- 學位論文
利用PPG訊號重建QRS波群基於可轉換之注意力機制神經網路
Reconstructing QRS Complex from PPG by Transformed Attentional Neural Networks
摘要
若有技術能將光體積變化描記圖(PPG)轉換成心電圖(ECG)中的QRS波群，將會對需要長時間監測生理訊號的民眾產生革命性的影響。但是要直接從光體積變化描記圖轉換成心電圖是非常具有挑戰性的，因為光體積變化描記圖一般會因為：1. 不同的裝置；2.個體上的差異，而有不同的偏差，使得訊號的對齊校準相當困難。在本篇論文中，我們是首創利用端到端的深度學習方法並藉由光體積變化描記圖重建心電圖中的QRS波群。特別的是，我們提出一個新穎的編碼器–解碼器架構並含有：1.序列轉換網路來自動化校準偏差；2.注意力機制網路來動態地調整對於模型重要的區域；3.加強對於QRS波群的損失函數，以此來達到更好的重建效果。在真實資料集的實驗結果中顯現了我們方法的有效性：對於重建的R尖峰僅有3.67\%偵測失敗率以及對於真實訊號以及重建訊號的脈衝轉換時間具有高相關性。這些結果讓原本昂貴的心電圖臨床研究變得更容易進行，開創了利用光體積變化描記圖重建心電圖的可能性。
並列摘要
Technology that translates photoplethysmogram (PPG) into the QRS complex of electrocardiogram (ECG) would be transformative for people who require continuously monitoring. However, directly decoding the QRS complex of ECG from PPG is challenging because PPG signals usually have different offsets due to 1) different devices, and 2) personal differences, which makes the alignment difficult. In the thesis, we make the first attempt to reconstruct the QRS complex of ECG only from the recording of PPG by an end-to-end deep learning-based approach. Specifically, we propose a novel encoder-decoder architecture containing three components: 1) a sequence transformer network which automatically calibrates the offset, 2) an attention network, which dynamically identifies regions of interest, and 3) a new QRS complex-enhanced loss for better reconstruction. The experiment results on a real dataset demonstrate the effectiveness of the proposed method: 3.67\% R peak failure rate of the reconstructed ECG and high correlation of pulse transit time between the reconstructed QRS complex and the groundtruth QRS complex ($ ho = 0.844$), which creates a new opportunity for low-cost clinical studies via the waveform-level reconstruction of the QRS complex of ECG from PPG.