Unsupervised denoising of the non-invasive fetal electrocardiogram with sparse domain Kalman filtering and vectorcardiographic loop alignment.

Even though the electrocardiogram (ECG) has potential to be used as a monitoring or diagnostic tool for fetuses, the use of non-invasive fetal ECG is complicated by relatively high amounts of noise and fetal movement during the measurement. Moreover, machine learning-based solutions to this problem struggle with the lack of clean reference data, which is difficult to obtain. To solve these problems, this work aims to incorporate fetal rotation correction with electrocardiogram denoising into a single unsupervised end-to-end trainable method.
This method uses the vectorcardiogram (VCG), a 3-dimensional representation of the ECG, as an input and extends the previously introduced Kalman-LISTA method with a Kalman filter for the estimation of fetal rotation, applying denoising to the rotation-corrected VCG. The resulting method was shown to outperform denoising auto-encoders by more than 3dB while achieving a rotation tracking error of less than 33°. Furthermore, the method was shown to be robust to a difference in signal to noise ratio between electrocardiographic leads and different rotational velocities. Future work should aim at improving the method's generalizability and evaluation of the method's value in research and clinical use. This value might not only derive from the denoised fetal ECG, but from the method's objective measure for fetal rotation as well due to it's potential for early detection of fetal complications.