Skip to main content Skip to main navigation



Hayit Greenspan; Anant Madabhush; Parvin Mousavi; Septimiu Salcudean; James Duncan; Tanveer Syeda-Mahmood; Russell Taylor (Hrsg.)
Medical Image Computing and Computer Assisted Intervention (MICCAI-2023), located at 26th International Conference on Medical Image Computing and Computer Assisted Intervention, October 8-12, Vancouver, BC, Canada, Conference paper (LNCS), Vol. 14221, No. Part II, ISBN 978-3-031-43894-3, Springer, Cham, 10/2023.


Active learning algorithms have become increasingly popular for training models with limited data. However, selecting data for annotation remains a challenging problem due to the limited information available on unseen data. To address this issue, we propose EdgeAL, which utilizes the edge information of unseen images as a priori information for measuring uncertainty. The uncertainty is quantified by analyzing the divergence and entropy in model predictions across edges. This measure is then used to select superpixels for annotation. We demonstrate the effectiveness of EdgeAL on multi-class Optical Coherence Tomography (OCT) segmentation tasks, where we achieved a 99% dice score while reducing the annotation label cost to 12%, 2.3%, and 3%, respectively, on three publicly available datasets (Duke, AROI, and UMN). The source code is available at


Weitere Links