Economics achieved through the use of artificial intelligence–powered contouring solutions in a network of oncology clinics in low- and middle-income countries

Background Contouring of target volumes and organs-at-risk (OARs) is among the most time-intensive steps in radiation therapy planning. Artificial intelligence (AI)–based autocontouring has the potential to improve efficiency and reduce clinician workload, particularly in high-volume settings. Methods This multi-center study evaluated time and labor cost savings following implementation of an AI-powered autocontouring solution (AI-Rad Companion Organs RT, Siemens Healthineers) across 18 oncology centers in a low- and middle-income country. Six physicians assessed 116 radiotherapy planning cases across multiple anatomical sites. Time required for manual contouring and post-autocontour editing was recorded. Time savings were converted into monetary value using three clinician cost scenarios, accounting for a notional software usage cost. Results Mean time savings across all cases was 13.8 minutes. After accounting for software costs, net savings ranged from INR 37 to INR 670 per case depending on clinician cost assumptions. Conclusion AI-based autocontouring significantly reduces clinician workload and delivers measurable labor cost savings in routine radiation oncology practice, supporting adoption in LMIC settings.