E pluribus unum: prospective acceptability benchmarking from the Contouring Collaborative for Consensus in Radiation Oncology crowdsourced initiative for multiobserver segmentation.

Diana Lin Kareem A WahidBenjamin E NelmsRenjie HeMohammed A NaserSimon DukeMichael V ShererJohn P ChristodouleasAbdallah S R MohamedMichael CisloJames D MurphyClifton D FullerErin F Gillespie

Published in: Journal of medical imaging (Bellingham, Wash.) (2023)

Multiple nonexpert-generated consensus ROIs met or exceeded expert-derived acceptability thresholds. Five nonexperts could potentially generate consensus segmentations for most ROIs with performance approximating experts, suggesting nonexpert segmentations as feasible cost-effective AI inputs.

Keyphrases

clinical practice
quality improvement
deep learning
artificial intelligence
convolutional neural network
tyrosine kinase
machine learning