Release Notes

Transfer Learning

Description

Clara Train SDK: Transfer Learning is a containerized Python package that simplifies deep learning tasks on medical image data (such as segmentation from 3D CT/MRI) and enables user to train or fine-tune pretrained models and export them for TensorRT based inference.

Key Features

Clara Train SDK: Transfer Learning includes

  • Configurable framework to simplify deep learning tasks from medical images.

  • Medical Model Archives (MMAR) including deep learning models and artifacts.

  • Model adaptation and retraining that is easy to use in heterogeneous multiple GPU environments.

  • Model Export API for easier deployment of applications to TensorRT based inference.

  • An annotation server - a python based server that is used when the docker run command is executed.

  • Bring Your Own Components - see Bring your own components.

Contents

Components included in this release

  • Transfer Learning and AI Assisted Annotation docker container

  • Medical Model Archives (MMAR) including deep learning models and artifacts.

  • Getting Started Guide containing usage and installation instructions

Software Requirements

Hardware Requirements

Known Issues

When training or fine tuning the models in multi-GPU setting on small number of training data, it is recommended to adjust the learning rate provided in the configuration files, e.g. multiple the learning rate by the GPU number as is recommended in https://arxiv.org/pdf/1706.02677.pdf.

Resolved Issues

The following issues were resolved in this release.

  • SDK stops training when data pipeline fails.

  • The log file info is incomplete when transform fails during training.

  • Evaluation result file overwrites when input files have the same name (but in different folders).

  • Data converter skips dicom images.

  • Model evaluation cannot load a frozen graph with TRT optimization.

  • If label data misses value for a class, during validation, validation mean dice will be computed to 0.

AI Assisted Annotation

Description

Clara Train SDK: AI Assisted Annotation (AIAA) is a feature enabling customers to bring AI-assisted workflows into medical imaging applications accelerating the annotation process with faster 3D segmentation.

Key Features

The release includes these features

  • AI Assisted Annotation for 3D segmentation and analysis.

  • 12 deep learning models for organ annotations.

  • Smart polygon editing for faster and efficient corrections.

  • Flexible C++ and Python API to integrate into a medical imaging application.

  • Adapt and consistently increase annotation accuracy over time using Transfer Learning workflow.

Contents

Components included in this release

  • Annotation server and annotation models.

  • Open Source code on Github for client side integration.

  • Getting Started Guide containing usage and installation instructions.

Software Requirements

Hardware Requirements

Recommended

  • 1 GPU or more

  • 16 GB GPU memory

  • 8 core CPU

  • 32 GB system RAM

  • 80 GB free disk space

Known Issues

When training or fine tuning the models in multi-GPU setting on small number of training data, it is recommended to adjust the learning rate provided in the configuration files, e.g. multiple the learning rate by the GPU number as is recommended in https://arxiv.org/pdf/1706.02677.pdf.

Resolved Issues

There are no resolved issues in this release.

Notices

Notice

THE INFORMATION IN THIS GUIDE AND ALL OTHER INFORMATION CONTAINED IN NVIDIA DOCUMENTATION REFERENCED IN THIS GUIDE IS PROVIDED “AS IS.” NVIDIA MAKES NO WARRANTIES, EXPRESSED, IMPLIED, STATUTORY, OR OTHERWISE WITH RESPECT TO THE INFORMATION FOR THE PRODUCT, AND EXPRESSLY DISCLAIMS ALL IMPLIED WARRANTIES OF NONINFRINGEMENT, MERCHANTABILITY, AND FITNESS FOR A PARTICULAR PURPOSE. Notwithstanding any damages that customer might incur for any reason whatsoever, NVIDIA’s aggregate and cumulative liability towards customer for the product described in this guide shall be limited in accordance with the NVIDIA terms and conditions of sale for the product.

THE NVIDIA PRODUCT DESCRIBED IN THIS GUIDE IS NOT FAULT TOLERANT AND IS NOT DESIGNED, MANUFACTURED OR INTENDED FOR USE IN CONNECTION WITH THE DESIGN, CONSTRUCTION, MAINTENANCE, AND/OR OPERATION OF ANY SYSTEM WHERE THE USE OR A FAILURE OF SUCH SYSTEM COULD RESULT IN A SITUATION THAT THREATENS THE SAFETY OF HUMAN LIFE OR SEVERE PHYSICAL HARM OR PROPERTY DAMAGE (INCLUDING, FOR EXAMPLE, USE IN CONNECTION WITH ANY NUCLEAR, AVIONICS, LIFE SUPPORT OR OTHER LIFE CRITICAL APPLICATION). NVIDIA EXPRESSLY DISCLAIMS ANY EXPRESS OR IMPLIED WARRANTY OF FITNESS FOR SUCH HIGH RISK USES. NVIDIA SHALL NOT BE LIABLE TO CUSTOMER OR ANY THIRD PARTY, IN WHOLE OR IN PART, FOR ANY CLAIMS OR DAMAGES ARISING FROM SUCH HIGH RISK USES.

NVIDIA makes no representation or warranty that the product described in this guide will be suitable for any specified use without further testing or modification. Testing of all parameters of each product is not necessarily performed by NVIDIA. It is customer’s sole responsibility to ensure the product is suitable and fit for the application planned by customer and to do the necessary testing for the application in order to avoid a default of the application or the product. Weaknesses in customer’s product designs may affect the quality and reliability of the NVIDIA product and may result in additional or different conditions and/or requirements beyond those contained in this guide. NVIDIA does not accept any liability related to any default, damage, costs or problem which may be based on or attributable to: (i) the use of the NVIDIA product in any manner that is contrary to this guide, or (ii) customer product designs.

Other than the right for customer to use the information in this guide with the product, no other license, either expressed or implied, is hereby granted by NVIDIA under this guide. Reproduction of information in this guide is permissible only if reproduction is approved by NVIDIA in writing, is reproduced without alteration, and is accompanied by all associated conditions, limitations, and notices.

Trademarks NVIDIA, the NVIDIA logo, and cuBLAS, CUDA, cuDNN, cuFFT, cuSPARSE, DIGITS, DGX, DGX-1, DGX Station, GRID, Jetson, Kepler, NVIDIA GPU Cloud, Maxwell, NCCL, NVLink, Pascal, Tegra, TensorRT, Tesla and Volta are trademarks and/or registered trademarks of NVIDIA Corporation in the Unites States and other countries. Other company and product names may be trademarks of the respective companies with which they are associated.

Copyright © 2019 NVIDIA Corporation. All rights reserved.