A Causal Intervention Scheme for Semantic Segmentation of Quasi-periodic Cardiovascular Signals

Precise segmentation is a vital first step to analyze semantic information of cardiac cycle and capture anomaly with cardiovascular signals. However, in the field of deep semantic segmentation, inference is often unilaterally confounded by the individual attribute of data. Towards cardiovascular sig...

Full description

Saved in:
Bibliographic Details
Published in:IEEE journal of biomedical and health informatics 2023-07, Vol.27 (7), p.1-13
Main Authors: Wang, Xingyao, Li, Yuwen, Gao, Hongxiang, Cheng, Xianghong, Li, Jianqing, Liu, Chengyu
Format: Article
Language:English
Subjects:
Biomedical monitoring
cardiovascular signal
causal intervention
Databases, Factual
Electrocardiography
Heart
heart sound
Heart Sounds
Humans
Morphology
Periodicity
QRS-complex
representation learning
Representations
Rhythm
Semantic segmentation
Semantics
Sound
Task analysis
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Precise segmentation is a vital first step to analyze semantic information of cardiac cycle and capture anomaly with cardiovascular signals. However, in the field of deep semantic segmentation, inference is often unilaterally confounded by the individual attribute of data. Towards cardiovascular signals, quasi-periodicity is the essential characteristic to be learned, regarded as the synthesize of the attributes of morphology (A_{m}) and rhythm (A_{r}). Our key insight is to suppress the over-dependence on A_{m} or A_{r} while the generation process of deep representations. To address this issue, we establish a structural causal model as the foundation to customize the intervention approaches on A_{m} and A_{r}, respectively. In this paper, we propose contrastive causal intervention (CCI) to form a novel training paradigm under a frame-level contrastive framework. The intervention can eliminate the implicit statistical bias brought by the single attribute and lead to more objective representations. We conduct comprehensive experiments with the controlled condition for QRS location and heart sound segmentation. The final results indicate that our approach can evidently improve the performance by up to 0.41% for QRS location and 2.73% for heart sound segmentation. The efficiency of the proposed method is generalized to multiple databases and noisy signals.
ISSN:2168-2194
2168-2208
2168-2208
DOI:10.1109/JBHI.2023.3270978