NGC | Catalog


For downloads and more information, please view on a desktop device.
Logo for clara_pt_brain_mri_segmentation_t1c


A pre-trained model for volumetric (3D) annotation of the tumor core (TC) from MRI scans (T1c).



Use Case



Clara Train

Latest Version



August 10, 2021


36.09 MB

Model Overview

A pre-trained model for volumetric (3D) segmentation of brain tumors from MRIs based on BraTS 2018 data.

Model Architecture

The model is trained to segment the "tumor core" (TC) subregion of primary (gliomas) brain tumors based on 1 input MRI scans (T1c). The TC describes the bulk of the tumor, which is what is typically resected.


This model utilized a similar approach described in 3D MRI brain tumor segmentation using autoencoder regularization, which was a winning method in BraTS2018 [1]. The training was performed with the following:

  • Script:
  • GPU: Atleast 16GB of GPU memory.
  • Actual Model Input: 224 x 224 x 144
  • AMP: True
  • Optimizer: Adam
  • Learning Rate: 1e-4
  • Loss: DiceLoss


The training data is from the Multimodal Brain Tumor Segmentation Challenge (BraTS) 2018.

  • Target: TC tumor subregion
  • Task: Segmentation
  • Modality: MRI
  • Size: 285 3D volumes

The provided labelled 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): 0.8261

Training and Validation

A graph showing the training and the validation loss and dice over 300 epochs.

How to Use this Model

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: 1 channel MRI (T1c at 1 x 1 x 1mm)


  1. Normalizing to unit std with zero mean

Augmentation for training:

  1. Randomly cropping to 224 x 224 x 144
  2. Randomly spatial flipping
  3. Randomly scaling and shifting intensity of the volume


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.


[1] Myronenko, Andriy. "3D MRI brain tumor segmentation using autoencoder regularization." International MICCAI Brainlesion Workshop. Springer, Cham, 2018.


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.