This Validated Pattern is based on a demo implemetation of an automated data pipeline for chest Xray analysis previously developed by Red Hat. The original demo can be found here.
The Validated Pattern includes the same functionality as the original demonstration. The difference is that we use the GitOps to deploy most of the components which includes operators, creation of namespaces, and cluster configuration.
The Validated Pattern includes:
- Ingest chest Xrays into an object store based on Ceph.
- The Object store sends notifications to a Kafka topic.
- A KNative Eventing Listener to the topic triggers a KNative Serving function.
- An ML-trained model running in a container makes a risk of Pneumonia assessment for incoming images.
- A Grafana dashboard displays the pipeline in real time, along with images incoming, processed and anonymized, as well as full metrics.
This pipeline is showcased in this video.
You can run a check before deployment to make sure that you have the required variables to deploy the Medical Diagnosis Validated Pattern.
You can run make predeploy to check your values. This will allow you to review your values and changed them in
the case there are typos or old values. The values files that should be reviewed prior to deploying the
Medical Diagnosis Validated Pattern are:
| Values File | Description |
|---|---|
| values-secret.yaml | This is the values file that will include the xraylab section with all the database secrets |
| values-global.yaml | File that is used to contain all the global values used by Helm |
Make sure you have the correct domain, clustername, externalUrl, targetBucket and bucketSource values.
Then you can run make install to deploy the Medical Diagnosis Validated Pattern.
This validated pattern is still being developed. More to come in the next few weeks. Any questions or concerns please contact Jonny Rickard or Lester Claudio.