A pre-trained model for volumetric (3D) segmentation of brain tumors from MRIs based on BraTS 2018 data.
The model is trained to annotate the "tumor core" (TC) subregion of primary (gliomas) brain tumors based on 1 input MRI scans (T1c) and 6 extreme points. The TC describes the bulk of the tumor, which is what is typically resected. The annotation algorithm is described in . The network architecture is described in . The workflow is described as below.
This model utilized a similar approach described in 3D MRI brain tumor segmentation using autoencoder regularization, which was a winning method in BraTS2018 . The training was performed with the following:
The training data is from the Multimodal Brain Tumor Segmentation Challenge (BraTS) 2018.
The provided labeled data was partitioned, based on our own split, into training (200 studies), validation (42 studies) and testing (43 studies) datasets.
The model was trained with 200 cases with our own split, as shown in the datalist json file in config folder. The achieved Dice scores on the validation and testing data are:
Tumor core (TC): 0.862 (testing)
The model was validated with NVIDIA hardware and software. For hardware, the model can run on any NVIDIA GPU with memory greater than 16 GB. For software, this model is usable only as part of Transfer Learning & Annotation Tools in Clara Train SDK container. Find out more about Clara Train at the Clara Train Collections on NGC.
Full instructions for the training and validation workflow can be found in our documentation.
Input: 2 channel
Augmentation for training: 3. Randomly spatial flipping 4. Normalizing to unit std with zero mean 5. Randomly scaling and shifting intensity of the volume 6. Add channel of Gaussian heatmap using extreme points
Output: 1 channel TC tumor subregion
This training and inference pipeline was developed by NVIDIA. It is based on a segmentation model developed by NVIDIA researchers. This research use only software has not been cleared or approved by FDA or any regulatory agency. Clara pre-trained models are for developmental purposes only and cannot be used directly for clinical procedures.
 Maninis, Kevis-Kokitsi, et al. "Deep extreme cut: From extreme points to object segmentation." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018. https://arxiv.org/abs/1711.09081.
 Myronenko, Andriy. "3D MRI brain tumor segmentation using autoencoder regularization." International MICCAI Brainlesion Workshop. Springer, Cham, 2018. https://arxiv.org/pdf/1810.11654.pdf.
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.