EdgeAL: An Edge Estimation Based Active Learning Approach for OCT Segmentation

TL;DR

EdgeAL introduces a novel active learning method for OCT segmentation that leverages edge information to efficiently select data for annotation, significantly reducing labeling costs while maintaining high accuracy.

Contribution

The paper proposes EdgeAL, an active learning approach that uses edge-based uncertainty to improve OCT segmentation with limited labeled data.

Findings

Achieved 99% dice score on OCT datasets.

Reduced annotation costs to 12%, 2.3%, and 3%.

Effective edge-based uncertainty measurement for data selection.

Abstract

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}