Combining Hough Transform and Deep Learning Approaches to Reconstruct ECG Signals From Printouts

TL;DR

This paper introduces a robust method combining Hough transform and deep learning to digitize ECG printouts, achieving top performance in the 2024 PhysioNet Challenge and enabling better data diversity for cardiac analysis.

Contribution

The paper presents a novel approach integrating image rotation correction, segmentation, and signal reconstruction to digitize ECGs from printouts, winning the 2024 PhysioNet Challenge.

Findings

Achieved an average CV signal-to-noise ratio of 17.02

Secured first place in the 2024 PhysioNet Challenge

Demonstrated the importance of large, diverse datasets for robustness

Abstract

This work presents our team's (SignalSavants) winning contribution to the 2024 George B. Moody PhysioNet Challenge. The Challenge had two goals: reconstruct ECG signals from printouts and classify them for cardiac diseases. Our focus was the first task. Despite many ECGs being digitally recorded today, paper ECGs remain common throughout the world. Digitising them could help build more diverse datasets and enable automated analyses. However, the presence of varying recording standards and poor image quality requires a data-centric approach for developing robust models that can generalise effectively. Our approach combines the creation of a diverse training set, Hough transform to rotate images, a U-Net based segmentation model to identify individual signals, and mask vectorisation to reconstruct the signals. We assessed the performance of our models using the 10-fold stratified cross-validation (CV) split of 21,799 recordings proposed by the PTB-XL dataset. On the digitisation task, our model achieved an average CV signal-to-noise ratio of 17.02 and an official Challenge score of 12.15 on the hidden set, securing first place in the competition. Our study shows the challenges of building robust, generalisable, digitisation approaches. Such models require large amounts of resources (data, time, and computational power) but have great potential in diversifying the data available.