PLAN_012 Diagnosis support endpoint accepts multiple images

Description

This test verifies that the API endpoint for the diagnosis support service accepts 1 to 5 clinical images per request and generates a preliminary diagnosis report by integrating findings from all images.

System requirements

This test can be executed with standard hardware, and it is not necessary to use any specific software. Any commonly available system should be sufficient for the task.

Preconditions

• The entire system (including the reverse proxy, REST API, and all upstream services) is deployed, operational, and accessible online.

Input data

Download this sample image](https://upload.wikimedia.org/wikipedia/commons/6/63/Atopic_dermatitis_child.JPG) to your computer. Using your preferred tool or programming language, convert it to a Base64 string and copy the encoded image into a text file. Next, replace <Paste-the-encoded-image-here> with the encoded image in the JSON payload below. We use the three ellipses inside the media JSON key to show that the image needs to be replaced as many times as there are images to be sent, as indicated by the corresponding test.

{
  "subject": {
    "reference": "fake-patient-id"
  },
  "media": [
    {
      "contentType": "image/jpeg",
      "data": <Paste-the-encoded-image-here>,
    },
    {
      "contentType": "image/jpeg",
      "data": <Paste-again-the-encoded-image-here>,
    },
    // ...
  ]
}

It's okay to use the same image repeatedly for this test, even though the results will be the same whether we use 1 or 5 images. Our goal here is to ensure the API can handle multiple images, not to evaluate the performance of the AI model.

Steps

1. Send three POST requests to the /diagnosis-support endpoint, each with 1, 3, and 5 images. Use the JSON payload from the “Input data” section for this.
2. Verify that the service processes the requests and returns a preliminary diagnosis report for each case.

Expected outcome

• The API service successfully accepts and processes requests with 1, 3, and 5 images.
• A preliminary diagnosis report is generated for each request.
• The report combines individual findings with aggregated results from all the provided images.

Verifies software requirements

• SWR-007

Risk control for

• 6. Incorrect diagnosis or follow up
• 7. Incorrect results shown to patient
• 35. Sensitivity to image variability
• 39. Lack of efficacy or clinical utility

Signature meaning

The signatures for the approval process of this document can be found in the verified commits at the repository for the QMS. As a reference, the team members who are expected to participate in this document and their roles in the approval process, as defined in Annex I Responsibility Matrix of the GP-001, are:

• Tester: JD-017, JD-009, JD-004
• Approver: JD-005