This package contains tools for training a simple 2D convolutional neural network deep learning model to identify and subclassify acute intracranial hemorrhage at noncontrast CT. Training data come from the RSNA Intracranial Hemorrhage Detection dataset on Kaggle.
-
Make sure a version of
mxnet
is installed with GPU support. For example:pip install mxnet-cu92mkl
-
Download this repository, either with
git clone <URL>
(where<URL>
is the git repository URL) or by clicking the download link in the git web interface. -
Install the companion python module. From the command line:
cd /path/to/unet_brats/ pip install .
Alternatively, install directly from the git repository like:
pip install git+https://github.com/johncolby/rsna_heme
Example Jupyter notebooks for training and testing/inference are included in the notebooks directory.