Strategies to Improve Real-World Applicability of Laparoscopic Anatomy Segmentation Models

arXiv:2403.17192v1 Announce Type: new
Abstract: Accurate identification and localization of anatomical structures of varying size and appearance in laparoscopic imaging are necessary to leverage the potential of computer vision techniques for surgical decision support. Segmentation performance of such models is traditionally reported using metrics of overlap such as IoU. However, imbalanced and unrealistic representation of classes in the training data and suboptimal selection of reported metrics have the potential to skew nominal segmentation performance and thereby ultimately limit clinical translation. …

abstract arxiv computer computer vision cs.cv decision decision support however identification imaging iou localization metrics performance segmentation strategies support type vision world