Introduction: Three-dimensional (3D) reconstructions of head and neck CT Angiography (CTA) improve anatomical visualization, spatial understanding, and diagnostic confidence. However, manual generation of these reconstructions – often assigned to CT technologists – can take up to over 30 minutes per case, creating workflow inefficiencies, delaying care, and limiting imaging capacity. Lumina 3D TM, an AI-powered solution by RapidAI, automates the production of full-head and neck 3D reconstructions and curved planar reformats (CPRs) within minutes. This study evaluated the impact of Lumina 3D TM on CT technologist workflow efficiency and imaging throughput in a real-world clinical setting. Methods: This retrospective study was conducted at Nebraska Methodist Health System where Lumina 3D TM was installed on 10 CT scanners and evaluated in clinical practice from April 2025 to July 2025. The software’s impact was assessed across 38 CT technologists with varying levels of experience. A random sample of 50 charts from non-stroke patients undergoing head and neck CTA was reviewed (25 charts pre Lumina 3D TM vs 25 charts post Lumina 3D TM). CT technologist time per case included both scanning and manual reconstruction time. The time to reconstruction was calculated as the difference between the “End Exam” timestamps in Cerner and the final reformatted image timestamps in PACS. Reconstruction durations before and after Lumina 3D TM implementation were compared. Results: Before Lumina 3D TM deployment, manual reconstruction averaged 31 minutes per patient. Post-implementation of Lumina 3D TM, automated reconstructions required just 7 minutes, reducing technologist time by 24 minutes (77. 4%). This translates to approximately 81. 6 hours of CT technologists’ time saved monthly (based on ≧204 monthly CTAs), enabling 108 additional scans per month. The increased throughput generated an estimated 43, 000/month in additional imaging revenue (at 405/scan). Conclusion: Implementation of Lumina 3D TM significantly improved CT workflow efficiency by reducing reconstruction time and technologist workload. The resulting time savings enabled increased imaging volume and revenue generation, demonstrating how AI-driven automation can optimize operational capacity and enhance patient throughput in radiology departments.
Cattau et al. (Thu,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: