Spatially Varying Label Smoothing: Capturing Uncertainty from Expert Annotations
This addresses calibration issues in medical image segmentation for clinicians, though it is incremental as it builds upon label smoothing.
The paper tackled the problem of noisy image segmentation boundaries by proposing Spatially Varying Label Smoothing (SVLS), a method that captures structural uncertainty from expert annotations, resulting in superior boundary prediction with improved uncertainty and model calibration across four clinical segmentation tasks.
The task of image segmentation is inherently noisy due to ambiguities regarding the exact location of boundaries between anatomical structures. We argue that this information can be extracted from the expert annotations at no extra cost, and when integrated into state-of-the-art neural networks, it can lead to improved calibration between soft probabilistic predictions and the underlying uncertainty. We built upon label smoothing (LS) where a network is trained on 'blurred' versions of the ground truth labels which has been shown to be effective for calibrating output predictions. However, LS is not taking the local structure into account and results in overly smoothed predictions with low confidence even for non-ambiguous regions. Here, we propose Spatially Varying Label Smoothing (SVLS), a soft labeling technique that captures the structural uncertainty in semantic segmentation. SVLS also naturally lends itself to incorporate inter-rater uncertainty when multiple labelmaps are available. The proposed approach is extensively validated on four clinical segmentation tasks with different imaging modalities, number of classes and single and multi-rater expert annotations. The results demonstrate that SVLS, despite its simplicity, obtains superior boundary prediction with improved uncertainty and model calibration.