NGC | Catalog
Welcome Guest
CatalogModelsclara_train_automl_mri_prostate_cg_and_pz

clara_train_automl_mri_prostate_cg_and_pz

For downloads and more information, please view on a desktop device.

Description

A pre-trained model using AutoML feature for volumetric (3D) segmentation of the prostate central gland and peripheral zone from the multimodal MR (T2, ADC).

Publisher

NVIDIA

Use Case

Segmentation

Framework

Medical

Latest Version

1

Modified

June 23, 2021

Size

20.83 MB

Description

A pre-trained model using AutoML feature for volumetric (3D) segmentation of the prostate central gland and peripheral zone from the multimodal MR (T2, ADC).

Model Overview

Data

This model is trained using the runnerup [1] awarded pipeline of the "Medical Segmentation Decathlon Challenge 2018" using the AHnet architecture [2] with 25 training image pairs and 7 validation images.

Training Data Source: Task05_Prostate.tar from http://medicaldecathlon.com/ The data was converted to resolution 1mm x 1mm x 1mm for training, using the following command.

nvmidl-dataconvert -d ${SOURCE_IMAGE_ROOT} -r 1 -s .nii.gz -e .nii.gz -o ${DESTINATION_IMAGE_ROOT}

Training configuration

The training was performed on 12GB-memory GPUs with the command automl.sh, which ran Clara Train AutoML to perform parameter search [3].

Training Graph Input Shape: 96 x 96 x 32

Input and output formats

Input: 2 channel MR image

Output: 2 channels: Label 1: prostate; Label 0: everything else

Scores

This model achieve the following Dice score on the validation data (our own split from the training dataset):

  1. Prostate: 0.724 (mean_dice1: 0.569 mean_dice2: 0.878)

Availability

In order to access this model please apply for general access:

https://developer.nvidia.com/clara

This model is usable only as part of Clara Train SDK container, you can download the model from NGC registry as described in Getting Started Guide.

Disclaimer

This is an example, not to be used for diagnostic purposes.

License

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.

References

[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.

[3] Yang, Dong, et al. "Searching Learning Strategy with Reinforcement Learning for 3D Medical Image Segmentation." International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, Cham, 2019. https://link.springer.com/chapter/10.1007/978-3-030-32245-8_1.