on using hashes here.

File details

Details for the file myopari-0.1.2-py3-none-any.whl.

File metadata

  • Download URL: myopari-0.1.2-py3-none-any.whl
  • Upload date:
  • Size: 18.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.10.13

File hashes

Hashes for myopari-0.1.2-py3-none-any.whl
Algorithm Hash digest
SHA256 25ee8f120d4a3c0b0788eacaa9059af2fd97ad1c101253930fa989bd671c536d
MD5 7a6564d16c78a60a1be329fa0a497fdd
BLAKE2b-256 48222490316d85e6686244ebe6299a5204f5d877f6d690648acd0a164f7b905b

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page