search

MHubAI / models

Stores the MHub models dockerfiles and scripts.
MIT License
8 stars 16 forks source link

BAMF FDG-Avid Breast Tumor #87

Open jithenece opened 4 months ago

jithenece commented 4 months ago

AIMI1 - Pretrained model for 3D semantic image segmentation of the FDG-avid lesions from PT/CT scans

jithenece commented 4 months ago 
sample:
  idc_version: Version 2: Updated 2020/01/10
  data:
  - SeriesInstanceUID: 1.3.6.1.4.1.14519.5.2.1.8162.7003.200887946066796652452097013479
    aws_url: s3://idc-open-data/7a375cfa-8708-46f0-b056-248dbaca851e/*
    path: case1/ct
  - SeriesInstanceUID: 1.3.6.1.4.1.14519.5.2.1.8162.7003.182230913012492714502249429083
    aws_url: s3://idc-open-data/739449f3-286c-4511-86a9-39172a50dc95/*
    path: case1/pt

reference:
  url: https://drive.google.com/file/d/1afkRFJqwgii1tUSMiQV_dPlDsUBl6_0g/view?usp=sharing
jithenece commented 4 months ago

Archive.zip Slicer screenshots added

jithenece commented 3 months ago

/test

sample:
  idc_version: "Data Release 2.0 January 10, 2020"
  data:
  - SeriesInstanceUID: 1.3.6.1.4.1.14519.5.2.1.8162.7003.200887946066796652452097013479
    aws_url: s3://idc-open-data/7a375cfa-8708-46f0-b056-248dbaca851e/*
    path: 'case_study1/ct'
  - SeriesInstanceUID: 1.3.6.1.4.1.14519.5.2.1.8162.7003.182230913012492714502249429083
    aws_url: s3://idc-open-data/739449f3-286c-4511-86a9-39172a50dc95/*
    path: 'case_study1/pt'

reference:
  url: https://drive.google.com/file/d/1yivXqTBMXslsmj3uD8gE9LojLCKh-BqV/view?usp=sharing
LennyN95 commented 2 months ago

@jithenece I wanted to run our test routine on all read for testing PR's, however, I noticed, the sample reference url you provided won't work with wget -O /tmp/ref.zip $RESSOURCE_URL. This might be specific to using a google drive link, however, I generally advice you to instead to attach your data to the PR directly (e.g., by uploading them to the comment) and to use the permanent link as a reference.

Please note, this needs to be updated on all effected PRs until testing can proceed.

jithenece commented 2 months ago

/test

Not many collection available for breast-pet-ct.

attaching segmentation output.zip

sample: 
  idc_version: 17.0
  data:
  - SeriesInstanceUID: 1.3.6.1.4.1.14519.5.2.1.8162.7003.539267076861125410814830191835
    aws_url: s3://idc-open-data/84c9b972-76e1-4fa3-a7ea-19b6500e497a/*
    path: case_study1/ct
  - SeriesInstanceUID: 1.3.6.1.4.1.14519.5.2.1.8162.7003.196821690630879561473146713439
    aws_url: s3://idc-open-data/33f0bd14-4bf5-469c-83db-183e1ab96f02/*
    path: case_study1/pt

reference:
  url: https://github.com/user-attachments/files/16927110/output.zip
LennyN95 commented 2 months ago

Please note, we updated our base image. All mhub dependencies are now installed in a virtual environment under /app/.venv running Python 3.11. Python, virtual environment and dependencies are now managed with uv. If required, you can create custom virtual environments, e.g., uv venv -p 3.8 .venv38 and use uv pip install -p .venv38 packge-name to install dependencies and uv run -p .venv3.8 python script.py to run a python script.

We also simplified our test routine. Sample and reference data now have to be uploaded to Zenodo and provided in a mhub.tom file at the project root. The process how to create and provide these sample data is explained in the updated testing phase article of our documentation. Under doi.org/10.5281/zenodo.13785615 we provide sample data as a reference.