Uncertainty-guided annotation enhances segmentation with the human-in-the-loop

TL;DR

This paper presents Uncertainty-Guided Annotation (UGA), a human-in-the-loop framework that improves medical image segmentation by quantifying model uncertainty and involving clinicians for corrections, enhancing accuracy and trustworthiness.

Contribution

The paper introduces UGA, a novel framework that leverages pixel-level uncertainty to facilitate clinician-guided corrections in medical image segmentation tasks.

Findings

UGA increased Dice coefficient from 0.66 to 0.76 with 5 patches.

Further improvement to 0.84 Dice with 10 patches.

Code is publicly available for community use.

Abstract

Deep learning algorithms, often critiqued for their 'black box' nature, traditionally fall short in providing the necessary transparency for trusted clinical use. This challenge is particularly evident when such models are deployed in local hospitals, encountering out-of-domain distributions due to varying imaging techniques and patient-specific pathologies. Yet, this limitation offers a unique avenue for continual learning. The Uncertainty-Guided Annotation (UGA) framework introduces a human-in-the-loop approach, enabling AI to convey its uncertainties to clinicians, effectively acting as an automated quality control mechanism. UGA eases this interaction by quantifying uncertainty at the pixel level, thereby revealing the model's limitations and opening the door for clinician-guided corrections. We evaluated UGA on the Camelyon dataset for lymph node metastasis segmentation which revealed that UGA improved the Dice coefficient (DC), from 0.66 to 0.76 by adding 5 patches, and further to 0.84 with 10 patches. To foster broader application and community contribution, we have made our code accessible at