EdgeAL: An Edge Estimation Based Active Learning Approach for OCT Segmentation
This work addresses the challenge of limited annotation data in medical imaging segmentation, specifically for OCT, with incremental improvements in active learning methods.
The paper tackled the problem of selecting data for annotation in active learning for OCT segmentation by proposing EdgeAL, which uses edge information to measure uncertainty and select superpixels for annotation, achieving a 99% dice score while reducing annotation label cost to as low as 2.3% on public datasets.
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 {\it 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 \url{https://github.com/Mak-Ta-Reque/EdgeAL}