Dice Semimetric Losses: Optimizing the Dice Score with Soft Labels
This work addresses a gap in medical imaging segmentation by enabling the use of soft labels with Dice-based losses, offering incremental improvements for practitioners in automated segmentation pipelines.
The authors tackled the problem of optimizing the Dice score in medical image segmentation by introducing Dice semimetric losses (DMLs), which support soft labels and outperform hard-label methods, achieving superior Dice scores and improved model calibration on benchmarks like QUBIQ, LiTS, and KiTS.
The soft Dice loss (SDL) has taken a pivotal role in numerous automated segmentation pipelines in the medical imaging community. Over the last years, some reasons behind its superior functioning have been uncovered and further optimizations have been explored. However, there is currently no implementation that supports its direct utilization in scenarios involving soft labels. Hence, a synergy between the use of SDL and research leveraging the use of soft labels, also in the context of model calibration, is still missing. In this work, we introduce Dice semimetric losses (DMLs), which (i) are by design identical to SDL in a standard setting with hard labels, but (ii) can be employed in settings with soft labels. Our experiments on the public QUBIQ, LiTS and KiTS benchmarks confirm the potential synergy of DMLs with soft labels (e.g. averaging, label smoothing, and knowledge distillation) over hard labels (e.g. majority voting and random selection). As a result, we obtain superior Dice scores and model calibration, which supports the wider adoption of DMLs in practice. The code is available at https://github.com/zifuwanggg/JDTLosses