Lessons learned from deploying imaging AI with the open PACS-AI platform

arXiv:2609.26981 · cs.CV, cs.CY · Submitted 2026-09-22 · Read on arXiv

cs.CV, cs.CY

Submitted: 2026-09-22

Updated: 2026-09-22

Comments: 28 pages (21 main text + 7 supplementary), 3 figures, 1 table

Code: https://github.com/HeartWise-AI/pacs-ai-backend

License: http://creativecommons.org/licenses/by/4.0/

The gist: We describe deploying imaging AI at six hospitals through PACS-AI, an open self-hosted platform.

Terminology

Abstract

We describe deploying imaging AI at six hospitals through PACS-AI, an open self-hosted platform. The binding constraint is not model accuracy but infrastructure to route studies, display results, capture feedback, and audit what runs. At one center, angiography models completed 515 of 607 jobs (84.8%); failures reflected absent diagnostic views, and 78.1% of 638 clinician ratings were positive. Publishing honest readiness levels for every model is itself a governance practice.

Sources

Related papers