Clara Deploy AI COVID-19 Classification Operator
CAUTION: This is NOT for diagnostics use.
This asset requires the Clara Deploy SDK. Follow the instructions on the Clara Ansible page to install the Clara Deploy SDK.
This inference pipeline was developed by NVIDIA. It is based on a segmentation and classification model developed by NVIDIA researchers in conjunction with the NIH. The Software is for Research Use Only. Software’s recommendation should not be solely or primarily relied upon to diagnose or treat COVID-19 by a Healthcare Professional. This research use only software has not been cleared or approved by FDA or any regulatory agency
This example is a containerized application, developed for use as one of the operators in the Clara Deploy pipelines. The Docker image for this application is built based on the Clara Deploy Python base container, which provides the interfaces with Clara Deploy SDK.
This application calculates the ratio of two volume images, e.g. the COVID-19 Ground Glass Opacity (GGO) segmentation vs the lung segmentation, where both the segmentation images are inferred from the same lung CT scan, and have the same pixel spacings. The volume images can be in NIfTI or MetaImage format.
The application, in the form of a Docker container, expects an input folder (/input
by default), which needs to be mapped to a folder on the host volume when the Docker container is started. This folder must contain a volume image file in the NIfTI or MetaImage format.
A second volume image file in NIfTI or MetaImage format must also be present in the label image folder (/label_image
by default).
The two volume images must have the same number of pixels and pixel spacings.
The application saves the volume ratio metrics in two txt
files in the output folder, /output
by default. The file names contain the name of the metrics as configured via an environment variable, e.g. covid_lung_ratio
, and postfix with raw_results
and summary_results
. For example, a positive COVID-19 case, the COVID-19 GGO to lung ratio raw results file contains the following.
covid_lung_ratio 0.04211345997147598
The application supports the following environment variables:
NVIDIA_CLARA_INPUT ('/input')
: The folder where the application search for the first volume image file.NVIDIA_CLARA_LABEL_IMAGE ('/label_image')
: The folder where the application search for the second volume image file.NVIDIA_CLARA_OUTPUT ('/output')
: The folder where the application saves the results.NVIDIA_CLARA_LOGS ('/logs')
: The folder for application logs.NVIDIA_CLARA_METRICS_NAME ('covid_lung_ratio')
: The name for the ratio metrics and used as output file name prefix.
The application source code files are in the directory app_volume_ratio
, as shown below
- The
ai4med
directory contains the library modules from Clara Train SDK V2.0, mainly for its transforms functions. - The
custom_libs
directory contains a custom writer which applies SoftMax to the inference results and then writes them to a csv file. - The
ngc
andpublic
directories contain documentation.
app_volume_ratio
├── ai4med
├── app.py
├── custom_libs
│ ├── custom_metric.py
│ └── __init__.py
├── Dockerfile
├── logging_config.json
├── main.py
├── ngc
│ ├── metadata.json
│ └── overview.md
├── public
│ └── docs
│ └── README.md
├── requirements.txt
/input
/output
An End User License Agreement is included with the product. By pulling and using the Clara Deploy asset on NGC, you accept the terms and conditions of these licenses. For Clara Deploy AI COVID-19 Classification Pipeline you accept the terms and conditions that are mentioned in the license file inside the package.
Release Notes, the Getting Started Guide, and the SDK itself are available at the NVIDIA Developer forum.
For answers to any questions you may have about this release, visit the NVIDIA Devtalk forum.