A morphology algorithm based on 2-dimensional flat structure element on ECG baseline wander elimination

Baseline wander always exists along with ECG signal. It is a kind of noise and may interference the diagnosis of cardio diseases, especially for the automatic diagnosis. Most methods could eliminate baseline wander already, however be difficult to meet the requisition of low distortion. To solve this problem, a morphology algorithm based on 2-D flat structure element is proposed, where flat structure element is often employed in previous work. The structure element is designed according to the shape, amplitude, period of the ECG signal itself, for a more accurate approximating to the ECG waveforms. Moreover, such structure element is variable by the feedback of filtered waveforms, which could elevate its robust. This algorithm is tested with the data from 8 files of MIT/BIH arrhythmia database, which contains 8 different shapes in ST segment, covering most of the cardiac conditions. The results are estimated in the baseline elimination as well as the distortion induced by filtering on the P waveform, QRS wave group, and the ST segments of ECG signal. Compared with those arguments of several classical strategies, the signal to noise ratio after processed by morphology based on non-flat structure element reaches the highest among all methods, and the ratio of deformation lowest, which means that this algorithm could both reduce the baseline wander, and control the distortion effectively.