04 · Case study

PACS with DICOM viewer supported with AI models

A study list, queues and AI workflows on top of PACS and OHIF, aimed at building segmentation models in the clinic without AI experts.

CUBE.AI · PACS · OHIF · Investigational use

Project evidence

PACS and AI workflow

Study review, AI execution, and result delivery in one workflow.

Expert reference
Expert reference
Model result
Model result
Lesion expert reference
Lesion expert reference
Lesion model result
Lesion model result
The task

Run AI workflows from queued PACS studies inside a familiar review workflow.

What we built

A PACS workflow with DICOM viewer support and AI model services (Create Queue, Run Queue, Create Workflow).

The result

Study triage, model execution, and review in one workflow.

Workflow

PACS queueDICOM viewerAI model result

Scope
PACS with DICOM viewer supported by AI
Aim
Building segmentation models in clinic without AI experts
Status
Investigational use only
  • Confirm who CUBE.AI was built for.
  • Re-record study-list demo 12s with synthetic studies (no clideo watermark, MRNs, accession numbers, dates, localhost tabs).
Discuss this projectNext: Multistage AI pipeline for spine segmentation →