Active Learning for Segmentation by Optimizing Content Information for Maximal Entropy

TL;DR

This paper introduces a novel active learning method for medical image segmentation that maximizes information content and improves annotation efficiency by selecting the most informative samples for manual labeling.

Contribution

It proposes a domain-representativeness penalization scheme and a Borda-count based sample querying method to enhance active learning for segmentation tasks.

Findings

Significantly improved segmentation performance with the proposed method.

Effective sample selection reduces annotation effort.

Outperforms baseline approaches in experiments.

Abstract

Segmentation is essential for medical image analysis tasks such as intervention planning, therapy guidance, diagnosis, treatment decisions. Deep learning is becoming increasingly prominent for segmentation, where the lack of annotations, however, often becomes the main limitation. Due to privacy concerns and ethical considerations, most medical datasets are created, curated, and allow access only locally. Furthermore, current deep learning methods are often suboptimal in translating anatomical knowledge between different medical imaging modalities. Active learning can be used to select an informed set of image samples to request for manual annotation, in order to best utilize the limited annotation time of clinical experts for optimal outcomes, which we focus on in this work. Our contributions herein are two fold: (1) we enforce domain-representativeness of selected samples using a proposed penalization scheme to maximize information at the network abstraction layer, and (2) we propose a Borda-count based sample querying scheme for selecting samples for segmentation. Comparative experiments with baseline approaches show that the samples queried with our proposed method, where both above contributions are combined, result in significantly improved segmentation performance for this active learning task.