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 \href{https://github.com/zifuwanggg/JDTLosses}{https://github.com/zifuwanggg/JDTLosses}.

翻译：软Dice损失（SDL）在医学影像社区的众多自动分割流程中扮演着关键角色。近些年来，其优越性能背后的部分原因已被揭示，并探索了进一步的优化方法。然而，当前尚无支持其在涉及软标签场景中直接使用的实现方式。因此，SDL的使用与软标签利用研究（同样在模型校准情境下）之间的协同作用仍存在缺失。在本文中，我们引入了Dice半度量损失（DMLs），其（i）在设计上于标准硬标签设定下与SDL完全相同，但（ii）可应用于软标签场景。我们在公开的QUBIQ、LiTS和KiTS基准上的实验证实，相较于硬标签（如多数投票和随机选择），DMLs与软标签（如平均化、标签平滑和知识蒸馏）具有潜在协同优势。由此，我们获得了更优的Dice分数和模型校准结果，这支持了DMLs在实践中的更广泛采用。代码可从\href{https://github.com/zifuwanggg/JDTLosses}{https://github.com/zifuwanggg/JDTLosses}获取。