Pretrained nnU-Net Model from the cMRI M&Ms Challenge 2020

Peter M. Full, Fabian Isensee, Paul F. Jäger, Klaus H. Haier-HeinZenodo 2020 · DOI

Abstract

Pretrained model of the winning contribution of the "Multi-Centre, Multi-Vendor &amp; Multi-Disease Cardiac Image Segmentation Challenge (M&amp;Ms)". The model is build with the nnU-Net framework and comprises an ensemble of five 2d and five 3d models. The model can be downloaded (after setting up the nnU-Net framework) using following command <pre><code>nnUNet_download_pretrained_model Task114_heart_mnms </code></pre> Data needs to be available as 3D .nii.gz files. For further specification how to prepare your data see or follow this nnU-Net example on prostate MRI data Once your data is prepared you can run inference with <pre><code># run prediction with 2d nnU-Net nnUNet_predict -i &lt;path_to_input_folder&gt; -o &lt;path_to_temporary_output_folder_2d&gt; --save_npz -t 114 -m 2d -tr nnUNetTrainerV2_MMS # run prediction with 3d nnU-Net nnUNet_predict -i &lt;path_to_input_folder&gt; -o &lt;path_to_temporary_output_folder_3d&gt; --save_npz -t 114 -m 3d_fullres -tr nnUNetTrainerV2_MMS # ensemble 2d and 3d predictions nnUNet_ensemble -f &lt;path_to_temporary_output_folder_2d&gt; &lt;path_to_temporary_output_folder_3d&gt; -o &lt;path_to_final_predictions&gt;</code></pre> Read the original work at Full P.M., Isensee F., Jäger P.F., Maier-Hein K. (2021) Studying Robustness of Semantic Segmentation Under Domain Shift in Cardiac MRI. In: Puyol Anton E. et al. (eds) Statistical Atlases and Computational Models of the Heart. M&amp;Ms and EMIDEC Challenges. STACOM 2020. Lecture Notes in Computer Science, vol 12592. Springer, Cham. https://doi.org/10.1007/978-3-030-68107-4_24
BibTeX
@inproceedings{full2020pretrained,
  author = {Peter M. Full and Fabian Isensee and Paul F. Jäger and Klaus H. Haier-Hein},
  title = {{Pretrained nnU-Net Model from the cMRI M\&amp;Ms Challenge 2020}},
  booktitle = {Zenodo},
  year = {2020},
  doi = {10.5281/zenodo.4134721},
}

Loading related content...

Figure