Researchers developed a pioneer surgical anonymization algorithm, validated across various robotic platforms, to remove out-of-body images in real-time. The algorithm successfully achieved a framewise anonymization roc auc-score of 99.46% on unseen procedures, increasing to 99.89% after post-processing. The deep learning model, ROBAN, offers safe real-time anonymization during complex surgical procedures on different robotic platforms, outperforming previous state-of-the-art algorithms even on unseen procedural types.
Journal Article by De Backer P, Simoens J (…) Mottrie A et 12 al. in Ann Surg
Copyright © 2024 The Author(s). Published by Wolters Kluwer Health, Inc.