Authors

• First authors
  • Chang Min Hyun (Yonsei University, South Korea)
  • Tae-Geun Kim (Yonsei University, South Korea)
• Corresponding authors
  • Chang Min Hyun (Yonsei University, South Korea)
  • Kyunghhun Lee (Kyung Hee University, South Korea)

Abstract

This study proposes an unsupervised sequence-to-sequence learning approach that automatically assesses the motion-induced reliability degradation of the cardiac volume signal (CVS) in multi-channel electrical impedance-based hemodynamic monitoring. The proposed method attempts to tackle shortcomings in existing learning-based assessment approaches, such as the requirement of manual annotation for motion influence and the lack of explicit mechanisms for realizing motion-induced abnormalities under contextual variations in CVS over time. By utilizing long-short term memory and variational auto-encoder structures, an encoder--decoder model is trained not only to self-reproduce an input sequence of the CVS but also to extrapolate the future in a parallel fashion. By doing so, the model can capture contextual knowledge lying in a temporal CVS sequence while being regularized to explore a general relationship over the entire time-series. A motion-influenced CVS of low-quality is detected, based on the residual between the input sequence and its neural representation with a cut--off value determined from the two-sigma rule of thumb over the training set. Our experimental observations validated two claims: (i) in the learning environment of label-absence, assessment performance is achievable at a competitive level to the supervised setting, and (ii) the contextual information across a time series of CVS is advantageous for effectively realizing motion-induced unrealistic distortions in signal amplitude and morphology. We also investigated the capability as a pseudo-labeling tool to minimize human-craft annotation by preemptively providing strong candidates for motion-induced anomalies. Empirical evidence has shown that machine-guided annotation can reduce inevitable human-errors during manual assessment while minimizing cumbersome and time-consuming processes.

Important links

• CMPB 108079
• ArXiv: 2305.09368

Citation

@article{HYUN2024108079,
  title         = {Unsupervised sequence-to-sequence learning for automatic signal quality assessment in multi-channel electrical impedance-based hemodynamic monitoring},
  journal       = {Computer Methods and Programs in Biomedicine},
  volume        = {247},
  pages         = {108079},
  year          = {2024},
  issn          = {0169-2607},
  doi           = {https://doi.org/10.1016/j.cmpb.2024.108079},
  url           = {https://www.sciencedirect.com/science/article/pii/S0169260724000750},
  author        = {Chang Min Hyun and Tae-Geun Kim and Kyounghun Lee},
  keywords      = {Cardiopulmonary monitoring, Electrical impedance, Signal quality assessment, Time-series anomaly detection, Unsupervised learning, Recurrent neural network, Variational auto-encoder}
}