Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
skyous 00dff0a148 | 1 year ago | |
---|---|---|
.. | ||
SimpleCRF-master | 1 year ago | |
nnUNet | 1 year ago | |
README.md | 1 year ago | |
WeaklySupervised-GrandChallenge-Logo.jpeg | 1 year ago |
The baseline is built on the combination of 2D nnUNet [1] and fully connected Conditional Random Fields (CRF)[2], which is motivated by Gao et al.'s method in addressing the missing annotation problem [3].
Run
nnUNet_train 2d nnUNetTrainerV2 TaskXXX_MYTASK all
Run
nnUNet_predict -i INPUT_FOLDER -o OUTPUT_FOLDER -t TASK_NAME_OR_ID -m 2d -disable_tta -f all --save_npz
Run
# pull docker image from hub.docker.com
docker pull gospelslave/weakly_suplearn_subtask1
# docker predict command
docker container run --gpus "device=1" --name weakly_suplearn_subtask1 --rm -v $PWD/TestImage/:/workspace/input/ -v $PWD/weakly_suplearn_subtask1_outputs/:/workspace/outputs/ gospelslave/weakly_suplearn_subtask1:latest /bin/bash -c "sh predict.sh"
Run
# pull docker image from hub.docker.com
docker pull gospelslave/weakly_suplearn_subtask2
# docker predict command
docker container run --gpus "device=1" --name weakly_suplearn_subtask2 --rm -v $PWD/TestImage/:/workspace/input/ -v $PWD/weakly_suplearn_subtask2_outputs/:/workspace/outputs/ gospelslave/weakly_suplearn_subtask2:latest /bin/bash -c "sh predict.sh"
Run
# pull docker image from hub.docker.com
docker pull gospelslave/weakly_suplearn_subtask3
# docker predict command
docker container run --gpus "device=1" --name weakly_suplearn_subtask3 --rm -v $PWD/TestImage/:/workspace/input/ -v $PWD/weakly_suplearn_subtask3_outputs/:/workspace/outputs/ gospelslave/weakly_suplearn_subtask3:latest /bin/bash -c "sh predict.sh"
Set input and output path and run
python AbdominalOrganCRFSeg.py
[1] F. Isensee, P. F. Jaeger, S. A. A. Kohl, J. Petersen, and K. H. Maier-Hein, "nnU-Net: a self-confifiguring method for deep learning" based biomedical image segmentation,” Nature Methods, vol. 18, no. 2, pp. 203–211, 2021.
[2] P. Krahenbuhl and V. Koltun, “Efficient inference in fully connected crfs with gaussian edge potentials,” vol. 24, pp. 109–117, 2011.
[3] M. Gao, Z. Xu, L. Lu, A. Wu, I. Nogues, R. M. Summers, and D. J. Mollura, “Segmentation label propagation using deep convolutional neural networks and dense conditional random field,” in 2016 IEEE 13th International Symposium on Biomedical Imaging, pp. 1265–1268, 2016.
We highly appreciate the out-of-the-box implementation of nnU-Net (by Dr. Fabian Isensee) and CRF (by Dr. Guotai Wang).
No Description
Python C++ Pickle C other
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》