针对生物医学分割中结构连续性需求，提出新型损失函数提升连通性。
Preserving instance continuity and length in segmentation through connectivity-aware loss computation
- 设计负中心线损失与简化拓扑损失，增强输出连通性
- 在信号缺失区域显著减少分割断裂，提升实例长度准确性
- 适合需要精确结构完整性分析的生物图像分割任务
在诸多生物医学分割任务中，保持细长结构的连续性和长度比体素级精度更为重要。本文提出两种新型损失函数——负中心线损失与简化拓扑损失，应用于卷积神经网络（CNN），有助于保留输出实例的连通性。同时讨论了下采样、间距校正等实验设计特性对获得连续分割掩码的作用。在3D光片荧光显微镜下的轴突起始段（AIS）数据集上进行评估，该任务因信号丢失易出现不连续问题。相比标准CNN及现有拓扑感知损失，所提方法显著降低每个实例的分割断裂数量，尤其在输入信号缺失区域表现更优，从而改善下游应用中的实例长度计算。结果表明，嵌入结构先验的损失设计可大幅提升生物分割的可靠性。
原文摘要 · Abstract (English)
In many biomedical segmentation tasks, the preservation of elongated structure continuity and length is more important than voxel-wise accuracy. We propose two novel loss functions, Negative Centerline Loss and Simplified Topology Loss, that, applied to Convolutional Neural Networks (CNNs), help preserve connectivity of output instances. Moreover, we discuss characteristics of experiment design, such as downscaling and spacing correction, that help obtain continuous segmentation masks. We evaluate our approach on a 3D light-sheet fluorescence microscopy dataset of axon initial segments (AIS), a task prone to discontinuity due to signal dropout. Compared to standard CNNs and existing topology-aware losses, our methods reduce the number of segmentation discontinuities per instance, particularly in regions with missing input signal, resulting in improved instance length calculation in downstream applications. Our findings demonstrate that structural priors embedded in the loss design can significantly enhance the reliability of segmentation for biological applications.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。