Open AccessA supervised machine learning semantic segmentation approach for detecting artifacts in plethysmography signals from wearables
Author(s) -
Zhicheng Guo,
Cheng Ding,
Xiao Hu,
Cynthia Rudin
Publication year - 2021
Publication title -
physiological measurement
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.674
H-Index - 101
eISSN - 1361-6579
pISSN - 0967-3334
DOI - 10.1088/1361-6579/ac3b3d
Subject(s) - computer science , artificial intelligence , margin (machine learning) , segmentation , artifact (error) , metric (unit) , pattern recognition (psychology) , wearable computer , set (abstract data type) , test set , modality (human–computer interaction) , machine learning , computer vision , engineering , programming language , operations management , embedded system
Objective . Wearable devices equipped with plethysmography (PPG) sensors provided a low-cost, long-term solution to early diagnosis and continuous screening of heart conditions. However PPG signals collected from such devices often suffer from corruption caused by artifacts. The objective of this study is to develop an effective supervised algorithm to locate the regions of artifacts within PPG signals. Approach . We treat artifact detection as a 1D segmentation problem. We solve it via a novel combination of an active-contour-based loss and an adapted U-Net architecture. The proposed algorithm was trained on the PPG DaLiA training set, and further evaluated on the PPG DaLiA testing set, WESAD dataset and TROIKA dataset. Main results . We evaluated with the DICE score, a well-established metric for segmentation accuracy evaluation in the field of computer vision. The proposed method outperforms baseline methods on all three datasets by a large margin (≈7 percentage points above the next best method). On the PPG DaLiA testing set, WESAD dataset and TROIKA dataset, the proposed method achieved 0.8734 ± 0.0018, 0.9114 ± 0.0033 and 0.8050 ± 0.0116 respectively. The next best method only achieved 0.8068 ± 0.0014, 0.8446 ± 0.0013 and 0.7247 ± 0.0050. Significance . The proposed method is able to pinpoint exact locations of artifacts with high precision; in the past, we had only a binary classification of whether a PPG signal has good or poor quality. This more nuanced information will be critical to further inform the design of algorithms to detect cardiac arrhythmia.