11.8. Malaria Microscopy Classification Pipeline

The Malaria Microscopy Classification pipeline is one of the reference pipelines provided with Clara Deploy SDK. A pre-trained model for classification of malaria from PNG images representing the microscopy slides is used in the pipeline. This pipeline depends on the Clara Deploy CLI to send PNG images and trigger a job.

Once the pipeline is started, the AI model classifies input images and saves the output as new images with the classification label burnt-in on top of the images. If the class category of a specific image is “parasitized”, the operator burns in the letter “T” to the upper left corner of the output image, otherwise the letter “F” is written out. The output images can be downloaded by Clara CLI and viewed by any PNG image viewer such as GIMP.

11.8.1. Pipeline Definition

The Malaria Microscopy Classification pipeline is defined in the Clara Deploy pipeline definition language. This pipeline utilizes built-in reference containers to construct the following operator:

  • The ai-app-malaria operator performs AI inference against the NVIDIA TensorRT Inference server to generate malaria classification images.

The following is the details of pipeline definition, with comments describing each operator’s functions as well as input and output.

api-version: 0.4.0
name: malaria-pipeline
operators:
  - name: ai-app-malaria
    description: Classifying Malaria Images
    container:
      image: clara/ai-malaria
      tag: latest
    input:
    - path: /input
    output:
    - path: /output
    services:
    - name: trtis
      container:
        image: nvcr.io/nvidia/tensorrtserver
        tag: 19.08-py3
        command: ["trtserver", "--model-store=$(NVIDIA_CLARA_SERVICE_DATA_PATH)/models"]
      connections:
        http:
        - name: NVIDIA_CLARA_TRTISURI
          port: 8000

11.8.2. Executing the Pipeline

Please refer to the Run Reference Pipelines using Local Input Files in the How to run a Reference Pipeline section to learn how to register a pipeline and execute the pipeline using local input files.