Predicting Generalization of AI Colonoscopy Models to Unseen Data

arXiv:2403.09920v1 Announce Type: new
Abstract: Background and aims Generalizability of AI colonoscopy algorithms is important for wider adoption in clinical practice. However, current techniques for evaluating performance on unseen data require expensive and time-intensive labels.
Methods We use a "Masked Siamese Network" (MSN) to identify novel phenomena in unseen data and predict polyp detector performance. MSN is trained to predict masked out regions of polyp images, without any labels. We test MSN's ability to be trained on data only from …

abstract adoption algorithms arxiv clinical cs.ai cs.cv cs.cy current data however identify labels msn network novel performance practice type