Saved in:
Bibliographic Details
Main Authors: Zhang, Peihong, Li, Zhixin, Liu, Yuxuan, Sang, Rui, Cai, Yiqiang, Tan, Yizhou, Li, Shengchen
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.17346
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918315195105280
author Zhang, Peihong
Li, Zhixin
Liu, Yuxuan
Sang, Rui
Cai, Yiqiang
Tan, Yizhou
Li, Shengchen
author_facet Zhang, Peihong
Li, Zhixin
Liu, Yuxuan
Sang, Rui
Cai, Yiqiang
Tan, Yizhou
Li, Shengchen
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_17346
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TopSeg: A Multi-Scale Topological Framework for Data-Efficient Heart Sound Segmentation
Zhang, Peihong
Li, Zhixin
Liu, Yuxuan
Sang, Rui
Cai, Yiqiang
Tan, Yizhou
Li, Shengchen
Sound
Artificial Intelligence
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.
title TopSeg: A Multi-Scale Topological Framework for Data-Efficient Heart Sound Segmentation
topic Sound
Artificial Intelligence
url https://arxiv.org/abs/2510.17346