A pre-trained model for volumetric (3D) segmentation of the lung from CT images.
The model is trained using a 3D anisotropic hybrid network .
The training was performed with the following:
This model was trained on a global dataset with a large experimental cohort collected from across the globe. The CT volumes of 120 independent subjects are provided by NIH with experts’ lung region annotations.
Dice score is used for evaluating the performance of the model. On the test set, the trained model achieved score of ~0.95 for lung.
Training acc over 1250 epochs.
Validation mean dice over 1250 epochs.
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 CT image with intensity in HU and arbitary spacing
Augmentation for training:
Output: 2 channels
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.
 Liu, Siqi, et al. "3D Anisotropic Hybrid Network: Transferring Convolutional Features from 2D Images to 3D Anisotropic Volumes." In International Conference on Medical Image Computing and Computer-Assisted Intervention (pp. 851-858). Springer, Cham. https://arxiv.org/pdf/1711.08580.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.