Accurately segmenting thin tubular structures, such as vessels, nerves, roads or concrete cracks, is a crucial task in computer vision. Standard deep learning-based segmentation loss functions, such as Dice or Cross-Entropy, focus on volumetric overlap, often at the expense of preserving structural connectivity or topology. This can lead to segmentation errors that adversely affect downstream tasks, including flow calculation, navigation, and structural inspection. Although current topology-focused losses mark an improvement, they introduce significant computational and memory overheads. This is particularly relevant for 3D data, rendering these losses infeasible for larger volumes as well as increasingly important multi-class segmentation problems. To mitigate this, we propose a novel Skeleton Recall Loss, which effectively addresses these challenges by circumventing intensive GPU-based calculations with inexpensive CPU operations. It demonstrates overall superior performance to current state-of-the-art approaches on five public datasets for topology-preserving segmentation, while substantially reducing computational overheads by more than 90%. In doing so, we introduce the first multi-class capable loss function for thin structure segmentation, excelling in both efficiency and efficacy for topology-preservation.

翻译：在计算机视觉中，精确分割细长管状结构（如血管、神经、道路或混凝土裂缝）是一项关键任务。基于深度学习的标准分割损失函数（如Dice损失或交叉熵损失）主要关注体素重叠度，往往以牺牲结构连通性或拓扑完整性为代价。这可能导致分割错误，进而对下游任务（包括流量计算、导航和结构检测）产生不利影响。尽管当前聚焦拓扑保持的损失函数已有所改进，但它们带来了显著的计算与内存开销。这一问题在三维数据中尤为突出，使得这些损失函数难以应用于大规模体积数据以及日益重要的多类别分割问题。为缓解此问题，我们提出了一种新颖的骨架召回损失函数，该方法通过使用轻量级CPU操作替代基于GPU的密集型计算，有效应对上述挑战。在五个用于拓扑保持分割的公开数据集上，该损失函数在整体性能上优于当前最先进方法，同时将计算开销降低90%以上。在此基础上，我们首次提出了适用于多类别细长结构分割的损失函数，在拓扑保持的效率和效能方面均表现出色。