clara_ct_seg_spleen_amp is a pre-trained model for volumteric (3D) segmentation of spleen from CT images trained in mixed precision mode using NVIDIA's Automatic Mixed Precision (AMP).
This model is trained using the runnerup [1] awarded pipeline of the "Medical Segmentation Decathlon Challenge 2018" using the AHnet architecture [2] with 32 training images and 9 validation images.
The training dataset is Task09_Spleen.tar from http://medicaldecathlon.com/.
The data must be converted to 1mm resolution before training:
nvmidl-dataconvert -d ${SOURCE_IMAGE_ROOT} -r 1 -s .nii.gz -e .nii.gz -o ${DESTINATION_IMAGE_ROOT}
NOTE: to match up with the default setting, we suggest that ${DESTINATION_IMAGE_ROOT} match DATA_ROOT as defined in environment.json in this MMAR's config folder.
The training was performed with command train_2gpu.sh, which required 12GB-memory GPUs.
Training Graph Input Shape: dynamic
Actual Model Input: 96 x 96 x 96
Input: 1 channel CT image
Output: 2 channels: Label 1: spleen; Label 0: everything else
This model achieve the following Dice score on the validation data (our own split from the training dataset):
In order to access this model please apply for general access:
https://developer.nvidia.com/clara
This model is usable only as part of Transfer Learning & Annotation Tools in Clara Train SDK container. You can download the model from NGC registry as described in Getting Started Guide.
This model is only compatible with Clara Train SDK v2.0 and will not work with v1.1 and v1.0.
This is an example, not to be used for diagnostic purposes
End User License Agreement is included with the product. Licenses are also available along with the model application zip file. By pulling and using the Clara Train SDK container and downloading models, you accept the terms and conditions of these licenses.
[1] Xia, Yingda, et al. "3D Semi-Supervised Learning with Uncertainty-Aware Multi-View Co-Training." arXiv preprint arXiv:1811.12506 (2018). https://arxiv.org/abs/1811.12506.
[2] Liu, Siqi, et al. "3d anisotropic hybrid network: Transferring convolutional features from 2d images to 3d anisotropic volumes." International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, Cham, 2018. https://arxiv.org/abs/1711.08580.