Hand-drawn Symbol Recognition of Surgical Flowsheet Graphs with Deep Image Segmentation
This work addresses the computational inaccessibility of perioperative data in low to middle income countries by enabling digitization of surgical flowsheets, though it is incremental as it applies an existing method to a new domain-specific task.
The paper tackled the problem of digitizing hand-drawn symbols on surgical flowsheets in low-resource settings by developing a U-Net-based deep image segmentation method, achieving over 99% accuracy in detecting heart rate and blood pressure symbols and over 95% of predictions within an absolute error of five compared to actual values.
Perioperative data are essential to investigating the causes of adverse surgical outcomes. In some low to middle income countries, these data are computationally inaccessible due to a lack of digitization of surgical flowsheets. In this paper, we present a deep image segmentation approach using a U-Net architecture that can detect hand-drawn symbols on a flowsheet graph. The segmentation mask outputs are post-processed with techniques unique to each symbol to convert into numeric values. The U-Net method can detect, at the appropriate time intervals, the symbols for heart rate and blood pressure with over 99 percent accuracy. Over 95 percent of the predictions fall within an absolute error of five when compared to the actual value. The deep learning model outperformed template matching even with a small size of annotated images available for the training set.