cs.CVcs.CY
Lessons learned from deploying imaging AI with the open PACS-AI platform
📅
👥 14 authors
arXiv:2609.26981v1
Authors
Samuel KadouryJulie G. HussinPascal Thériault-LauzierLaurent Létourneau-GuillonRob LewisAdam McArthurGordon J. HarrisHouda BahigPierre-Luc DézielJay KshirsagarJacob L. JaremkoJulien Cohen-AdadJacques DelfrateRobert Avram
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.
Paper Information
- arXiv ID:
- 2609.26981v1
- Published:
Related Categories
cs.CVcs.CY