Update multistage-diagram-segmentation preprocessor

[gvzdv]

I believe there is no corresponding issue for this — correct me if I'm wrong.
Since we've switched to Qwen 3, we are now using a normalized coordinate set (0-1000) as opposed to pixel coordinates produced by Qwen 2.5.

This fix ensures the conversion of normalized coordinates (produced by Qwen) to pixel coordinates (required by SAM).

Tested on Unicorn using examples from the IMAGE website.

Required Information

• I referenced the issue addressed in this PR.
• I described the changes made and how these address the issue.
• I described how I tested these changes.

Coding/Commit Requirements

• I followed applicable coding standards where appropriate (e.g., PEP8)
• I have not committed any models or other large files.

New Component Checklist (mandatory for new microservices)

• I added an entry to docker-compose.yml and build.yml.
• I created A CI workflow under .github/workflows.
• I have created a README.md file that describes what the component does and what it depends on (other microservices, ML models, etc.).

OR

• I have not added a new component in this PR.