用拓扑特征提升心音分割的数据效率，少标注也能准。
TopSeg: A Multi-Scale Topological Framework for Data-Efficient Heart Sound Segmentation
- 基于多尺度拓扑特征捕捉心音动态，结合轻量时序网络解码。
- 在10%数据下仍优于频谱图输入，跨数据集泛化能力强。
- 适合标注数据少、需高稳定性的临床心音分析场景。
基于时频特征的深度学习方法在心音（PCG）分割中虽准确，但依赖大量专家标注数据，限制了鲁棒性与部署。本文提出TopSeg，一种以拓扑表示为核心的框架，通过多尺度拓扑特征编码PCG动态，并使用轻量级时序卷积网络（TCN）解码，配合顺序与持续时间约束的推理步骤。仅在PhysioNet 2016数据集上进行受试者级子采样训练，并在CirCor数据集上外部验证。在相同容量解码器下，拓扑特征始终优于频谱图和包络输入，尤其在低数据预算时优势显著；作为完整系统，TopSeg在相同数据量下超越代表性端到端基线，全量数据下仍具竞争力。10%训练数据下的消融实验表明，所有尺度均贡献显著，结合H_0与H_1可实现更可靠的心音峰（S1/S2）定位与边界稳定性。结果表明，拓扑感知表示为数据高效、跨数据集的PCG分割提供了强归纳偏置，适用于标注数据有限的实际场景。
原文摘要 · Abstract (English)
Deep learning approaches for heart-sound (PCG) segmentation built on time-frequency features can be accurate but often rely on large expert-labeled datasets, limiting robustness and deployment. We present TopSeg, a topological representation-centric framework that encodes PCG dynamics with multi-scale topological features and decodes them using a lightweight temporal convolutional network (TCN) with an order- and duration-constrained inference step. To evaluate data efficiency and generalization, we train exclusively on PhysioNet 2016 dataset with subject-level subsampling and perform external validation on CirCor dataset. Under matched-capacity decoders, the topological features consistently outperform spectrogram and envelope inputs, with the largest margins at low data budgets; as a full system, TopSeg surpasses representative end-to-end baselines trained on their native inputs under the same budgets while remaining competitive at full data. Ablations at 10% training confirm that all scales contribute and that combining H_0 and H_1 yields more reliable S1/S2 localization and boundary stability. These results indicate that topology-aware representations provide a strong inductive bias for data-efficient, cross-dataset PCG segmentation, supporting practical use when labeled data are limited.
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。