Aschoplex - precise choroid plexus segmentation in brain MRIs
2 min read
A tool for automated extraction and quantitative analysis of the choroid plexus (ChP) on 3D T1-weighted brain MRI scans. The model is built on an ensemble of five AI models (three DynUNet and two UNETR) using the MONAI framework. The solution was trained on data from the COMPASS-ND cohort for neurodegenerative disease research (including Alzheimer's and Parkinson's diseases). It helps researchers quickly obtain segmentation masks and evaluate choroid plexus volume in millimeters.
Key features
- Model ensemble: a combination of DynUNet and UNETR architectures for more accurate prediction.
- Volume estimation: calculation of choroid plexus volume in cubic millimeters and milliliters.
- MONAI ecosystem: full integration with the PyTorch-based medical deep learning ecosystem.
- Local execution: inference scripts for running on hardware with CUDA support.
What you can do
- MRI analysis: run automated segmentation of 3D T1-weighted scans in NIfTI format.
- Research: use for large-scale phenotyping of structural MRIs in Alzheimer's or Parkinson's disease.
- Integration: set up a medical image processing pipeline in a research laboratory.
Example
Running the full model ensemble for inference:
python run_inference.py \
--input /data/subject001.nii.gz \
--output ./predictionsRead more
DetailsRequirements: Linux, GPU with CUDA (for example, RTX A6000), Python 3.9, PyTorch 1.13.1, MONAI 1.0.1.
Input data: 3D T1-weighted MRIs in NIfTI format.
Limitations: for research purposes only, CPU inference is not supported.
License: Apache-2.0.










Comments