AI RESEARCH
Conservative AI for Safety-Sensitive Medical Image Restoration: Residual-Bounded CT-CTA Enhancement for Intracranial Aneurysm-Relevant Signal Recovery
arXiv CS.CV
•
ArXi:2605.16458v1 Announce Type: new Image restoration models are increasingly applied to degraded medical scans, but in safety-sensitive settings they must improve image quality without uncontrolled modification of clinically important regions. This is especially relevant for intracranial CT and CT angiography (CTA), where small vessels and aneurysm-relevant cues lie near high-contrast anatomical boundaries. We frame medical image restoration as a conservative AI problem and present a residual-bounded 2.5D restoration framework trained on synthetically degraded CT/CTA inputs.