Related Experiment Video
Updated: Jan 10, 2026
Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
Published on: July 11, 2025
The Impact of Artificial Intelligence Auto-Contouring on Resident Education
Alexander S Qian1, Nikhil V Kotha2, Evan Porter1
1Department of Radiation Oncology, The University of California San Francisco, San Francisco, California.
Purpose:
The integration of artificial intelligence auto-contouring (AAC) in radiation oncology has streamlined the delineation of organs at risk (OARs). Assessing OAR contours is a vital skill in radiation oncology. This study assessed the impact of AAC on residents' contouring education and skill acquisition and its consequences for educational programming.
Methods And Materials:
We conducted a cross-sectional survey of residents and resident-facing faculty at 2 tertiary centers that implemented AAC within the prior year. Respondents completed anonymous Likert (1-5) and free-text items; group differences were analyzed using 2-sample t tests (p ≤ .05). Free-text comments underwent thematic analysis.
Results:
Responses were received from 24 of 30 residents (80%) and 20 of 35 faculty (57%). Compared with faculty, residents more often reported that AAC improved their anatomic understanding (residents: 3.9 vs faculty: 2.1, p < .001) and overall education (4.2 vs 2.3, p < .001). Both groups agreed that AAC reduced time spent contouring (4.6 vs 4.4, p = .39) and improved the workflow from simulation to plan approval (4.5 vs 4.0, p = .08). Perceived AAC contour quality was neutral (3.33 vs 2.85, p = .11). AAC was viewed as improving familiarity with standardized OAR nomenclature (4.3 vs 3.3, p = .001) and as contributing positively to clinic (4.7 vs 3.7, p < .001) and resident well-being (4.6 vs 3.6, p < .001). Faculty comments highlighted inaccurate or incomplete contours and uncertainty about residents' systematic review or correction of AAC output, raising concerns about reduced practice with de novo delineation and computed tomography anatomy. Residents acknowledged AAC's imperfections but emphasized time savings and the ability to redirect effort toward other educational activities.
Conclusions:
Residents and faculty diverge on AAC's educational value, particularly its effect on anatomic learning. However, both recognize benefits for workflow and well-being. Improving the integration and understanding of AAC-derived OARs during contouring will be crucial to improving resident training and ensuring high-quality care delivery in the era of artificial intelligence.
