A Novel Method for ECG Paper Records Digitization

Abstract

Most of the ECG test recordings obtained from patients in clinic is in paper records. It is difficult for efficient and automatic diagnosis of cardiac diseases based on paper ECG recordings without expert experiences. Thus, the digitization of ECG papers is of great significance for both basic research and clinical purposes. However, most of current methods extracting signals from single lead ECG images are manual, prohibiting their use for large database. This study proposed an algorithm to extract ECG signals automatically from scanned 12 lead ECG paper recordingsThe original ECG recording images were pre-processed by operations including edge detection, image binarization and skew correction. After pre-processing, ECG waveforms were extracted from background grids based on Connected Component Analysis (CCA). For waveform segmentation, horizontal projection was applied to obtain segmentation boundaries. The ECG signal trace was then traversed to extract ECG signal time series. The extracted signal was plotted by using MATLAB as final ECG signal graphThe proposed algorithm was tested on 129 actual ECG recordings of patients. The results revealed that the extracted signals retained essential features of paper ECG recordings.