Uncertainty-guided annotation enhances segmentation with the human-in-the-loop
This addresses the problem of model uncertainty and out-of-domain data in medical imaging for clinicians, though it is incremental as it builds on existing human-in-the-loop methods.
The paper tackles the challenge of deep learning models lacking transparency for clinical use by introducing the Uncertainty-Guided Annotation (UGA) framework, which improves lymph node metastasis segmentation on the Camelyon dataset, increasing the Dice coefficient from 0.66 to 0.84 with clinician corrections.
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