Metrics to evaluate the performance of auto-segmentation for radiation treatment planning: A critical review

Highlights: • There is no consensus on the best metrics to assess auto-segmented contours. • Purely geometric measures may not be predictive of clinically meaningful endpoints. • Physician ratings are correlated with clinical outcomes, but difficult to implement. • Multi-domain evaluation is essential to judge the clinical readiness of auto-segmentation. Advances in artificial intelligence-based methods have led to the development and publication of numerous systems for auto-segmentation in radiotherapy. These systems have the potential to decrease contour variability, which has been associated with poor clinical outcomes and increased efficiency in the treatment planning workflow. However, there are no uniform standards for evaluating auto-segmentation platforms to assess their efficacy at meeting these goals. Here, we review the most frequently used evaluation techniques which include geometric overlap, dosimetric parameters, time spent contouring, and clinical rating scales. These data suggest that many of the most commonly used geometric indices, such as the Dice Similarity Coefficient, are not well correlated with clinically meaningful endpoints. As such, a multi-domain evaluation, including composite geometric and/or dosimetric metrics with physician-reported assessment, is necessary to gauge the clinical readiness of auto-segmentation for radiation treatment planning.